Merge pull request #567 from Paladinium/main_improve_github_actions

Improve paths-filter for Docker github action

.github/ISSUE_TEMPLATE/bug-report-support-request.md

@@ -1,13 +1,14 @@
 ---
-name: Bug report/Support request
-about: Create a report to help us improve
+name: Support Request/Issue
+about: Use this to create a support request or report a bug/issue
 title: ''
 labels: ''
 assignees: ''
 
 ---
+🔴 If you have installed AllTalk in a custom Python environment, I will only be able to provide limited assistance/support. AllTalk draws on a variety of scripts and libraries that are not written or managed by myself, and they may fail, error or give strange results in custom built python environments.
 
-Please generate a diagnostics report and upload the "diagnostics.log".
+🔴 Please generate a diagnostics report and upload the "diagnostics.log" as this helps me understand your configuration.
 
 https://github.com/erew123/alltalk_tts/tree/main?#-how-to-make-a-diagnostics-report-file
 

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1 @@
+blank_issues_enabled: false

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,12 +1,15 @@
 ---
 name: Feature request
-about: Suggest an idea for this project
+about: Use this to create a Feature request
 title: ''
 labels: ''
 assignees: ''
 
 ---
 
+**Please confirm you have read the current Features request list**
+https://github.com/erew123/alltalk_tts/discussions/74
+
 **Is your feature request related to a problem? Please describe.**
 A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
 

.github/actions/docker-setup/action.yml

@@ -0,0 +1,73 @@
+name: 'Setting up docker'
+
+inputs:
+  DOCKERHUB_USERNAME:
+    description: "Docker hub username"
+    required: true
+  DOCKERHUB_REPO_NAME:
+    description: "Docker hub repo name"
+    required: true
+  DOCKERHUB_TOKEN:
+    description: "Docker hub token"
+    required: true
+
+runs:
+  using: "composite"
+  steps:
+    - name: Free Disk Space (Ubuntu)
+      uses: jlumbroso/free-disk-space@v1.3.1
+      with:
+        tool-cache: true
+        swap-storage: false
+        large-packages: false
+    - name: Read variables
+      shell: bash
+      run: |
+        source ./docker/variables.sh
+        for key in "${!ALLTALK_VARS[@]}"
+        do
+          echo "${key}=${ALLTALK_VARS[${key}]}"
+          echo "${key}=${ALLTALK_VARS[${key}]}" >> $GITHUB_ENV
+        done
+
+    - name: Extract version from Git Tag
+      shell: bash {0}
+      run: |
+        # Use the git tag if existing, otherwise 'latest':
+        DOCKER_TAG=$( echo "${{ github.ref }}" | grep -q tags | cut -d'/' -f 3 )
+        if [ -z "${DOCKER_TAG}" ]; then
+          DOCKER_TAG="latest"
+        fi
+        echo "Using DOCKER_TAG=${DOCKER_TAG}"
+        echo "DOCKER_TAG=${DOCKER_TAG}" >> $GITHUB_ENV
+
+    - name: Extract Docker Hub User and Repo Name
+      shell: bash
+      env:
+        DOCKERHUB_USERNAME: ${{ inputs.DOCKERHUB_USERNAME }}
+        DOCKERHUB_REPO_NAME: ${{ inputs.DOCKERHUB_REPO_NAME }}
+      run: |
+        if [ -n "${DOCKERHUB_USERNAME}" ]; then
+          echo "Using Github repository variable 'DOCKERHUB_USERNAME' as Docker hub username with value: '${DOCKERHUB_USERNAME}'"
+          echo "DOCKERHUB_USERNAME=${DOCKERHUB_USERNAME}" >> $GITHUB_ENV
+        else
+          echo "Using Github repository name as Docker hub username"
+          echo "DOCKERHUB_USERNAME=$(echo ${{ github.repository }} | cut -d'/' -f 1)" >> $GITHUB_ENV
+        fi
+
+        if [ -n "${DOCKERHUB_REPO_NAME}" ]; then
+          echo "Using Github repository variable 'DOCKERHUB_REPO_NAME' as Docker hub repo name with value: '${DOCKERHUB_REPO_NAME}'"
+          echo "DOCKERHUB_REPO_NAME=${DOCKERHUB_REPO_NAME}" >> $GITHUB_ENV
+        else
+          echo "Using Github repository name as Docker hub repo name"
+          echo "DOCKERHUB_REPO_NAME=$(echo ${{ github.repository }} | cut -d'/' -f 2)" >> $GITHUB_ENV
+        fi
+
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v3
+
+    - name: Login to DockerHub
+      uses: docker/login-action@v3
+      with:
+        username: ${{ inputs.DOCKERHUB_USERNAME }}
+        password: ${{ inputs.DOCKERHUB_TOKEN }}

.github/workflows/publish-docker-v2.yml

@@ -0,0 +1,124 @@
+name: Publish Docker v2
+
+on:
+  workflow_dispatch:
+  release:
+    types: [ published ]
+  push:
+    branches:
+      - 'alltalkbeta'
+    tags:
+      - 'v*'
+
+# Limit the concurrency of entire workflow runs for a specific branch:
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build_base_environment_docker_image:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Setup docker
+        uses: ./.github/actions/docker-setup
+        with:
+          DOCKERHUB_USERNAME: ${{ vars.DOCKERHUB_USERNAME }}
+          DOCKERHUB_REPO_NAME: ${{ vars.DOCKERHUB_REPO_NAME }}
+          DOCKERHUB_TOKEN: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: |
+            ${{ env.DOCKERHUB_USERNAME }}/${{ env.DOCKERHUB_REPO_NAME }}_environment
+          tags: |
+            # Use sematic versioning on push tag event:
+            type=semver,pattern={{version}}
+            # set latest tag for main and alltalkbeta branch:
+            type=raw,value=latest,enable=${{ github.ref == format('refs/heads/{0}', 'main') || github.ref == format('refs/heads/{0}', 'alltalkbeta') }}
+
+      - uses: dorny/paths-filter@v3
+        id: changes
+        with:
+          base: 'alltalkbeta'
+          filters: |
+            docker-base:
+              - 'docker/variables.sh'
+              - 'docker/base/Dockerfile'
+            docker-workflow:
+              - '.github/workflows/publish-docker*.yml'
+
+      - name: Build and push base Docker image
+        if: |
+          steps.changes.outputs.docker-base == 'true' ||
+          steps.changes.outputs.docker-workflow == 'true' ||
+          github.event_name == 'release' ||
+          (github.event_name == 'push' && contains(github.ref, 'refs/tags/'))
+        uses: docker/build-push-action@v6
+        with:
+          context: ./docker/base
+          file: ./docker/base/Dockerfile
+          platforms: "linux/amd64"
+          push: true
+          build-args: |
+            CUDA_VERSION=${{ env.CUDA_VERSION }}
+            PYTHON_VERSION=${{ env.PYTHON_VERSION }}
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=registry,ref=${{ env.DOCKERHUB_USERNAME }}/${{ env.DOCKERHUB_REPO_NAME }}_environment:buildcache
+          cache-to: type=registry,ref=${{ env.DOCKERHUB_USERNAME }}/${{ env.DOCKERHUB_REPO_NAME }}_environment:buildcache,mode=max
+
+  build_main_docker_image:
+    needs: build_base_environment_docker_image
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        tts: [ xtts, vits, piper ]
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Setup docker
+        uses: ./.github/actions/docker-setup
+        with:
+          DOCKERHUB_USERNAME: ${{ vars.DOCKERHUB_USERNAME }}
+          DOCKERHUB_REPO_NAME: ${{ vars.DOCKERHUB_REPO_NAME }}
+          DOCKERHUB_TOKEN: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: |
+            ${{ env.DOCKERHUB_USERNAME }}/${{ env.DOCKERHUB_REPO_NAME }}
+          flavor: |
+            suffix=-${{ matrix.tts }},onlatest=true
+          tags: |
+            # Use sematic versioning on push tag event:
+            type=semver,pattern={{version}}
+            # set latest tag for main and alltalkbeta branch:
+            type=raw,value=latest,enable=${{ github.ref == format('refs/heads/{0}', 'main') || github.ref == format('refs/heads/{0}', 'alltalkbeta') }}
+
+      - name: Build and push base Docker image
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: ./Dockerfile
+          platforms: "linux/amd64"
+          push: true
+          build-args: |
+            TTS_MODEL=${{ matrix.tts }}
+            ALLTALK_DIR=${{ env.ALLTALK_DIR }}
+            DEEPSPEED_VERSION=${{ env.DEEPSPEED_VERSION }}
+            DOCKER_TAG=${{ env.DOCKER_TAG }}
+            DOCKER_REPOSITORY=${{ env.DOCKERHUB_USERNAME }}/
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=registry,ref=${{ env.DOCKERHUB_USERNAME }}/${{ env.DOCKERHUB_REPO_NAME }}:buildcache-${{ matrix.tts }}
+          cache-to: type=registry,ref=${{ env.DOCKERHUB_USERNAME }}/${{ env.DOCKERHUB_REPO_NAME }}:buildcache-${{ matrix.tts }},mode=max

.github/workflows/publish-docker.yml

@@ -1,8 +1,8 @@
-name: Publish Docker image
+name: Publish Docker image (main branch)
 
 on:
-  push:
-    branches: [main]
+#  push:
+#    branches: [main]
   release:
     types: [published]
   workflow_dispatch:

.github/workflows/python-ci.yml

@@ -0,0 +1,53 @@
+# This workflow will install Python dependencies, run tests and lint with a single version of Python
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
+
+name: Python CI
+
+on: [push, pull_request]
+
+permissions:
+  contents: read
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python 3.11.9
+        uses: actions/setup-python@v3
+        if: ${{ hashFiles('./test') != '' }}
+        with:
+          python-version: "3.11.9"
+      - name: Install dependencies
+        if: ${{ hashFiles('./test') != '' }}
+        run: |
+          python -m pip install --upgrade pip
+          if [ -f system/requirements/requirements_unit_test.txt ]; then
+            pip install -r system/requirements/requirements_unit_test.txt;
+          fi
+      - name: Test with pytest
+        if: ${{ hashFiles('./test') != '' }}
+        run: |
+          pytest test --doctest-modules --junitxml=junit/test-results.xml --cov=com --cov-report=xml --cov-report=html
+      - name: Surface failing tests
+        if: always()
+        uses: pmeier/pytest-results-action@v0.6.0
+        with:
+          # A list of JUnit XML files, directories containing the former, and wildcard
+          # patterns to process.
+          # See @actions/glob for supported patterns.
+          path: junit/test-results.xml
+
+          # (Optional) Add a summary of the results at the top of the report
+          summary: true
+
+          # (Optional) Select which results should be included in the report.
+          # Follows the same syntax as `pytest -r`
+          display-options: fEX
+
+          # (Optional) Fail the workflow if no JUnit XML was found.
+          fail-on-empty: false
+
+          # (Optional) Title of the test results section in the workflow summary
+          title: Test results

Deepspeed-Windows/11.1/csrc/quantization/pt_binding.cpp

@@ -1,285 +0,0 @@
-// Copyright (c) Microsoft Corporation.
-// SPDX-License-Identifier: Apache-2.0
-
-// DeepSpeed Team
-
-#include <ATen/cuda/CUDAContext.h>
-#include <torch/extension.h>
-#include <cassert>
-#include <vector>
-#include "quantization.h"
-
-template <typename T>
-at::Tensor ds_quantize(at::Tensor& vals, int groups, int bits)
-{
-    auto t_size = vals.sizes();
-    int size = 1;
-    for (auto dim : t_size) size *= dim;
-
-    if ((((size / groups) - 1) / 4096 + 1) <= 256) {
-        launch_fake_quantize_kernel(
-            (T*)vals.data_ptr(), size, groups, bits, at::cuda::getCurrentCUDAStream());
-    }
-    return vals;
-}
-
-template <typename T>
-at::Tensor ds_sr_quantize(at::Tensor& vals, int groups, int bits)
-{
-    auto t_size = vals.sizes();
-    int size = 1;
-    for (auto dim : t_size) size *= dim;
-
-    if (((size / groups) / 4 / 1024) <= 256) {
-        launch_sr_fake_quantize_kernel(
-            (T*)vals.data_ptr(), size, groups, bits, at::cuda::getCurrentCUDAStream());
-    }
-    return vals;
-}
-
-template <typename T>
-at::Tensor ds_quantize_asym(at::Tensor& vals, int groups, int bits)
-{
-    auto t_size = vals.sizes();
-    int size = 1;
-    for (auto dim : t_size) size *= dim;
-
-    if ((((size / groups) - 1) / 4096 + 1) <= 256) {
-        launch_fake_quantize_kernel_asym(
-            (T*)vals.data_ptr(), size, groups, bits, at::cuda::getCurrentCUDAStream());
-    }
-    return vals;
-}
-
-template <typename T>
-at::Tensor ds_sr_quantize_asym(at::Tensor& vals, int groups, int bits)
-{
-    auto t_size = vals.sizes();
-    int size = 1;
-    for (auto dim : t_size) size *= dim;
-
-    if (((size / groups) / 4 / 1024) <= 256) {
-        launch_sr_fake_quantize_kernel_asym(
-            (T*)vals.data_ptr(), size, groups, bits, at::cuda::getCurrentCUDAStream());
-    }
-    return vals;
-}
-
-std::vector<at::Tensor> quantize_kernel(at::Tensor& input_vals,
-                                        int groups,
-                                        int numBits,
-                                        quantize::Type quantType)
-{
-    auto dtype = at::kFloat;
-    auto params_options = at::TensorOptions()
-                              .dtype(dtype)
-                              .layout(at::kStrided)
-                              .device(at::kCUDA)
-                              .requires_grad(false);
-    const int param_elems = (quantize::requires_offset(quantType)) ? 2 : 1;
-    auto params = torch::empty({groups, param_elems}, params_options);
-
-    auto output_options = at::TensorOptions()
-                              .dtype(at::kChar)
-                              .layout(at::kStrided)
-                              .device(at::kCUDA)
-                              .requires_grad(false);
-
-    auto output_sizes = input_vals.sizes().vec();
-    output_sizes[output_sizes.size() - 1] /= numBits == 8 ? 1 : 2;
-    auto output = torch::empty(output_sizes, output_options);
-
-    const int elems_per_group = at::numel(input_vals) / groups;
-
-    launch_quant((int8_t*)output.data_ptr(),
-                 (float*)params.data_ptr(),
-                 (__half*)input_vals.data_ptr(),
-                 groups,
-                 elems_per_group,
-                 numBits,
-                 quantType,
-                 at::cuda::getCurrentCUDAStream());
-
-    return {output, params};
-}
-
-template <typename T>
-at::Tensor dequantize(at::Tensor& quantized_data,
-                      at::Tensor& params,
-                      int groups,
-                      int num_bits,
-                      quantize::Type quant_type)
-{
-    auto dtype = (std::is_same<T, float>::value) ? torch::kFloat32 : torch::kFloat16;
-    auto output_options = at::TensorOptions()
-                              .dtype(dtype)
-                              .layout(at::kStrided)
-                              .device(at::kCUDA)
-                              .requires_grad(false);
-
-    auto output_sizes = quantized_data.sizes().vec();
-    output_sizes[output_sizes.size() - 1] *= num_bits == 8 ? 1 : 2;
-    auto output = torch::empty(output_sizes, output_options);
-
-    const int total_elems = at::numel(output);
-    const int elems_per_group = total_elems / groups;
-
-    launch_dequantize_kernel((T*)output.data_ptr(),
-                             (const int8_t*)quantized_data.data_ptr(),
-                             (const float*)params.data_ptr(),
-                             quant_type,
-                             num_bits,
-                             elems_per_group,
-                             total_elems,
-                             at::cuda::getCurrentCUDAStream());
-
-    return output;
-}
-
-at::Tensor dequantize_int4_to_half_experimental(at::Tensor& data_in,
-                                                at::Tensor& scale_buffer,
-                                                at::Tensor& min_val_buffer,
-                                                int num_group,
-                                                int group_size)
-{
-    auto output_options = at::TensorOptions().dtype(at::kHalf).device(at::kCUDA);
-    auto output = torch::empty({num_group, group_size}, output_options);
-
-    launch_dequantize_int4_to_half_experimental((uint8_t*)data_in.data_ptr(),
-                                                (half*)output.data_ptr(),
-                                                (half*)scale_buffer.data_ptr(),
-                                                (half*)min_val_buffer.data_ptr(),
-                                                num_group,
-                                                group_size,
-                                                at::cuda::getCurrentCUDAStream());
-
-    return output;
-}
-
-std::vector<at::Tensor> ds_swizzle_quant(at::Tensor& input_vals,
-                                         int groups,
-                                         int num_bits,
-                                         quantize::Type quant_type,
-                                         int pipeline_size,
-                                         int nodes,
-                                         int devices_per_node)
-{
-    auto scales_options = at::TensorOptions()
-                              .dtype(at::kFloat)
-                              .layout(at::kStrided)
-                              .device(at::kCUDA)
-                              .requires_grad(false);
-    const int scales_elems = (quantize::requires_offset(quant_type)) ? 2 : 1;
-    auto scales = torch::empty({groups, scales_elems}, scales_options);
-
-    auto output_options = at::TensorOptions()
-                              .dtype(at::kChar)
-                              .layout(at::kStrided)
-                              .device(at::kCUDA)
-                              .requires_grad(false);
-
-    const int quantization_scalar = 8 / num_bits;
-    const int compressed_vals = at::numel(input_vals) / quantization_scalar;
-
-    auto output = torch::empty({compressed_vals}, output_options);
-    const int elems_per_group = at::numel(input_vals) / groups;
-
-    launch_swizzled_quant((int8_t*)output.data_ptr(),
-                          (float*)scales.data_ptr(),
-                          (__half*)input_vals.data_ptr(),
-                          num_bits,
-                          quant_type,
-                          groups,
-                          elems_per_group,
-                          pipeline_size,
-                          nodes,
-                          devices_per_node,
-                          at::cuda::getCurrentCUDAStream());
-
-    return {output, scales};
-}
-
-std::vector<at::Tensor> quantized_reduction(at::Tensor& input_vals,
-                                            at::Tensor& input_scales,
-                                            int in_groups,
-                                            int out_groups,
-                                            int num_bits,
-                                            quantize::Type quant_type,
-                                            int devices_per_node)
-{
-    auto scales_options = at::TensorOptions()
-                              .dtype(at::kFloat)
-                              .layout(at::kStrided)
-                              .device(at::kCUDA)
-                              .requires_grad(false);
-    const int scales_elems = (quantize::requires_offset(quant_type)) ? 2 : 1;
-    auto scales = torch::empty({out_groups, scales_elems}, scales_options);
-
-    auto output_options = at::TensorOptions()
-                              .dtype(at::kChar)
-                              .layout(at::kStrided)
-                              .device(at::kCUDA)
-                              .requires_grad(false);
-
-     std::vector<int64_t> sz_vector(input_vals.sizes().begin(), input_vals.sizes().end());
-     sz_vector[sz_vector.size() - 1] = sz_vector.back() / devices_per_node;  // num of GPU per nodes
-     at::IntArrayRef sz(sz_vector);
-     auto output = torch::empty(sz, output_options);
-
-     const int elems_per_in_tensor = at::numel(input_vals) / devices_per_node;
-     const int elems_per_in_group = elems_per_in_tensor / (in_groups / devices_per_node);
-     const int elems_per_out_group = elems_per_in_tensor / out_groups;
-
-// old code:
-//    std::vector<long int> sz(input_vals.sizes().begin(), input_vals.sizes().end());
-//    sz[sz.size() - 1] = sz.back() / devices_per_node;  // num of GPU per nodes
-//    const int elems_per_in_tensor = at::numel(input_vals) / devices_per_node;
-//    auto output = torch::empty(sz, output_options);
-
-//    const int elems_per_in_group = elems_per_in_tensor / (in_groups / devices_per_node);
-//    const int elems_per_out_group = elems_per_in_tensor / out_groups;
-
-    launch_dequant_reduce((int8_t*)output.data_ptr(),
-                          (float*)scales.data_ptr(),
-                          (const int8_t*)input_vals.data_ptr(),
-                          (const float*)input_scales.data_ptr(),
-                          devices_per_node,
-                          num_bits,
-                          quant_type,
-                          out_groups,
-                          elems_per_out_group,
-                          elems_per_in_tensor,
-                          in_groups / devices_per_node,
-                          elems_per_in_group,
-                          at::cuda::getCurrentCUDAStream());
-    return {output, scales};
-}
-
-PYBIND11_MODULE(TORCH_EXTENSION_NAME, m)
-{
-    m.def("ds_quantize_fp32", &ds_quantize<float>, "DeepSpeed Quantize with fp32 (CUDA)");
-    m.def("ds_quantize_fp16", &ds_quantize<__half>, "DeepSpeed Quantize with fp16 (CUDA)");
-    m.def("ds_sr_quantize_fp32", &ds_sr_quantize<float>, "DeepSpeed Quantize with fp32 (CUDA)");
-    m.def("ds_sr_quantize_fp16", &ds_sr_quantize<__half>, "DeepSpeed Quantize with fp16 (CUDA)");
-    m.def("ds_quantize_asym_fp32", &ds_quantize_asym<float>, "DeepSpeed Quantize with fp32 (CUDA)");
-    m.def(
-        "ds_quantize_asym_fp16", &ds_quantize_asym<__half>, "DeepSpeed Quantize with fp16 (CUDA)");
-    m.def("ds_sr_quantize_asym_fp32",
-          &ds_sr_quantize_asym<float>,
-          "DeepSpeed Quantize with fp32 (CUDA)");
-    m.def("ds_sr_quantize_asym_fp16",
-          &ds_sr_quantize_asym<__half>,
-          "DeepSpeed Quantize with fp16 (CUDA)");
-    pybind11::enum_<quantize::Type>(m, "QuantizationType")
-        .value("Symmetric", quantize::Type::Symmetric)
-        .value("Asymmetric", quantize::Type::Asymmetric)
-        .export_values();
-    m.def("quantize", &quantize_kernel);
-    m.def("dequantize", &dequantize<__half>);
-    m.def("dequantize_fp32", &dequantize<float>);
-    m.def("dequantize_int4_to_half_experimental",
-          &dequantize_int4_to_half_experimental,
-          "Dequantize int4 to half (experimental)");
-    m.def("swizzle_quant", &ds_swizzle_quant);
-    m.def("quantized_reduction", &quantized_reduction);
-}

Deepspeed-Windows/11.1/deepspeed/env_report.py

@@ -1,160 +0,0 @@
-# Copyright (c) Microsoft Corporation.
-# SPDX-License-Identifier: Apache-2.0
-
-# DeepSpeed Team
-
-import os
-import torch
-import deepspeed
-import subprocess
-import argparse
-import psutil
-from .ops.op_builder.all_ops import ALL_OPS
-from .git_version_info import installed_ops, torch_info
-from deepspeed.accelerator import get_accelerator
-
-GREEN = '\033[92m'
-RED = '\033[91m'
-YELLOW = '\033[93m'
-END = '\033[0m'
-SUCCESS = f"{GREEN} [SUCCESS] {END}"
-OKAY = f"{GREEN}[OKAY]{END}"
-WARNING = f"{YELLOW}[WARNING]{END}"
-FAIL = f'{RED}[FAIL]{END}'
-INFO = '[INFO]'
-
-color_len = len(GREEN) + len(END)
-okay = f"{GREEN}[OKAY]{END}"
-warning = f"{YELLOW}[WARNING]{END}"
-
-
-def op_report(verbose=True):
-    max_dots = 23
-    max_dots2 = 11
-    h = ["op name", "installed", "compatible"]
-    print("-" * (max_dots + max_dots2 + len(h[0]) + len(h[1])))
-    print("DeepSpeed C++/CUDA extension op report")
-    print("-" * (max_dots + max_dots2 + len(h[0]) + len(h[1])))
-
-    print("NOTE: Ops not installed will be just-in-time (JIT) compiled at\n"
-          "      runtime if needed. Op compatibility means that your system\n"
-          "      meet the required dependencies to JIT install the op.")
-
-    print("-" * (max_dots + max_dots2 + len(h[0]) + len(h[1])))
-    print("JIT compiled ops requires ninja")
-    ninja_status = OKAY if ninja_installed() else FAIL
-    print('ninja', "." * (max_dots - 5), ninja_status)
-    print("-" * (max_dots + max_dots2 + len(h[0]) + len(h[1])))
-    print(h[0], "." * (max_dots - len(h[0])), h[1], "." * (max_dots2 - len(h[1])), h[2])
-    print("-" * (max_dots + max_dots2 + len(h[0]) + len(h[1])))
-    installed = f"{GREEN}[YES]{END}"
-    no = f"{YELLOW}[NO]{END}"
-    for op_name, builder in ALL_OPS.items():
-        dots = "." * (max_dots - len(op_name))
-        is_compatible = OKAY if builder.is_compatible(verbose) else no
-        is_installed = installed if installed_ops.get(op_name, False) else no
-        dots2 = '.' * ((len(h[1]) + (max_dots2 - len(h[1]))) - (len(is_installed) - color_len))
-        print(op_name, dots, is_installed, dots2, is_compatible)
-    print("-" * (max_dots + max_dots2 + len(h[0]) + len(h[1])))
-
-
-def ninja_installed():
-    try:
-        import ninja  # noqa: F401 # type: ignore
-    except ImportError:
-        return False
-    return True
-
-
-def nvcc_version():
-    import torch.utils.cpp_extension
-    cuda_home = torch.utils.cpp_extension.CUDA_HOME
-    if cuda_home is None:
-        return f"{RED} [FAIL] cannot find CUDA_HOME via torch.utils.cpp_extension.CUDA_HOME={torch.utils.cpp_extension.CUDA_HOME} {END}"
-    try:
-        output = subprocess.check_output([cuda_home + "/bin/nvcc", "-V"], universal_newlines=True)
-    except FileNotFoundError:
-        return f"{RED} [FAIL] nvcc missing {END}"
-    output_split = output.split()
-    release_idx = output_split.index("release")
-    release = output_split[release_idx + 1].replace(',', '').split(".")
-    return ".".join(release)
-
-
-def get_shm_size():
-    try:
-        temp_dir = os.getenv('TEMP') or os.getenv('TMP') or os.path.join(os.path.expanduser('~'), 'tmp')
-        shm_stats = psutil.disk_usage(temp_dir)
-        shm_size = shm_stats.total
-        shm_hbytes = human_readable_size(shm_size)
-        warn = []
-        if shm_size < 512 * 1024**2:
-            warn.append(
-                f" {YELLOW} [WARNING] Shared memory size might be too small, consider increasing it. {END}"
-            )
-            # Add additional warnings specific to your use case if needed.
-        return shm_hbytes, warn
-    except Exception as e:
-        return "UNKNOWN", [f"Error getting shared memory size: {e}"]
-
-def human_readable_size(size):
-    units = ['B', 'KB', 'MB', 'GB', 'TB']
-    i = 0
-    while size >= 1024 and i < len(units) - 1:
-        size /= 1024
-        i += 1
-    return f'{size:.2f} {units[i]}'
-
-
-def debug_report():
-    max_dots = 33
-
-    report = [("torch install path", torch.__path__), ("torch version", torch.__version__),
-              ("deepspeed install path", deepspeed.__path__),
-              ("deepspeed info", f"{deepspeed.__version__}, {deepspeed.__git_hash__}, {deepspeed.__git_branch__}")]
-    if get_accelerator().device_name() == 'cuda':
-        hip_version = getattr(torch.version, "hip", None)
-        report.extend([("torch cuda version", torch.version.cuda), ("torch hip version", hip_version),
-                       ("nvcc version", (None if hip_version else nvcc_version())),
-                       ("deepspeed wheel compiled w.", f"torch {torch_info['version']}, " +
-                        (f"hip {torch_info['hip_version']}" if hip_version else f"cuda {torch_info['cuda_version']}"))
-                       ])
-    else:
-        report.extend([("deepspeed wheel compiled w.", f"torch {torch_info['version']} ")])
-
-    report.append(("shared memory (/dev/shm) size", get_shm_size()))
-
-    print("DeepSpeed general environment info:")
-    for name, value in report:
-        warns = []
-        if isinstance(value, tuple):
-            value, warns = value
-        print(name, "." * (max_dots - len(name)), value)
-        if warns:
-            for warn in warns:
-                print(warn)
-
-
-def parse_arguments():
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--hide_operator_status',
-                        action='store_true',
-                        help='Suppress display of installation and compatibility statuses of DeepSpeed operators. ')
-    parser.add_argument('--hide_errors_and_warnings', action='store_true', help='Suppress warning and error messages.')
-    args = parser.parse_args()
-    return args
-
-
-def main(hide_operator_status=False, hide_errors_and_warnings=False):
-    if not hide_operator_status:
-        op_report(verbose=not hide_errors_and_warnings)
-    debug_report()
-
-
-def cli_main():
-    args = parse_arguments()
-    main(hide_operator_status=args.hide_operator_status, hide_errors_and_warnings=args.hide_errors_and_warnings)
-
-
-if __name__ == "__main__":
-    main()

Deepspeed-Windows/11.2/csrc/quantization/pt_binding.cpp

@@ -1,299 +0,0 @@
-// Copyright (c) Microsoft Corporation.
-// SPDX-License-Identifier: Apache-2.0
-
-// DeepSpeed Team
-
-#include <ATen/cuda/CUDAContext.h>
-#include <torch/extension.h>
-#include <cassert>
-#include <vector>
-#include "quantization.h"
-
-template <typename T>
-at::Tensor ds_quantize(at::Tensor& vals, int groups, int bits)
-{
-    auto t_size = vals.sizes();
-    int size = 1;
-    for (auto dim : t_size) size *= dim;
-
-    if ((((size / groups) - 1) / 4096 + 1) <= 256) {
-        launch_fake_quantize_kernel(
-            (T*)vals.data_ptr(), size, groups, bits, at::cuda::getCurrentCUDAStream());
-    }
-    return vals;
-}
-
-template <typename T>
-at::Tensor ds_sr_quantize(at::Tensor& vals, int groups, int bits)
-{
-    auto t_size = vals.sizes();
-    int size = 1;
-    for (auto dim : t_size) size *= dim;
-
-    if (((size / groups) / 4 / 1024) <= 256) {
-        launch_sr_fake_quantize_kernel(
-            (T*)vals.data_ptr(), size, groups, bits, at::cuda::getCurrentCUDAStream());
-    }
-    return vals;
-}
-
-template <typename T>
-at::Tensor ds_quantize_asym(at::Tensor& vals, int groups, int bits)
-{
-    auto t_size = vals.sizes();
-    int size = 1;
-    for (auto dim : t_size) size *= dim;
-
-    if ((((size / groups) - 1) / 4096 + 1) <= 256) {
-        launch_fake_quantize_kernel_asym(
-            (T*)vals.data_ptr(), size, groups, bits, at::cuda::getCurrentCUDAStream());
-    }
-    return vals;
-}
-
-template <typename T>
-at::Tensor ds_sr_quantize_asym(at::Tensor& vals, int groups, int bits)
-{
-    auto t_size = vals.sizes();
-    int size = 1;
-    for (auto dim : t_size) size *= dim;
-
-    if (((size / groups) / 4 / 1024) <= 256) {
-        launch_sr_fake_quantize_kernel_asym(
-            (T*)vals.data_ptr(), size, groups, bits, at::cuda::getCurrentCUDAStream());
-    }
-    return vals;
-}
-
-std::vector<at::Tensor> quantize_kernel(at::Tensor& input_vals,
-                                        int groups,
-                                        int numBits,
-                                        quantize::Type quantType)
-{
-    auto dtype = at::kFloat;
-    auto params_options = at::TensorOptions()
-                              .dtype(dtype)
-                              .layout(at::kStrided)
-                              .device(at::kCUDA)
-                              .requires_grad(false);
-    const int param_elems = (quantize::requires_offset(quantType)) ? 2 : 1;
-    auto params = torch::empty({groups, param_elems}, params_options);
-
-    auto output_options = at::TensorOptions()
-                              .dtype(at::kChar)
-                              .layout(at::kStrided)
-                              .device(at::kCUDA)
-                              .requires_grad(false);
-
-    auto output_sizes = input_vals.sizes().vec();
-    output_sizes[output_sizes.size() - 1] /= numBits == 8 ? 1 : 2;
-    auto output = torch::empty(output_sizes, output_options);
-
-    const int elems_per_group = at::numel(input_vals) / groups;
-
-    launch_quant((int8_t*)output.data_ptr(),
-                 (float*)params.data_ptr(),
-                 (__half*)input_vals.data_ptr(),
-                 groups,
-                 elems_per_group,
-                 numBits,
-                 quantType,
-                 at::cuda::getCurrentCUDAStream());
-
-    return {output, params};
-}
-
-template <typename T>
-at::Tensor dequantize(at::Tensor& quantized_data,
-                      at::Tensor& params,
-                      int groups,
-                      int num_bits,
-                      quantize::Type quant_type)
-{
-    auto dtype = (std::is_same<T, float>::value) ? torch::kFloat32 : torch::kFloat16;
-    auto output_options = at::TensorOptions()
-                              .dtype(dtype)
-                              .layout(at::kStrided)
-                              .device(at::kCUDA)
-                              .requires_grad(false);
-
-    auto output_sizes = quantized_data.sizes().vec();
-    output_sizes[output_sizes.size() - 1] *= num_bits == 8 ? 1 : 2;
-    auto output = torch::empty(output_sizes, output_options);
-
-    const int total_elems = at::numel(output);
-    const int elems_per_group = total_elems / groups;
-
-    launch_dequantize_kernel((T*)output.data_ptr(),
-                             (const int8_t*)quantized_data.data_ptr(),
-                             (const float*)params.data_ptr(),
-                             quant_type,
-                             num_bits,
-                             elems_per_group,
-                             total_elems,
-                             at::cuda::getCurrentCUDAStream());
-
-    return output;
-}
-
-at::Tensor dequantize_int4_to_half_experimental(at::Tensor& data_in,
-                                                at::Tensor& scale_buffer,
-                                                at::Tensor& min_val_buffer,
-                                                int num_group,
-                                                int group_size)
-{
-    auto output_options = at::TensorOptions().dtype(at::kHalf).device(at::kCUDA);
-    auto output = torch::empty({num_group, group_size}, output_options);
-
-    launch_dequantize_int4_to_half_experimental((uint8_t*)data_in.data_ptr(),
-                                                (half*)output.data_ptr(),
-                                                (half*)scale_buffer.data_ptr(),
-                                                (half*)min_val_buffer.data_ptr(),
-                                                num_group,
-                                                group_size,
-                                                at::cuda::getCurrentCUDAStream());
-
-    return output;
-}
-
-at::Tensor dequantize_int8_to_half_experimental(at::Tensor& data_in,
-                                                at::Tensor& scale_buffer,
-                                                at::Tensor& min_val_buffer,
-                                                int num_group,
-                                                int group_size)
-{
-    auto output_options = at::TensorOptions().dtype(at::kHalf).device(at::kCUDA);
-    auto output = torch::empty({num_group, group_size}, output_options);
-
-    launch_dequantize_int8_to_half_experimental((uint8_t*)data_in.data_ptr(),
-                                                (half*)output.data_ptr(),
-                                                (half*)scale_buffer.data_ptr(),
-                                                (half*)min_val_buffer.data_ptr(),
-                                                num_group,
-                                                group_size,
-                                                at::cuda::getCurrentCUDAStream());
-
-    return output;
-}
-
-std::vector<at::Tensor> ds_swizzle_quant(at::Tensor& input_vals,
-                                         int groups,
-                                         int num_bits,
-                                         quantize::Type quant_type,
-                                         int pipeline_size,
-                                         int nodes,
-                                         int devices_per_node)
-{
-    auto scales_options = at::TensorOptions()
-                              .dtype(at::kFloat)
-                              .layout(at::kStrided)
-                              .device(at::kCUDA)
-                              .requires_grad(false);
-    const int scales_elems = (quantize::requires_offset(quant_type)) ? 2 : 1;
-    auto scales = torch::empty({groups, scales_elems}, scales_options);
-
-    auto output_options = at::TensorOptions()
-                              .dtype(at::kChar)
-                              .layout(at::kStrided)
-                              .device(at::kCUDA)
-                              .requires_grad(false);
-
-    const int quantization_scalar = 8 / num_bits;
-    const int compressed_vals = at::numel(input_vals) / quantization_scalar;
-
-    auto output = torch::empty({compressed_vals}, output_options);
-    const int elems_per_group = at::numel(input_vals) / groups;
-
-    launch_swizzled_quant((int8_t*)output.data_ptr(),
-                          (float*)scales.data_ptr(),
-                          (__half*)input_vals.data_ptr(),
-                          num_bits,
-                          quant_type,
-                          groups,
-                          elems_per_group,
-                          pipeline_size,
-                          nodes,
-                          devices_per_node,
-                          at::cuda::getCurrentCUDAStream());
-
-    return {output, scales};
-}
-
-std::vector<at::Tensor> quantized_reduction(at::Tensor& input_vals,
-                                            at::Tensor& input_scales,
-                                            int in_groups,
-                                            int out_groups,
-                                            int num_bits,
-                                            quantize::Type quant_type,
-                                            int devices_per_node)
-{
-    auto scales_options = at::TensorOptions()
-                              .dtype(at::kFloat)
-                              .layout(at::kStrided)
-                              .device(at::kCUDA)
-                              .requires_grad(false);
-    const int scales_elems = (quantize::requires_offset(quant_type)) ? 2 : 1;
-    auto scales = torch::empty({out_groups, scales_elems}, scales_options);
-
-    auto output_options = at::TensorOptions()
-                              .dtype(at::kChar)
-                              .layout(at::kStrided)
-                              .device(at::kCUDA)
-                              .requires_grad(false);
-
-    std::vector<int64_t> sz_vector(input_vals.sizes().begin(), input_vals.sizes().end());
-    sz_vector[sz_vector.size() - 1] = sz_vector.back() / devices_per_node;  // num of GPU per nodes
-    at::IntArrayRef sz(sz_vector);
-    auto output = torch::empty(sz, output_options);
-
-    const int elems_per_in_tensor = at::numel(input_vals) / devices_per_node;
-    const int elems_per_in_group = elems_per_in_tensor / (in_groups / devices_per_node);
-    const int elems_per_out_group = elems_per_in_tensor / out_groups;
-
-    launch_dequant_reduce((int8_t*)output.data_ptr(),
-                          (float*)scales.data_ptr(),
-                          (const int8_t*)input_vals.data_ptr(),
-                          (const float*)input_scales.data_ptr(),
-                          devices_per_node,
-                          num_bits,
-                          quant_type,
-                          out_groups,
-                          elems_per_out_group,
-                          elems_per_in_tensor,
-                          in_groups / devices_per_node,
-                          elems_per_in_group,
-                          at::cuda::getCurrentCUDAStream());
-    return {output, scales};
-}
-
-PYBIND11_MODULE(TORCH_EXTENSION_NAME, m)
-{
-    m.def("ds_quantize_fp32", &ds_quantize<float>, "DeepSpeed Quantize with fp32 (CUDA)");
-    m.def("ds_quantize_fp16", &ds_quantize<__half>, "DeepSpeed Quantize with fp16 (CUDA)");
-    m.def("ds_sr_quantize_fp32", &ds_sr_quantize<float>, "DeepSpeed Quantize with fp32 (CUDA)");
-    m.def("ds_sr_quantize_fp16", &ds_sr_quantize<__half>, "DeepSpeed Quantize with fp16 (CUDA)");
-    m.def("ds_quantize_asym_fp32", &ds_quantize_asym<float>, "DeepSpeed Quantize with fp32 (CUDA)");
-    m.def(
-        "ds_quantize_asym_fp16", &ds_quantize_asym<__half>, "DeepSpeed Quantize with fp16 (CUDA)");
-    m.def("ds_sr_quantize_asym_fp32",
-          &ds_sr_quantize_asym<float>,
-          "DeepSpeed Quantize with fp32 (CUDA)");
-    m.def("ds_sr_quantize_asym_fp16",
-          &ds_sr_quantize_asym<__half>,
-          "DeepSpeed Quantize with fp16 (CUDA)");
-    pybind11::enum_<quantize::Type>(m, "QuantizationType")
-        .value("Symmetric", quantize::Type::Symmetric)
-        .value("Asymmetric", quantize::Type::Asymmetric)
-        .export_values();
-    m.def("quantize", &quantize_kernel);
-    m.def("dequantize", &dequantize<__half>);
-    m.def("dequantize_fp32", &dequantize<float>);
-    m.def("dequantize_int4_to_half_experimental",
-          &dequantize_int4_to_half_experimental,
-          "Dequantize int4 to half (experimental)");
-    m.def("dequantize_int8_to_half_experimental",
-          &dequantize_int8_to_half_experimental,
-          "Dequantize int8 to half (experimental)");
-    m.def("swizzle_quant", &ds_swizzle_quant);
-    m.def("quantized_reduction", &quantized_reduction);
-}

Deepspeed-Windows/11.2/deepspeed/env_report.py

@@ -1,161 +0,0 @@
-# Copyright (c) Microsoft Corporation.
-# SPDX-License-Identifier: Apache-2.0
-
-# DeepSpeed Team
-
-import os
-import torch
-import deepspeed
-import subprocess
-import argparse
-import psutil
-from .ops.op_builder.all_ops import ALL_OPS
-from .git_version_info import installed_ops, torch_info
-from deepspeed.accelerator import get_accelerator
-
-GREEN = '\033[92m'
-RED = '\033[91m'
-YELLOW = '\033[93m'
-END = '\033[0m'
-SUCCESS = f"{GREEN} [SUCCESS] {END}"
-OKAY = f"{GREEN}[OKAY]{END}"
-WARNING = f"{YELLOW}[WARNING]{END}"
-FAIL = f'{RED}[FAIL]{END}'
-INFO = '[INFO]'
-
-color_len = len(GREEN) + len(END)
-okay = f"{GREEN}[OKAY]{END}"
-warning = f"{YELLOW}[WARNING]{END}"
-
-
-def op_report(verbose=True):
-    max_dots = 23
-    max_dots2 = 11
-    h = ["op name", "installed", "compatible"]
-    print("-" * (max_dots + max_dots2 + len(h[0]) + len(h[1])))
-    print("DeepSpeed C++/CUDA extension op report")
-    print("-" * (max_dots + max_dots2 + len(h[0]) + len(h[1])))
-
-    print("NOTE: Ops not installed will be just-in-time (JIT) compiled at\n"
-          "      runtime if needed. Op compatibility means that your system\n"
-          "      meet the required dependencies to JIT install the op.")
-
-    print("-" * (max_dots + max_dots2 + len(h[0]) + len(h[1])))
-    print("JIT compiled ops requires ninja")
-    ninja_status = OKAY if ninja_installed() else FAIL
-    print('ninja', "." * (max_dots - 5), ninja_status)
-    print("-" * (max_dots + max_dots2 + len(h[0]) + len(h[1])))
-    print(h[0], "." * (max_dots - len(h[0])), h[1], "." * (max_dots2 - len(h[1])), h[2])
-    print("-" * (max_dots + max_dots2 + len(h[0]) + len(h[1])))
-    installed = f"{GREEN}[YES]{END}"
-    no = f"{YELLOW}[NO]{END}"
-    for op_name, builder in ALL_OPS.items():
-        dots = "." * (max_dots - len(op_name))
-        is_compatible = OKAY if builder.is_compatible(verbose) else no
-        is_installed = installed if installed_ops.get(op_name, False) else no
-        dots2 = '.' * ((len(h[1]) + (max_dots2 - len(h[1]))) - (len(is_installed) - color_len))
-        print(op_name, dots, is_installed, dots2, is_compatible)
-    print("-" * (max_dots + max_dots2 + len(h[0]) + len(h[1])))
-
-
-def ninja_installed():
-    try:
-        import ninja  # noqa: F401 # type: ignore
-    except ImportError:
-        return False
-    return True
-
-
-def nvcc_version():
-    import torch.utils.cpp_extension
-    cuda_home = torch.utils.cpp_extension.CUDA_HOME
-    if cuda_home is None:
-        return f"{RED} [FAIL] cannot find CUDA_HOME via torch.utils.cpp_extension.CUDA_HOME={torch.utils.cpp_extension.CUDA_HOME} {END}"
-    try:
-        output = subprocess.check_output([cuda_home + "/bin/nvcc", "-V"], universal_newlines=True)
-    except FileNotFoundError:
-        return f"{RED} [FAIL] nvcc missing {END}"
-    output_split = output.split()
-    release_idx = output_split.index("release")
-    release = output_split[release_idx + 1].replace(',', '').split(".")
-    return ".".join(release)
-
-
-def get_shm_size():
-    try:
-        temp_dir = os.getenv('TEMP') or os.getenv('TMP') or os.path.join(os.path.expanduser('~'), 'tmp')
-        shm_stats = psutil.disk_usage(temp_dir)
-        shm_size = shm_stats.total
-        shm_hbytes = human_readable_size(shm_size)
-        warn = []
-        if shm_size < 512 * 1024**2:
-            warn.append(
-                f" {YELLOW} [WARNING] Shared memory size might be too small, consider increasing it. {END}"
-            )
-            # Add additional warnings specific to your use case if needed.
-        return shm_hbytes, warn
-    except Exception as e:
-        return "UNKNOWN", [f"Error getting shared memory size: {e}"]
-
-
-def human_readable_size(size):
-    units = ['B', 'KB', 'MB', 'GB', 'TB']
-    i = 0
-    while size >= 1024 and i < len(units) - 1:
-        size /= 1024
-        i += 1
-    return f'{size:.2f} {units[i]}'
-
-
-def debug_report():
-    max_dots = 33
-
-    report = [("torch install path", torch.__path__), ("torch version", torch.__version__),
-              ("deepspeed install path", deepspeed.__path__),
-              ("deepspeed info", f"{deepspeed.__version__}, {deepspeed.__git_hash__}, {deepspeed.__git_branch__}")]
-    if get_accelerator().device_name() == 'cuda':
-        hip_version = getattr(torch.version, "hip", None)
-        report.extend([("torch cuda version", torch.version.cuda), ("torch hip version", hip_version),
-                       ("nvcc version", (None if hip_version else nvcc_version())),
-                       ("deepspeed wheel compiled w.", f"torch {torch_info['version']}, " +
-                        (f"hip {torch_info['hip_version']}" if hip_version else f"cuda {torch_info['cuda_version']}"))
-                       ])
-    else:
-        report.extend([("deepspeed wheel compiled w.", f"torch {torch_info['version']} ")])
-
-    report.append(("shared memory (/dev/shm) size", get_shm_size()))
-
-    print("DeepSpeed general environment info:")
-    for name, value in report:
-        warns = []
-        if isinstance(value, tuple):
-            value, warns = value
-        print(name, "." * (max_dots - len(name)), value)
-        if warns:
-            for warn in warns:
-                print(warn)
-
-
-def parse_arguments():
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--hide_operator_status',
-                        action='store_true',
-                        help='Suppress display of installation and compatibility statuses of DeepSpeed operators. ')
-    parser.add_argument('--hide_errors_and_warnings', action='store_true', help='Suppress warning and error messages.')
-    args = parser.parse_args()
-    return args
-
-
-def main(hide_operator_status=False, hide_errors_and_warnings=False):
-    if not hide_operator_status:
-        op_report(verbose=not hide_errors_and_warnings)
-    debug_report()
-
-
-def cli_main():
-    args = parse_arguments()
-    main(hide_operator_status=args.hide_operator_status, hide_errors_and_warnings=args.hide_errors_and_warnings)
-
-
-if __name__ == "__main__":
-    main()

Deepspeed-Windows/DeepSpeed readme.txt

@@ -1,18 +0,0 @@
-These are the modified files you would need for a MANUAL build of DeepSpeed 11.1 or 11.2.
-
-They were created by a mix of instructions from erew123 and S95Sedan.
-
-
-- You still have to download the DeepSpeed v11.1 or v11.2 installation files from Microsoft to use these files.
-
-https://github.com/microsoft/DeepSpeed/releases/tag/v0.11.2
-
-
-- These files were provided by S95Sedan here: 
-
-https://github.com/S95Sedan/Deepspeed-Windows
-
-
-- They are related to the manual build of DeepSpeed for AllTalk, which is linked here: 
-
-https://github.com/erew123/alltalk_tts/tree/main?tab=readme-ov-file#-option-2---a-bit-more-complicated

Dockerfile

@@ -1,12 +1,20 @@
-FROM ubuntu:22.04
+FROM nvidia/cuda:12.1.1-devel-ubuntu22.04
 ENV HOST 0.0.0.0
 RUN apt-get update && apt-get upgrade -y \
     && apt-get install -y git build-essential portaudio19-dev \
     python3 python3-pip gcc wget \
+    ocl-icd-opencl-dev opencl-headers clinfo \
+    libclblast-dev libopenblas-dev libaio-dev \
+    && mkdir -p /etc/OpenCL/vendors && echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd \
     && ln -s /usr/bin/python3 /usr/bin/python
+
 WORKDIR /app
+ENV CUDA_DOCKER_ARCH=all
+COPY system/requirements/requirements_docker.txt system/requirements/requirements_docker.txt
+RUN pip install --no-cache-dir --no-deps -r system/requirements/requirements_docker.txt && \
+    pip install --no-cache-dir deepspeed
 COPY . .
-RUN pip install --no-cache-dir -r requirements_other.txt
-EXPOSE 7851
+
+EXPOSE 7851 7852
 RUN chmod +x launch.sh
 ENTRYPOINT ["sh", "-c", "./launch.sh"]

atsetup.bat

@@ -1,7 +1,7 @@
 @echo off
 cd /D "%~dp0"
-
-set PATH=%PATH%;%SystemRoot%\system32
+setlocal enabledelayedexpansion
+@set "PATH=%PATH%;%SystemRoot%\system32"
 
 :: Generate the ESC character
 for /F %%a in ('echo prompt $E ^| cmd') do set "ESC=%%a"
@@ -25,6 +25,15 @@ set "L_CYAN=%ESC%[96m"
 set "L_WHITE=%ESC%[97m"
 set "RESET=%ESC%[0m"
 
+echo "%CD%"| findstr /C:" " >nul &&  echo. && echo    %L_BLUE%ALLTALK WINDOWS SETUP UTILITY%RESET% && echo. &&  echo. &&  echo    You are trying to install AllTalk in a folder that has a space in the folder path e.g. && echo. && echo       C:\%L_RED%program files%RESET%\alltalk_tts && echo.	&& echo    This causes errors with Conda and Python scripts. Please follow this link for reference: &&  echo. && echo      %L_CYAN%https://docs.anaconda.com/free/working-with-conda/reference/faq/#installing-anaconda%RESET% && echo. && echo    Please use a folder path that has no spaces in it e.g. && echo. && echo       C:\myfiles\alltalk_tts\ && echo. && echo. && pause && goto :end
+
+@rem Check for special characters in installation path
+set "SPCHARMESSAGE="WARNING: Special characters were detected in the installation path!" "         This can cause the installation to fail!""
+echo "%CD%"| findstr /R /C:"[!#\$%&()\*+,;<=>?@\[\]\^`{|}~]" >nul && (
+	call :PrintBigMessage %SPCHARMESSAGE%
+)
+set SPCHARMESSAGE=
+
 @rem Check if curl is available
 curl --version >nul 2>&1
 if "%ERRORLEVEL%" NEQ "0" (
@@ -61,28 +70,36 @@ echo    environment. If you have NOT done this, please run %L_GREEN%cmd_windows.
 echo    in the %L_GREEN%text-generation-webui%RESET% folder and then re-run this script.
 echo.
 echo    BASE REQUIREMENTS
-echo    1) Install the requirements for a %L_GREEN%Nvidia machine%RESET%.
-echo    2) Install the requirements for a %L_GREEN%AMD or MAC machine%RESET%.
+echo    1) Apply/Re-Apply the requirements for %L_GREEN%Text-generation-webui%RESET%.
 echo.
 echo    OPTIONAL
-echo    3) Install the Finetuning requirements.
-echo    4) Install DeepSpeed v11.2 for CUDA %L_GREEN%11.8%RESET% and Python-3.11.x.
-echo    5) Install DeepSpeed v11.2 for CUDA %L_GREEN%12.1%RESET% and Python-3.11.x.
-echo    6) Uninstall DeepSpeed.
+echo    2) Git Pull the latest AllTalk updates from Github
+echo.
+echo    DEEPSPEED FOR %L_YELLOW=%PyTorch 2.1.x%RESET%
+echo    4) Install DeepSpeed v11.2 for CUDA %L_GREEN%11.8%RESET% and Python-3.11.x and %L_YELLOW%PyTorch 2.1.x%RESET%.
+echo    5) Install DeepSpeed v11.2 for CUDA %L_GREEN%12.1%RESET% and Python-3.11.x and %L_YELLOW%PyTorch 2.1.x%RESET%.
+echo.
+echo    DEEPSPEED FOR %L_YELLOW=%PyTorch 2.2.x%RESET% (March 2024 builds of Text-gen-webui and later)
+echo    6) Install DeepSpeed v14.0 for CUDA %L_GREEN%12.1%RESET% and Python-3.11.x and %L_YELLOW%PyTorch 2.2.x%RESET%.
+echo    7) Install DeepSpeed v14.0 for CUDA %L_GREEN%11.8%RESET% and Python-3.11.x and %L_YELLOW%PyTorch 2.2.x%RESET%.
+echo.
+echo    U) Uninstall DeepSpeed.
 echo.
 echo.   OTHER
-echo    7) Generate a diagnostics file.
+echo    8) Generate a diagnostics file.
 echo.
 echo    9) %L_RED%Exit/Quit%RESET%
 echo.
 set /p WebUIOption="Enter your choice: "
 if "%WebUIOption%"=="1" goto InstallNvidiaTextGen
-if "%WebUIOption%"=="2" goto InstallOtherTextGen
-if "%WebUIOption%"=="3" goto InstallFinetuneTextGen
+if "%WebUIOption%"=="2" goto TGGitpull
 if "%WebUIOption%"=="4" goto InstallDeepSpeed118TextGen
 if "%WebUIOption%"=="5" goto InstallDeepSpeed121TextGen
-if "%WebUIOption%"=="6" goto UnInstallDeepSpeed
-if "%WebUIOption%"=="7" goto GenerateDiagsTextGen
+if "%WebUIOption%"=="6" goto InstallDeepSpeed121TextGenPytorch221
+if "%WebUIOption%"=="7" goto InstallDeepSpeed118TextGenPytorch221
+if "%WebUIOption%"=="U" goto UnInstallDeepSpeed
+if "%WebUIOption%"=="u" goto UnInstallDeepSpeed
+if "%WebUIOption%"=="8" goto GenerateDiagsTextGen
 if "%WebUIOption%"=="9" goto End
 goto WebUIMenu
 
@@ -95,27 +112,33 @@ echo    BASE REQUIREMENTS
 echo    1) Install AllTalk as a Standalone Application
 echo.
 echo    OPTIONAL
-echo    2) Delete AllTalk's custom Python environment
-echo    3) Install the Finetuning requirements
+echo    2) Git Pull the latest AllTalk updates from Github
+echo    3) Re-Apply/Update the requirements file
+echo    4) Delete AllTalk's custom Python environment
+echo    5) Purge the PIP cache
 echo.
 echo.   OTHER
-echo    4) Generate a diagnostics file
+echo    8) Generate a diagnostics file
 echo.
 echo    9) %L_RED%Exit/Quit%RESET%
 echo.
 set /p StandaloneOption="Enter your choice: "
 if "%StandaloneOption%"=="1" goto InstallCustomStandalone
-if "%StandaloneOption%"=="2" goto DeleteCustomStandalone
-if "%StandaloneOption%"=="3" goto InstallFinetuneStandalone
-if "%StandaloneOption%"=="4" goto GenerateDiagsStandalone
-if "%StandaloneOption%"=="9" goto End
+if "%StandaloneOption%"=="2" goto STGitpull
+if "%StandaloneOption%"=="3" goto STReapplyrequirements
+if "%StandaloneOption%"=="4" goto STDeleteCustomStandalone
+if "%StandaloneOption%"=="5" goto STPurgepipcache
+if "%StandaloneOption%"=="8" goto GenerateDiagsStandalone
+if "%StandaloneOption%"=="9" goto EndStandalone
 goto StandaloneMenu
 
 :InstallNvidiaTextGen
-pip install -r requirements_nvidia.txt
+pip install -r system\requirements\requirements_textgen.txt
 if %ERRORLEVEL% neq 0 (
     echo.
-    echo    There was an error installing the Nvidia requirements.
+    echo    There was an error installing the requirements.
+    echo    Have you started your Text-gen-webui Python environment
+    echo    with cmd_{yourOS} before running atsetup.bat?
     echo    Press any key to return to the menu.
     echo.
     pause
@@ -123,46 +146,28 @@ if %ERRORLEVEL% neq 0 (
 )
 Echo.
 echo.
-Echo    Nvidia machine requirements installed successfully.
+Echo    Requirements installed successfully.
 Echo. 
 pause
 goto WebUIMenu
 
-:InstallOtherTextGen
-pip install -r requirements_other.txt
+:TGGitpull
+git pull
 if %ERRORLEVEL% neq 0 (
-    echo. 
-    echo    There was an error installing the Other requirements.
+    echo.
+    echo    There was an error pulling from Github.
     echo    Press any key to return to the menu.
     echo.
     pause
     goto WebUIMenu
 )
 Echo.
-echo.
-Echo    Other machine requirements installed successfully.
+echo     AllTalk Updated from Github. Please re-apply
+echo     the latest requirements file. Option 1
 Echo. 
 pause
 goto WebUIMenu
 
-:InstallFinetuneTextGen
-pip install -r requirements_finetune.txt
-if %ERRORLEVEL% neq 0 (
-    echo.
-    echo    There was an error installing the Finetune requirements.
-    echo    Press any key to return to the menu.
-    echo.
-    pause
-    goto WebUIMenu
-)
-Echo.
-Echo    Finetune requirements installed successfully. Please ensure you have installed CUDA 11.8.
-Echo    Finetune needs access to %L_GREEN%cublas64_11.dll%RESET% and will error if this is not setup correctly.
-Echo    Please see here for details %L_GREEN%https://github.com/erew123/alltalk_tts#-finetuning-a-model%RESET%
-Echo.
-pause
-goto WebUIMenu
-
 :InstallDeepSpeed118TextGen
 echo Downloading DeepSpeed...
 curl -LO https://github.com/erew123/alltalk_tts/releases/download/deepspeed/deepspeed-0.11.2+cuda118-cp311-cp311-win_amd64.whl
@@ -227,6 +232,70 @@ del deepspeed-0.11.2+cuda121-cp311-cp311-win_amd64.whl
 pause
 goto WebUIMenu
 
+:InstallDeepSpeed121TextGenPytorch221
+echo Downloading DeepSpeed...
+curl -LO https://github.com/erew123/alltalk_tts/releases/download/DeepSpeed-14.0/deepspeed-0.14.0+ce78a63-cp311-cp311-win_amd64.whl
+if %ERRORLEVEL% neq 0 (
+    echo.
+    echo    Failed to download DeepSpeed wheel file.
+    echo    Please check your internet connection or try again later.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto WebUIMenu
+)
+echo    DeepSpeed wheel file downloaded successfully.
+echo    Installing DeepSpeed...
+pip install deepspeed-0.14.0+ce78a63-cp311-cp311-win_amd64.whl
+if %ERRORLEVEL% neq 0 (
+    echo. 
+    echo    Failed to install DeepSpeed.
+    echo    Please check if the wheel file is compatible with your system.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto WebUIMenu
+)
+Echo.
+echo.
+Echo    DeepSpeed installed successfully.
+Echo. 
+del deepspeed-0.14.0+ce78a63-cp311-cp311-win_amd64.whl
+pause
+goto WebUIMenu
+
+:InstallDeepSpeed118TextGenPytorch221
+echo Downloading DeepSpeed...
+curl -LO https://github.com/erew123/alltalk_tts/releases/download/DeepSpeed-14.0/deepspeed-0.14.0+cu118-cp311-cp311-win_amd64.whl
+if %ERRORLEVEL% neq 0 (
+    echo.
+    echo    Failed to download DeepSpeed wheel file.
+    echo    Please check your internet connection or try again later.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto WebUIMenu
+)
+echo    DeepSpeed wheel file downloaded successfully.
+echo    Installing DeepSpeed...
+pip install deepspeed-0.14.0+cu118-cp311-cp311-win_amd64.whl
+if %ERRORLEVEL% neq 0 (
+    echo. 
+    echo    Failed to install DeepSpeed.
+    echo    Please check if the wheel file is compatible with your system.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto WebUIMenu
+)
+Echo.
+echo.
+Echo    DeepSpeed installed successfully.
+Echo. 
+del deepspeed-0.14.0+cu118-cp311-cp311-win_amd64.whl
+pause
+goto WebUIMenu
+
 :UnInstallDeepSpeed
 pip uninstall deepspeed
 if %ERRORLEVEL% neq 0 (
@@ -320,49 +389,20 @@ if not exist "%INSTALL_ENV_DIR%\python.exe" ( echo. && echo Conda environment is
 @rem activate installer env
 call "%CONDA_ROOT_PREFIX%\condabin\conda.bat" activate "%INSTALL_ENV_DIR%" || ( echo. && echo Miniconda hook not found. && goto end )
 
-@rem Ask user for the type of requirements to install
 echo.
-echo    %L_BLUE%Choose the type of requirements to install%RESET%
+echo     Downloading and installing PyTorch. This step can take a long time
+echo     depending on your internet connection and hard drive speed. Please
+echo     be patient.
 echo.
-echo    1. Nvidia graphics card machines
-echo    2. Other machines (mac, amd, etc)
+pip install torch==2.2.2+cu121 torchaudio>=2.2.2+cu121 --upgrade --force-reinstall --extra-index-url https://download.pytorch.org/whl/cu121
+echo Installing other requirements.
 echo.
-set /p UserChoice="Enter your choice (1 or 2): "
+pip install -r system\requirements\requirements_standalone.txt
+curl -LO https://github.com/erew123/alltalk_tts/releases/download/DeepSpeed-14.0/deepspeed-0.14.0+ce78a63-cp311-cp311-win_amd64.whl
+echo Installing DeepSpeed...
+pip install deepspeed-0.14.0+ce78a63-cp311-cp311-win_amd64.whl
+del deepspeed-0.14.0+ce78a63-cp311-cp311-win_amd64.whl
 
-@rem Install requirements based on user choice
-if "%UserChoice%" == "1" (
-    echo.
-    echo Installing Nvidia requirements...
-    echo Downloading Pytorch with CUDA..
-    pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --upgrade --force-reinstall --index-url https://download.pytorch.org/whl/cu121
-    pip install numpy==1.24.4
-    pip install typing-extensions>=4.8.0
-    pip install networkx<3.0.0,>=2.5.0
-    pip install fsspec>=2023.6.0
-    pip install soundfile==0.12.1
-    pip install uvicorn==0.24.0.post1
-    pip install transformers>=4.37.1
-    pip install TTS==0.21.3
-    pip install fastapi==0.104.1
-    pip install Jinja2==3.1.2
-    pip install requests==2.31.0
-    pip install tqdm==4.66.1
-    pip install importlib-metadata==4.8.1
-    pip install packaging==23.2
-    pip install pydantic==1.10.13
-    pip install sounddevice==0.4.6
-    pip install python-multipart==0.0.6
-    pip install cutlet>=0.3.0
-    pip install unidic-lite>=1.0.8
-    echo Downloading DeepSpeed...
-    curl -LO https://github.com/erew123/alltalk_tts/releases/download/DeepSpeed-12.7/deepspeed-0.12.7+d058d4b-cp311-cp311-win_amd64.whl
-    echo Installing DeepSpeed...
-    pip install deepspeed-0.12.7+d058d4b-cp311-cp311-win_amd64.whl
-    del deepspeed-0.12.7+d058d4b-cp311-cp311-win_amd64.whl
-) else (
-    echo Installing requirements for other machines...
-    pip install -r requirements_other.txt
-)
 
 @rem Create start_environment.bat to run AllTalk environment
 echo @echo off > start_environment.bat
@@ -377,14 +417,22 @@ echo set CONDA_ROOT_PREFIX=%cd%\alltalk_environment\conda >> start_alltalk.bat
 echo set INSTALL_ENV_DIR=%cd%\alltalk_environment\env >> start_alltalk.bat
 echo call "%CONDA_ROOT_PREFIX%\condabin\conda.bat" activate "%INSTALL_ENV_DIR%" >> start_alltalk.bat
 echo call python script.py >> start_alltalk.bat
+@rem Create start_finetune.bat to run AllTalk
+echo @echo off > start_finetune.bat
+echo cd /D "%~dp0" >> start_finetune.bat
+echo set CONDA_ROOT_PREFIX=%cd%\alltalk_environment\conda >> start_finetune.bat
+echo set INSTALL_ENV_DIR=%cd%\alltalk_environment\env >> start_finetune.bat
+echo call "%CONDA_ROOT_PREFIX%\condabin\conda.bat" activate "%INSTALL_ENV_DIR%" >> start_finetune.bat
+echo call python finetune.py >> start_finetune.bat
 Echo.
-Echo    start_alltalk.bat has been created.
-Echo    You can now start AllTalk with %L_YELLOW%start_alltalk.bat%RESET%
+Echo    Run %L_YELLOW%start_alltalk.bat%RESET% to start AllTalk.
+Echo    Run %L_YELLOW%start_finetune.bat%RESET% to start Finetuning.
+Echo    Run %L_YELLOW%start_environment.bat%RESET% to start the AllTalk Python environment.
 Echo.
 pause
 goto StandaloneMenu
 
-:DeleteCustomStandalone
+:STDeleteCustomStandalone
 @rem Check if the alltalk_environment directory exists
 if not exist "%cd%\alltalk_environment\" (
     echo.
@@ -418,47 +466,6 @@ Echo.
 pause
 goto StandaloneMenu
 
-:InstallFinetuneStandalone
-cd /D "%~dp0"
-set CONDA_ROOT_PREFIX=%cd%\alltalk_environment\conda
-set INSTALL_ENV_DIR=%cd%\alltalk_environment\env
-@rem Check if the Conda environment exists
-if not exist "%INSTALL_ENV_DIR%\python.exe" (
-    echo.
-    echo    The Conda environment at "%INSTALL_ENV_DIR%" does not exist.
-    echo    Please install the environment before proceeding.
-    echo.
-    pause
-    goto StandaloneMenu
-)
-@rem Attempt to activate the Conda environment
-call "%CONDA_ROOT_PREFIX%\condabin\conda.bat" activate "%INSTALL_ENV_DIR%"
-if errorlevel 1 (
-    echo. 
-    echo    Failed to activate the Conda environment.
-    echo    Please check your installation and try again.
-    echo.
-    pause
-    goto StandaloneMenu
-)
-@rem Proceed with installing requirements
-pip install -r requirements_finetune.txt
-if %ERRORLEVEL% neq 0 (
-    echo. 
-    echo    There was an error installing the Finetune requirements.
-    echo    Press any key to return to the menu.
-    echo.
-    pause
-    goto StandaloneMenu
-)
-Echo.
-Echo    Finetune requirements installed successfully. Please ensure you have installed CUDA 11.8.
-Echo    Finetune needs access to %L_GREEN%cublas64_11.dll%RESET% and will error if this is not setup correctly.
-Echo    Please see here for details %L_GREEN%https://github.com/erew123/alltalk_tts#-finetuning-a-model%RESET%
-Echo.
-pause
-goto StandaloneMenu
-
 :GenerateDiagsStandalone
 cd /D "%~dp0"
 set CONDA_ROOT_PREFIX=%cd%\alltalk_environment\conda
@@ -499,6 +506,154 @@ Echo.
 pause
 goto StandaloneMenu
 
+:STReapplyrequirements
+cd /D "%~dp0"
+set CONDA_ROOT_PREFIX=%cd%\alltalk_environment\conda
+set INSTALL_ENV_DIR=%cd%\alltalk_environment\env
+@rem Check if the Conda environment exists
+if not exist "%INSTALL_ENV_DIR%\python.exe" (
+    echo.
+    echo    The Conda environment at "%INSTALL_ENV_DIR%" does not exist.
+    echo    Please install the environment before proceeding.
+    echo. 
+    pause
+    goto StandaloneMenu
+)
+@rem Attempt to activate the Conda environment
+call "%CONDA_ROOT_PREFIX%\condabin\conda.bat" activate "%INSTALL_ENV_DIR%"
+if errorlevel 1 (
+    echo. 
+    echo    Failed to activate the Conda environment.
+    echo    Please check your installation and try again.
+    echo.
+    pause
+    goto StandaloneMenu
+)
+@rem Run Reapply requirements
+echo.
+echo     Downloading and installing PyTorch. This step can take a long time
+echo     depending on your internet connection and hard drive speed. Please
+echo     be patient.
+echo.
+pip install torch==2.2.2+cu121 torchaudio>=2.2.2+cu121 --upgrade --force-reinstall --extra-index-url https://download.pytorch.org/whl/cu121
+echo Installing other requirements.
+echo.
+pip install -r system\requirements\requirements_standalone.txt
+C:/Windows/system32/curl.exe -LO https://github.com/erew123/alltalk_tts/releases/download/DeepSpeed-14.0/deepspeed-0.14.0+ce78a63-cp311-cp311-win_amd64.whl
+echo Installing DeepSpeed...
+pip install deepspeed-0.14.0+ce78a63-cp311-cp311-win_amd64.whl
+del deepspeed-0.14.0+ce78a63-cp311-cp311-win_amd64.whl
+if %ERRORLEVEL% neq 0 (
+    echo.
+    echo    There was an error.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto StandaloneMenu
+)
+Echo.
+Echo.
+Echo    Requirements have been re-applied/updated.
+Echo.
+pause
+goto StandaloneMenu
+
+:STPurgepipcache
+cd /D "%~dp0"
+set CONDA_ROOT_PREFIX=%cd%\alltalk_environment\conda
+set INSTALL_ENV_DIR=%cd%\alltalk_environment\env
+@rem Check if the Conda environment exists
+if not exist "%INSTALL_ENV_DIR%\python.exe" (
+    echo.
+    echo    The Conda environment at "%INSTALL_ENV_DIR%" does not exist.
+    echo    Please install the environment before proceeding.
+    echo. 
+    pause
+    goto StandaloneMenu
+)
+@rem Attempt to activate the Conda environment
+call "%CONDA_ROOT_PREFIX%\condabin\conda.bat" activate "%INSTALL_ENV_DIR%"
+if errorlevel 1 (
+    echo. 
+    echo    Failed to activate the Conda environment.
+    echo    Please check your installation and try again.
+    echo.
+    pause
+    goto StandaloneMenu
+)
+@rem Clear the PIP cache
+echo.
+echo     Purging the PIP cache of downloaded files.
+echo.
+pip cache purge
+if %ERRORLEVEL% neq 0 (
+    echo.
+    echo    There was an error.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto StandaloneMenu
+)
+Echo.
+Echo    The PIP cache has been purged.
+Echo.
+pause
+goto StandaloneMenu
+
+:STGitpull
+cd /D "%~dp0"
+set CONDA_ROOT_PREFIX=%cd%\alltalk_environment\conda
+set INSTALL_ENV_DIR=%cd%\alltalk_environment\env
+@rem Check if the Conda environment exists
+if not exist "%INSTALL_ENV_DIR%\python.exe" (
+    echo.
+    echo    The Conda environment at "%INSTALL_ENV_DIR%" does not exist.
+    echo    Please install the environment before proceeding.
+    echo. 
+    pause
+    goto StandaloneMenu
+)
+@rem Attempt to activate the Conda environment
+call "%CONDA_ROOT_PREFIX%\condabin\conda.bat" activate "%INSTALL_ENV_DIR%"
+if errorlevel 1 (
+    echo. 
+    echo    Failed to activate the Conda environment.
+    echo    Please check your installation and try again.
+    echo.
+    pause
+    goto StandaloneMenu
+)
+@rem Pull from Github
+echo.
+echo     Pulling the latest updates. Please re-apply
+echo     the latest requirements file. Option 3
+echo.
+git pull
+if %ERRORLEVEL% neq 0 (
+    echo.
+    echo    There was an error pulling from Github.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto StandaloneMenu
+)
+Echo.
+echo     AllTalk Updated from Github. Please re-apply
+echo     the latest requirements file. Option 3
+Echo.
+pause
+goto StandaloneMenu
+
+:EndStandalone
+echo Exiting AllTalk Setup Utility...
+echo.
+Echo    Remember, after installation you can....
+Echo    Run %L_YELLOW%start_alltalk.bat%RESET% to start AllTalk.
+Echo    Run %L_YELLOW%start_finetune.bat%RESET% to start Finetuning.
+Echo    Run %L_YELLOW%start_environment.bat%RESET% to start the AllTalk Python environment.
+Echo.
+exit /b
+
 :End
 echo Exiting AllTalk Setup Utility...
 exit /b

atsetup.sh

@@ -28,6 +28,40 @@ check_curl() {
     fi
 }
 
+# Check if the current directory path contains a space
+containsSpace=false
+currentPath=$(pwd)
+if echo "$currentPath" | grep -q ' '; then
+    containsSpace=true
+fi
+
+if [ "$containsSpace" = true ]; then
+    echo
+    echo -e "    ${L_BLUE}ALLTALK LINUX SETUP UTILITY${NC}"
+    echo
+    echo
+    echo -e "    You are trying to install AllTalk in a folder that has a space in the"
+    echo -e "    folder path e.g."
+    echo 
+    echo -e "       /home/${L_RED}program files${NC}/alltalk_tts"
+    echo 
+    echo -e "    This causes errors with Conda and Python scripts. Please follow this"
+    echo -e "    link for reference:"
+    echo 
+    echo -e "      ${L_CYAN}https://docs.anaconda.com/free/working-with-conda/reference/faq/#installing-anaconda${NC}"
+    echo 
+    echo -e "    Please use a folder path that has no spaces in it e.g." 
+    echo 
+    echo -e "       /home/myfiles/alltalk_tts/"
+    echo 
+    echo
+    read -p "Press Enter to continue..." 
+    exit 1
+else
+    # Continue with the main menu
+    echo "Continue with the main menu."
+fi
+
 # Main Menu
 main_menu() {
     while true; do
@@ -64,11 +98,12 @@ webui_menu() {
         echo -e "    in the ${L_GREEN}text-generation-webui${NC} folder and then re-run this script."
         echo
         echo "    BASE REQUIREMENTS"
-        echo -e "    1) Install the AllTalk requirements for an ${L_GREEN}Nvidia GPU machine.${NC}"
-        echo -e "    2) Install the AllTalk requirements for an ${L_GREEN}AMD or MAC machine.${NC}"
+        echo -e "    1) Apply/Re-Apply the requirements for an ${L_GREEN}Text-generation-webui${NC}"
         echo
         echo "    OPTIONAL"
-        echo "    3) Install the Finetuning requirements."
+        echo "    2) Git Pull the latest AllTalk updates from Github"
+        echo
+        echo "    DEEPSPEED"
         echo "    4) Install DeepSpeed."
         echo "    5) Uninstall DeepSpeed."
         echo
@@ -81,8 +116,7 @@ webui_menu() {
 
         case $webui_option in
             1) install_nvidia_textgen ;;
-            2) install_other_textgen ;;
-            3) install_finetune_textgen ;;
+            2) tg_gitpull ;;
             4) install_deepspeed ;;
             5) uninstall_deepspeed ;;
             6) generate_diagnostics_textgen ;;
@@ -93,52 +127,40 @@ webui_menu() {
 }
 
 install_nvidia_textgen() {
-    local requirements_file="requirements_nvidia.txt"
-    echo "    Installing Finetune requirements from $requirements_file..."
+    local requirements_file="system/requirements/requirements_textgen.txt"
+    echo "    Installing Requirements from $requirements_file..."
     if ! pip install -r "$requirements_file"; then
-        echo "    There was an error installing the Nvidia requirements."
+        echo
+        echo "    There was an error pulling from Github."
         echo "    Please check the output for details."
         read -p "    Press any key to return to the menu. " -n 1
         echo
         return
     fi
-    echo "    Nvidia requirements installed successfully."
+    echo
+    echo "    Requirements installed successfully."
+    echo
+    echo -e "    To install ${L_YELLOW}DeepSpeed${NC} on Linux, there are additional"
+    echo -e "    steps required. Please see the Github or documentation on DeepSeed."
+    echo
     read -p "    Press any key to continue. " -n 1
     echo
 }
 
-install_other_textgen() {
-    local requirements_file="requirements_other.txt"
-    echo "    Installing Other machine requirements from $requirements_file..."
-    if ! pip install -r "$requirements_file"; then
-        echo "    There was an error installing the Other requirements."
-        echo "    Please check the output for details."
-        read -p "    Press any key to return to the menu. " -n 1
-        echo
-        return
-    fi
-    echo "    Other machine requirements installed successfully."
-    read -p "    Press any key to continue. " -n 1
+tg_gitpull() {
     echo
-}
-
-install_finetune_textgen() {
-    local requirements_file="requirements_finetune.txt"
-    echo "    Installing Finetune requirements from $requirements_file..."
-    if ! pip install -r "$requirements_file"; then
-        echo "    There was an error installing the Finetune requirements."
+    if ! git pull; then
+        echo
+        echo "    There was an error installing the requirements."
         echo "    Please check the output for details."
+        echo
         read -p "    Press any key to return to the menu. " -n 1
         echo
         return
     fi
     echo
-    echo "    Finetune base requirements installed successfully."
-    echo
-    echo -e "    Finetuning requires access to ${GREEN}Cublas${NC} from the ${GREEN}Nvidia CUDA Toolkit${NC}, so will need installing."
-    echo
-    echo -e "    Instructions can be found here:"
-    echo -e "    ${GREEN}https://github.com/erew123/alltalk_tts?#-finetuning-a-model${NC}"
+    echo "    AllTalk Updated from Github. Please re-apply"
+    echo "    the latest requirements file. (Option 1)"
     echo
     read -p "    Press any key to continue. " -n 1
     echo
@@ -185,12 +207,16 @@ uninstall_deepspeed() {
     echo "Uninstalling DeepSpeed..."
     pip uninstall -y deepspeed
     if [ $? -ne 0 ]; then
+        echo
         echo "    There was an error uninstalling DeepSpeed."
+        echo
         echo "    Press any key to return to the menu."
         read -n 1
         return
     fi
+    echo
     echo "    DeepSpeed uninstalled successfully."
+    echo
     echo "    Press any key to continue."
     read -n 1
 }
@@ -198,13 +224,17 @@ uninstall_deepspeed() {
 generate_diagnostics_textgen() {
     # Run diagnostics
     if ! python diagnostics.py; then
+        echo
         echo "    There was an error running diagnostics."
+        echo
         read -p "    Press any key to return to the menu. " -n 1
         echo
         return
     fi
-
-    echo "    Diagnostics completed successfully."
+    echo
+    echo "    Diagnostics log file generated successfully."
+    echo "    Please see diagnostics.log"
+    echo
     read -p "    Press any key to continue. " -n 1
     echo
 }
@@ -220,12 +250,16 @@ standalone_menu() {
         echo "    1) Install AllTalk as a Standalone Application"
         echo
         echo "    OPTIONAL"
-        echo "    2) Delete AllTalk's custom Python environment"
-        echo "    3) Install the Finetuning requirements"
-        echo "    4) Install DeepSpeed."
+        echo "    2) Git Pull the latest AllTalk updates from Github"
+        echo "    3) Re-Apply/Update the requirements file"
+        echo "    4) Delete AllTalk's custom Python environment"
+        echo "    5) Purge the PIP cache"
+        echo
+        echo "    DEEPSPEED"
+        echo "    6) DeepSpeed Instructions/Install"
         echo
         echo "    OTHER"        
-        echo "    5) Generate a diagnostics file"
+        echo "    8) Generate a diagnostics file"
         echo
         echo -e "    9)${L_RED} Exit/Quit${NC}"
         echo
@@ -233,16 +267,19 @@ standalone_menu() {
 
         case $standalone_option in
             1) install_custom_standalone ;;
-            2) delete_custom_standalone ;;
-            3) install_finetune_standalone ;;
-            4) install_deepspeed ;;
-            5) generate_diagnostics_standalone ;;
+            2) gitpull_standalone ;;
+            3) reapply_standalone ;;
+            4) delete_custom_standalone ;;
+            5) pippurge_standalone ;;
+            6) install_deepspeed ;;
+            8) generate_diagnostics_standalone ;;
             9) exit 0 ;;
             *) echo "Invalid option"; sleep 2 ;;
         esac
     done
 }
 
+
 install_custom_standalone() {
     cd "$(dirname "${BASH_SOURCE[0]}")"
 
@@ -284,39 +321,15 @@ install_custom_standalone() {
     # Activate the environment and install requirements
     source "${CONDA_ROOT_PREFIX}/etc/profile.d/conda.sh"
     conda activate "${INSTALL_ENV_DIR}"
-
     echo
-    echo -e "    ${L_BLUE}Choose the type of requirements to install${NC}"
+    echo "    Downloading and installing PyTorch. This step can take a long time"
+    echo "    depending on your internet connection and hard drive speed. Please"
+    echo "    be patient."
+    pip install torch==2.2.1+cu121 torchaudio==2.2.1+cu121 --upgrade --force-reinstall --extra-index-url https://download.pytorch.org/whl/cu121
     echo
-    echo "    1. Nvidia graphics card machines"
-    echo "    2. Other machines (mac, amd, etc)"
+    echo "    Installing additional requirements."
     echo
-    read -p "    Enter your choice (1 or 2): " user_choice
-
-    if [ "$user_choice" == "1" ]; then
-    	pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --upgrade --force-reinstall --index-url https://download.pytorch.org/whl/cu121
-    	pip install numpy==1.24.4
-	pip install typing-extensions>=4.8.0
-	pip install networkx<3.0.0,>=2.5.0
-    	pip install fsspec>=2023.6.0
-	pip install soundfile==0.12.1
-    	pip install uvicorn==0.24.0.post1
-        pip install transformers>=4.37.1
-    	pip install TTS==0.21.3
-    	pip install fastapi==0.104.1
-    	pip install Jinja2==3.1.2
-    	pip install requests==2.31.0
-    	pip install tqdm==4.66.1
-    	pip install importlib-metadata==4.8.1
-    	pip install packaging==23.2
-    	pip install pydantic==1.10.13
-    	pip install sounddevice==0.4.6
-    	pip install python-multipart==0.0.6
-        pip install cutlet>=0.3.0
-    	pip install unidic-lite>=1.0.8
-    else
-        pip install -r requirements_other.txt
-    fi
+    pip install -r system/requirements/requirements_standalone.txt
     # Create start_environment.sh to run AllTalk
     cat << EOF > start_environment.sh
 #!/bin/bash
@@ -333,27 +346,42 @@ unset PYTHONPATH
 unset PYTHONHOME
 export CUDA_PATH="$INSTALL_ENV_DIR"
 export CUDA_HOME="$CUDA_PATH"
+export LD_LIBRARY_PATH=`python3 -c 'import os; import nvidia.cublas.lib; import nvidia.cudnn.lib; print(os.path.dirname(nvidia.cublas.lib.__file__) + ":" + os.path.dirname(nvidia.cudnn.lib.__file__))'`
 # activate env
 bash --init-file <(echo "source \"$CONDA_ROOT_PREFIX/etc/profile.d/conda.sh\" && conda activate \"$INSTALL_ENV_DIR\"")
 EOF
     # Create start_alltalk.sh to run AllTalk
     cat << EOF > start_alltalk.sh
 #!/bin/bash
+export LD_LIBRARY_PATH=`python3 -c 'import os; import nvidia.cublas.lib; import nvidia.cudnn.lib; print(os.path.dirname(nvidia.cublas.lib.__file__) + ":" + os.path.dirname(nvidia.cudnn.lib.__file__))'`
 source "${CONDA_ROOT_PREFIX}/etc/profile.d/conda.sh"
 conda activate "${INSTALL_ENV_DIR}"
 python script.py
+EOF
+    # Create start_finetune.sh to run AllTalk
+    cat << EOF > start_finetune.sh
+#!/bin/bash
+export TRAINER_TELEMETRY=0
+export LD_LIBRARY_PATH=`python3 -c 'import os; import nvidia.cublas.lib; import nvidia.cudnn.lib; print(os.path.dirname(nvidia.cublas.lib.__file__) + ":" + os.path.dirname(nvidia.cudnn.lib.__file__))'`
+source "${CONDA_ROOT_PREFIX}/etc/profile.d/conda.sh"
+conda activate "${INSTALL_ENV_DIR}"
+python finetune.py
 EOF
     chmod +x start_alltalk.sh
     chmod +x start_environment.sh
+    chmod +x start_finetune.sh
     echo
     echo
-    echo -e "    start_alltalk.sh has been created."
-    echo -e "    You can now start AllTalk with ${L_YELLOW}./start_alltalk.sh${NC}"
+    echo -e "    Run ${L_YELLOW}./start_alltalk.sh${NC} to start AllTalk."
+    echo -e "    Run ${L_YELLOW}./start_finetune.sh${NC} to start Finetuning."
+    echo -e "    Run ${L_YELLOW}./start_environment.sh${NC} to start the AllTalk Python environment."
+    echo
+    echo -e "    To install ${L_YELLOW}DeepSpeed${NC} on Linux, there are additional"
+    echo -e "    steps required. Please see the Github or documentation on DeepSeed."
     echo
     read -p "    Press any key to continue. " -n 1
 }
 
-
 delete_custom_standalone() {
     local env_dir="$PWD/alltalk_environment"
     # Check if the alltalk_environment directory exists
@@ -380,47 +408,15 @@ delete_custom_standalone() {
     echo
 }
 
-install_finetune_standalone() {
-    local env_dir="$PWD/alltalk_environment"
-    local conda_root_prefix="${env_dir}/conda"
-    local install_env_dir="${env_dir}/env"
-    if [ ! -d "${install_env_dir}" ]; then
-        echo "    The Conda environment at '${install_env_dir}' does not exist."
-        echo "    Please install the environment before proceeding."
-        read -p "    Press any key to return to the menu. " -n 1
-        echo
-        return
-    fi
-    source "${conda_root_prefix}/etc/profile.d/conda.sh"
-    conda activate "${install_env_dir}"
-    local requirements_file="requirements_finetune.txt"
-    echo "Installing Finetune requirements from $requirements_file..."
-    if ! pip install -r "$requirements_file"; then
-        echo "    There was an error installing the Finetune requirements."
-        echo "    Please check the output for details."
-        read -p "    Press any key to return to the menu. " -n 1
-        echo
-        return
-    fi
-    echo
-    echo "    Finetune base requirements installed successfully."
-    echo
-    echo -e "    Finetuning requires access to ${GREEN}Cublas${NC} from the ${GREEN}Nvidia CUDA Toolkit${NC}, so will need installing."
-    echo
-    echo -e "    Instructions can be found here:"
-    echo -e "    ${GREEN}https://github.com/erew123/alltalk_tts?#-finetuning-a-model${NC}"
-    echo
-    read -p "    Press any key to continue. " -n 1
-    echo
-}
-
 generate_diagnostics_standalone() {
     local env_dir="$PWD/alltalk_environment"
     local conda_root_prefix="${env_dir}/conda"
     local install_env_dir="${env_dir}/env"
     if [ ! -d "${install_env_dir}" ]; then
+        echo
         echo "    The Conda environment at '${install_env_dir}' does not exist."
         echo "    Please install the environment before proceeding."
+        echo
         read -p "    Press any key to return to the menu. " -n 1
         echo
         return
@@ -428,16 +424,97 @@ generate_diagnostics_standalone() {
     source "${conda_root_prefix}/etc/profile.d/conda.sh"
     conda activate "${install_env_dir}"
     if ! python diagnostics.py; then
+        echo
         echo "    There was an error running diagnostics."
+        echo
         read -p "    Press any key to return to the menu. " -n 1
         echo
         return
     fi
+    echo
     echo "    Diagnostics completed successfully."
     read -p "    Press any key to continue. " -n 1
     echo
 }
 
+gitpull_standalone() {
+    local env_dir="$PWD/alltalk_environment"
+    local conda_root_prefix="${env_dir}/conda"
+    local install_env_dir="${env_dir}/env"
+    if [ ! -d "${install_env_dir}" ]; then
+        echo
+        echo "    The Conda environment at '${install_env_dir}' does not exist."
+        echo "    Please install the environment before proceeding."
+        echo
+        read -p "    Press any key to return to the menu. " -n 1
+        echo
+        return
+    fi
+    source "${conda_root_prefix}/etc/profile.d/conda.sh"
+    conda activate "${install_env_dir}"
+    if ! git pull; then
+        echo
+        echo "    There was an error pulling from Github."
+        echo
+        read -p "    Press any key to return to the menu. " -n 1
+        echo
+        return
+    fi
+    echo
+    echo "    AllTalk Updated from Github. Please re-apply."
+    echo "    the latest requirements file. (Option 3)"
+    echo
+    read -p "    Press any key to continue. " -n 1
+    echo
+}
+
+pippurge_standalone() {
+    if ! pip cache purge; then
+        echo
+        echo "    There was an error."
+        echo
+        read -p "    Press any key to return to the menu. " -n 1
+        echo
+        return
+    fi
+    echo
+    echo "    The PIP cache has been purged."
+    echo
+    read -p "    Press any key to continue. " -n 1
+    echo
+}
+
+reapply_standalone() {
+    local env_dir="$PWD/alltalk_environment"
+    local conda_root_prefix="${env_dir}/conda"
+    local install_env_dir="${env_dir}/env"
+    if [ ! -d "${install_env_dir}" ]; then
+        echo
+        echo "    The Conda environment at '${install_env_dir}' does not exist."
+        echo "    Please install the environment before proceeding."
+        echo
+        read -p "    Press any key to return to the menu. " -n 1
+        echo
+        return
+    fi
+    source "${conda_root_prefix}/etc/profile.d/conda.sh"
+    conda activate "${install_env_dir}"
+    echo
+    echo "    Downloading and installing PyTorch. This step can take a long time"
+    echo "    depending on your internet connection and hard drive speed. Please"
+    echo "    be patient."
+    pip install torch>=2.2.1+cu121 torchaudio>=2.2.1+cu121 --upgrade --force-reinstall --extra-index-url https://download.pytorch.org/whl/cu121
+    echo
+    echo "    Installing additional requirements."
+    echo
+    pip install -r system/requirements/requirements_standalone.txt
+    echo
+    echo "    Requirements have been re-applied/updated."
+    echo
+    read -p "    Press any key to continue. " -n 1
+    echo
+}
+
 
 # Start the main menu
 main_menu

diagnostics.py

@@ -8,12 +8,15 @@ try:
     import re
     import sys
     import glob
+    import site
     import textwrap
+    import torch
     import packaging.version
     import packaging.specifiers
     from packaging.specifiers import SpecifierSet
     from packaging.specifiers import SpecifierSet
     from packaging.version import parse as parse_version
+    from pathlib import Path
 except ImportError as e:
     print(f"\033[91mError importing module: {e}\033[0m\n")
     print("\033[94mPlease ensure you started the Text-generation-webUI Python environment with either\033[0m")
@@ -21,6 +24,8 @@ except ImportError as e:
     print("\033[94mfrom the text-generation-webui directory, and then try running the diagnostics again.\033[0m")
     exit(1)
 
+this_dir = Path(__file__).parent
+
 try:
     import psutil
 except ImportError:
@@ -29,24 +34,30 @@ except ImportError:
     import psutil
 
 def get_requirements_file():
-    requirements_files = glob.glob("requirements*.txt")
+    this_dir = Path(__file__).parent  # Assuming 'this_dir' is defined as the script's directory
+    requirements_dir = this_dir / 'system' / 'requirements'
+    requirements_files = list(requirements_dir.glob('requirements*.txt'))  # Using pathlib for globbing
+    
     if not requirements_files:
         print("\033[91mNo requirements files found.\033[0m")
         return None
 
     print("\033[94m\nSelect a requirements file to check against (or press Enter for default 'requirements.txt'):\033[0m\n")
-    for i, file in enumerate(requirements_files, start=1):
-        print(f"{i}. {file}")
+    for i, file_path in enumerate(requirements_files, start=1):
+        print(f"    {i}. {file_path.name}")  # Only print the filename
 
     choice = input("\nEnter the number of your choice: ")
     try:
         choice = int(choice) - 1
-        return requirements_files[choice]
+        return str(requirements_files[choice])  # Return the full path as a string
     except (ValueError, IndexError):
-        return "requirements.txt"
+        return str(requirements_dir / "requirements.txt")  # Return the default path as a string
 
 # Set up logging with filemode='w'
-logging.basicConfig(filename='diagnostics.log', filemode='w', level=logging.INFO)
+logging.basicConfig(filename='diagnostics.log',
+                    filemode='w',
+                    level=logging.INFO,
+                    format='%(message)s')  # Custom format
 
 # Function to get GPU information using subprocess
 def get_gpu_info():
@@ -55,6 +66,22 @@ def get_gpu_info():
         return result.stdout
     except FileNotFoundError:
         return "NVIDIA GPU information not available"
+    
+def get_cpu_info():
+    cpu_info = {
+        'physical_cores': psutil.cpu_count(logical=False),
+        'total_cores': psutil.cpu_count(logical=True),
+        'max_frequency': psutil.cpu_freq().max
+    }
+    return cpu_info
+
+def get_disk_info():
+    disk_info = []
+    partitions = psutil.disk_partitions()
+    for p in partitions:
+        usage = psutil.disk_usage(p.mountpoint)
+        disk_info.append(f" Drive: {p.device} | Total: {usage.total / (1024 ** 3):.2f} GB | Used: {usage.used / (1024 ** 3):.2f} GB | Free: {usage.free / (1024 ** 3):.2f} GB | Type: {p.fstype}")
+    return disk_info
 
 # Function to check if a port is in use
 def is_port_in_use(port):
@@ -73,6 +100,38 @@ def satisfies_wildcard(installed_version, required_version):
         return True
     return False
 
+def test_cuda():
+    cuda_available = torch.cuda.is_available()
+    if cuda_available:
+        try:
+            # Attempt to create a tensor on GPU
+            torch.tensor([1.0, 2.0]).cuda()
+            return "Success - CUDA is available and working."
+        except Exception as e:
+            return f"Fail - CUDA is available but not working. Error: {e}"
+    else:
+        return "Fail - CUDA is not available."
+
+def find_files_in_path_with_wildcard(pattern):
+    # Get the site-packages directory of the current Python environment
+    site_packages_path = site.getsitepackages()
+    found_paths = []
+    # Adjust the sub-directory based on the operating system
+    sub_directory = "nvidia/cublas"
+    if platform.system() == "Linux":
+        sub_directory = os.path.join(sub_directory, "lib")
+    else:
+        sub_directory = os.path.join(sub_directory, "bin")
+    # Iterate over each site-packages directory (there can be more than one)
+    for directory in site_packages_path:
+        # Construct the search directory path
+        search_directory = os.path.join(directory, sub_directory)
+        # Use glob to find all files matching the pattern in this directory
+        for file_path in glob.glob(os.path.join(search_directory, pattern)):
+            if os.path.isfile(file_path):  # Ensure it's a file
+                found_paths.append(file_path)
+    return found_paths
+
 # Function to log and print system information
 def log_system_info():
     # System information
@@ -88,6 +147,9 @@ def log_system_info():
 
     # Torch version
     torch_version = torch.__version__
+    cuda_test_result = test_cuda()
+    cpu_info = get_cpu_info()
+    disk_info = get_disk_info()
 
     # System RAM using psutil
     try:
@@ -123,6 +185,10 @@ def log_system_info():
     search_path = sys.path
     path_env = os.environ.get('PATH', 'N/A')
 
+    # Check for cublas
+    file_name = 'cublas64_11.*' if platform.system() == "Windows" else 'libcublas.so.11*'
+    found_paths = find_files_in_path_with_wildcard(file_name)
+
     # Compare with requirements file
     requirements_file = get_requirements_file()
     if requirements_file:
@@ -146,52 +212,72 @@ def log_system_info():
             logging.info(f"NOTE {requirements_file} not found. Skipping version checks.")
 
     # Log and print information
-    logging.info(f"OS Version: {os_version}")
-    logging.info(f"Note: Windows 11 will list as build is 10.x.22xxx")
-    logging.info(f"Torch Version: {torch_version}")
-    logging.info(f"System RAM: {system_ram}")
-    logging.info(f"CUDA_HOME: {cuda_home}")
-    logging.info(f"Port Status: {port_status}")
-    logging.info(f"Python Version: {platform.python_version()}")
-    logging.info(f"Python Version Info: {python_version_info}")
-    logging.info(f"Python Executable: {python_executable}")
-    logging.info(f"Python Virtual Environment: {python_virtual_env} (Should be N/A when in Text-generation-webui Conda Python environment)")
-    logging.info(f"Conda Environment: {conda_env}")
+    logging.info(f"OPERATING SYSTEM:")
+    logging.info(f" OS Version: {os_version}")
+    logging.info(f" Note: Windows 11 will list as build is 10.x.22xxx")
+    logging.info(f"\nHARDWARE ENVIRONMENT:")
+    logging.info(f" CPU: Physical Cores: {cpu_info['physical_cores']}, Total Cores: {cpu_info['total_cores']}, Max Frequency: {cpu_info['max_frequency']} MHz")
+    logging.info(f" System RAM: {system_ram}")
+    logging.info(f"\nGPU INFORMATION:{gpu_info}")
+    logging.info("DISK INFORMATION:")
+    for disk in disk_info:
+        logging.info(disk)
+    logging.info("\nNETWORK PORT:")
+    logging.info(f" Port Status: {port_status}")
+    logging.info("\nCUDA:")
+    logging.info(f" CUDA Working: {cuda_test_result}")
+    logging.info(f" CUDA_HOME: {cuda_home}")
+    if found_paths:
+        logging.info(f" Cublas64_11 Path: {', '.join(found_paths)}")
+    else:
+        logging.info(f" Cublas64_11 Path: Not found in any search path directories.")
+    logging.info("\nPYTHON & PYTORCH:")
+    logging.info(f" Torch Version: {torch_version}")
+    logging.info(f" Python Version: {platform.python_version()}")
+    logging.info(f" Python Version Info: {python_version_info}")
+    logging.info(f" Python Executable: {python_executable}")
+    logging.info(f" Python Virtual Environment: {python_virtual_env} (Should be N/A when in Text-generation-webui Conda Python environment)")
+    logging.info(f" Conda Environment: {conda_env}")
     logging.info("\nPython Search Path:")
     for path in search_path:
         logging.info(f"  {path}")
-    logging.info("\nOS PATH Environment Variable:")
+    logging.info("\nOS SEARCHPATH ENVIRONMENT:")
     for path in path_env.split(';'):
         logging.info(f"  {path}")
     if required_packages:  # Check if the dictionary is not empty
-        logging.info("\nPackage Versions:")
+        logging.info("\nPACKAGE VERSIONS vs REQUIREMENTS FILE:")
         max_package_length = max(len(package) for package in required_packages.keys())
         for package_name, (operator, required_version) in required_packages.items():
             installed_version = installed_packages.get(package_name, 'Not installed')
-            logging.info(f"{package_name.ljust(max_package_length)}  Required: {operator} {required_version.ljust(12)}  Installed: {installed_version}")
-    logging.info(f"GPU Information:\n{gpu_info}")
-    logging.info("Package Versions:")
+            logging.info(f" {package_name.ljust(max_package_length)}  Required: {operator} {required_version.ljust(12)}  Installed: {installed_version}")
+    logging.info("\nPYTHON PACKAGES:")
     for package, version in package_versions.items():
-        logging.info(f"{package}>= {version}")
+        logging.info(f" {package}>= {version}")
 
     # Print to screen
     print(f"\n\033[94mOS Version:\033[0m \033[92m{os_version}\033[0m")
     print(f"\033[94mOS Ver note:\033[0m \033[92m(Windows 11 will say build is 10.x.22xxx)\033[0m")
-    print(f"\033[94mCUDA_HOME:\033[0m \033[92m{cuda_home}\033[0m")
     print(f"\033[94mSystem RAM:\033[0m \033[92m{system_ram}\033[0m")
-    print(f"\033[94mPort Status:\033[0m \033[92m{port_status}\033[0m")
-    print(f"\033[94mTorch Version:\033[0m \033[92m{torch_version}\033[0m")
+    for disk in disk_info:
+        print(f"\033[94mDisk:\033[0m \033[92m{disk}\033[0m")
+    print(f"\033[94m\nGPU Information:\033[0m {gpu_info}")
+    print(f"\033[94mPort Status:\033[0m \033[92m{port_status}\033[0m\n")
+    if "Fail" in cuda_test_result:
+        print(f"\033[91mCUDA Working:\033[0m \033[91m{cuda_test_result}\033[0m")
+    else:
+        print(f"\033[94mCUDA Working:\033[0m \033[92m{cuda_test_result}\033[0m")
+    print(f"\033[94mCUDA_HOME:\033[0m \033[92m{cuda_home}\033[0m")
+    if found_paths:
+        print(f"\033[94mCublas64_11 Path:\033[0m \033[92m{', '.join(found_paths)}\033[0m")
+    else:
+        print(f"\033[94mCublas64_11 Path:\033[0m \033[91mNot found in any search path directories.\033[0m")    
+    print(f"\033[94m\nTorch Version:\033[0m \033[92m{torch_version}\033[0m")
     print(f"\033[94mPython Version:\033[0m \033[92m{platform.python_version()}\033[0m")
-    print(f"\033[94mPython Version Info:\033[0m \033[92m{python_version_info}\033[0m")
     print(f"\033[94mPython Executable:\033[0m \033[92m{python_executable}\033[0m")
-    print(f"\033[94mPython Virtual Environment:\033[0m \033[92m{python_virtual_env}\033[0m (Should be N/A when in Text-generation-webui Conda Python environment)")
     print(f"\033[94mConda Environment:\033[0m \033[92m{conda_env}\033[0m")
     print(f"\n\033[94mPython Search Path:\033[0m")
     for path in search_path:
         print(f"  {path}")
-    print(f"\n\033[94mOS Search PATH Environment Variable:\033[0m")
-    for path in path_env.split(';'):
-        print(f"  {path}")
     if required_packages:  # Check if the dictionary is not empty
         print("\033[94m\nRequirements file package comparison:\033[0m")
         max_package_length = max(len(package) for package in required_packages.keys())
@@ -214,7 +300,7 @@ def log_system_info():
             color_installed = "\033[92m" if condition_met else "\033[91m"
 
             # Print colored output
-            print(f"{package_name.ljust(max_package_length)}  Required: {color_required}{operator} {required_version.ljust(12)}\033[0m  Installed: {color_installed}{installed_version}\033[0m")
+            print(f"  {package_name.ljust(max_package_length)}  Required: {color_required}{operator} {required_version.ljust(12)}\033[0m  Installed: {color_installed}{installed_version}\033[0m")
 
         print("\nOn Nvidia Graphics cards machines, if your \033[92mInstalled\033[0m version of \033[92mTorch\033[0m and \033[92mTorchaudio\033[0m does")    
         print("not have \033[92m+cu118\033[0m (Cuda 11.8) or \033[92m+cu121\033[0m (Cuda 12.1) listed after them, you do not have CUDA")
@@ -231,9 +317,9 @@ def log_system_info():
         """)
         print(explanation.strip())
     print("")
-    print(f"GPU Information:{gpu_info}")
-    print(f"\033[94mDiagnostic log created:\033[0m \033[92mdiagnostics.log\033[0m")
-    print(f"\033[94mPlease upload the log file with any support ticket.\033[0m")
+    print(f"\033[94mDiagnostic log created:\033[0m \033[92mdiagnostics.log. \033[94mA brief summary of results is displayed above on\033[0m")
+    print(f"\033[94mscreen. Please see the log file for more detail.\033[0m")
+    print(f"\033[94m\nPlease upload the log file with any support ticket.\033[0m")
 
 if __name__ == "__main__":
-    log_system_info()
+    log_system_info()

docker-compose.yml

@@ -1,13 +1,27 @@
 version: '3.8'
 services:
   alltalk-tts:
-    image: erew123/alltalk_tts:cpu
+    image: ${IMAGE:-alltalk:v1-9c}
     restart: unless-stopped
     ports:
       - "7851:7851"
+      - "7852:7852"
     volumes:
       - ./outputs:/app/outputs/
       - ./models:/app/models/
       - ./voices:/app/voices/
       - ./finetune/put-voice-samples-in-here:/app/finetune/put-voice-samples-in-here
       - ./dockerconfig.json:/app/confignew.json
+    healthcheck:
+      test: ["CMD", "wget", "-qO-", "http://localhost:7851/api/ready"]
+      interval: 1m30s
+      timeout: 30s
+      retries: 5
+      start_period: 30s
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [ gpu ]

finetune/compact.py

@@ -1,26 +0,0 @@
-import torch
-import os
-MODEL_PATH = "best_model.pth"
-# Check if best_model.pth exists
-if not os.path.exists(MODEL_PATH):
-    print(f"\nCannot find \033[94m{MODEL_PATH}\033[0m in the current folder.")
-    
-    # Check if model.pth exists as an alternative
-    ALTERNATIVE_PATH = "model.pth"
-    if os.path.exists(ALTERNATIVE_PATH):
-        print(f"\nIf your model is currently called \033[93m{ALTERNATIVE_PATH}\033[0m please rename it to \033[94mbest_model.pth\033[0m.")
-    else:
-        print(f"Please put \033[91mbest_model.pth\033[0m in the current folder or rename your model file to \033[94mbest_model.pth\033[0m.")
-    exit(1)
-# Attempt to load the model
-try:
-    checkpoint = torch.load(MODEL_PATH, map_location=torch.device("cpu"))
-except Exception as e:
-    print("Error loading checkpoint:", e)
-    raise
-del checkpoint["optimizer"]
-for key in list(checkpoint["model"].keys()):
-    if "dvae" in key:
-        del checkpoint["model"][key]
-torch.save(checkpoint, "model.pth")
-print(f"\nYour compacted model is created \033[93mmodel.pth\033[0m.")

modeldownload.py

@@ -1,10 +1,13 @@
 import os
+import sys
 from pathlib import Path
 import requests
+from requests.exceptions import ConnectionError
 from tqdm import tqdm
 import importlib.metadata as metadata
 import json
 from packaging import version
+from datetime import datetime
 
 #################################################################
 #### LOAD PARAMS FROM confignew.json - REQUIRED FOR BRANDING ####
@@ -12,14 +15,12 @@ from packaging import version
 # STARTUP VARIABLE - Create "this_dir" variable as the current script directory
 this_dir = Path(__file__).parent.resolve()
 
-
 # load standard config file in and get settings
 def load_config(file_path):
     with open(file_path, "r") as config_file:
         config = json.load(config_file)
     return config
 
-
 config_file_path = this_dir / "confignew.json"
 params = load_config(config_file_path)
 
@@ -37,34 +38,26 @@ if modeldownload_config_file_path.exists():
     files_to_download = settings.get("files_to_download", {})
 else:
     # Default settings if the JSON file doesn't exist or is empty
-    print(
-        f"[{params['branding']}Startup] \033[91mWarning\033[0m modeldownload.json is missing so please re-download it and save it in the coquii_tts main folder."
-    )
-    print(
-        f"[{params['branding']}Startup] \033[91mWarning\033[0m API Local and XTTSv2 Local will error unless this is corrected."
-    )
+    print(f"[{params['branding']}Startup] \033[91mWarning\033[0m modeldownload.json is missing so please re-download it and save it in the coquii_tts main folder.")
+    print(f"[{params['branding']}Startup] \033[91mWarning\033[0m API Local and XTTSv2 Local will error unless this is corrected.")
 
 # Read the version specifier from requirements_nvidia.txt
-with open(this_dir / "requirements_nvidia.txt", "r") as req_file:
+with open(this_dir / "system" / "requirements" / "requirements_standalone.txt", "r") as req_file:
     requirements = req_file.readlines()
 
 tts_version_required = None
 for req in requirements:
-    if req.startswith("TTS>="):
-        tts_version_required = req.strip().split(">=")[1]
+    if req.startswith("TTS=="):
+        tts_version_required = req.strip().split("==")[1]
         break
 
 if tts_version_required is None:
-    raise ValueError(
-        f"[{params['branding']}Startup] \033[91mWarning\033[0m Could not find TTS version specifier in requirements_nvidia.txt"
-    )
-
+    raise ValueError(f"[{params['branding']}Startup] \033[91mWarning\033[0m Could not find TTS version specifier in requirements file")
 
 def create_directory_if_not_exists(directory):
     if not directory.exists():
         directory.mkdir(parents=True)
 
-
 def download_file(url, destination):
     response = requests.get(url, stream=True)
     total_size_in_bytes = int(response.headers.get("content-length", 0))
@@ -83,63 +76,118 @@ def download_file(url, destination):
 def check_tts_version():
     try:
         tts_version = metadata.version("tts")
-        print(
-            f"[{params['branding']}Startup] TTS version installed: \033[93m"
-            + tts_version
-            + "\033[0m"
-        )
+        print(f"[{params['branding']}Startup] \033[92mCurrent TTS Version    : \033[93m"+tts_version+"\033[0m")
 
         if version.parse(tts_version) < version.parse(tts_version_required):
-            print(
-                f"[{params['branding']}Startup] \033[91mWarning\033[0m TTS version is too old. Please upgrade to version \033[93m"
-                + tts_version_required
-                + "\033[0m or later.\033[0m"
-            )
-            print(
-                f"[{params['branding']}Startup] \033[91mWarning\033[0m At your terminal/command prompt \033[94mpip install --upgrade tts\033[0m"
-            )
+            print(f"[{params['branding']}Startup] \033[91mWarning\033[0m TTS version is too old. Please upgrade to version \033[93m"+tts_version_required+"\033[0m or later.\033[0m")
+            print(f"[{params['branding']}Startup] \033[91mWarning\033[0m At your terminal/command prompt \033[94mpip install --upgrade tts\033[0m")
         else:
-            print(f"[{params['branding']}Startup] TTS version is up to date.")
+            print(f"[{params['branding']}Startup] \033[92mCurrent TTS Version is :\033[93m Up to date\033[0m")
     except metadata.PackageNotFoundError:
-        print(
-            f"[{params['branding']}Startup] \033[91mWarning\033[0m TTS is not installed."
-        )
+        print(f"[{params['branding']}Startup] \033[91mWarning\033[0m TTS is not installed")
 
+def check_torch_version():
+    import torch
+    pytorch_version = torch.__version__
+    cuda_version = torch.version.cuda
+    major, minor, micro = sys.version_info[:3]
+    python_version = f"{major}.{minor}.{micro}"
+    print(f"[{params['branding']}Startup] \033[92mCurrent Python Version :\033[93m {python_version}\033[0m")
+    print(f"[{params['branding']}Startup] \033[92mCurrent PyTorch Version:\033[93m {pytorch_version}\033[0m")
+    if cuda_version is None:
+        print(f"[{params['branding']}Startup] \033[92mCurrent CUDA Version   :\033[91m CUDA is not available\033[0m")
+    else:
+        print(f"[{params['branding']}Startup] \033[92mCurrent CUDA Version   :\033[93m {cuda_version}\033[0m")
+
+def ordinal(n):
+    return "%d%s" % (n, "th" if 4 <= n % 100 <= 20 else {1: "st", 2: "nd", 3: "rd"}.get(n % 10, "th"))
+
+def format_datetime(iso_str):
+    # Parse the ISO 8601 string to datetime
+    dt = datetime.strptime(iso_str, "%Y-%m-%dT%H:%M:%SZ")
+    # Format the datetime into a more readable string
+    return dt.strftime(f"{ordinal(dt.day)} %B %Y at %H:%M")
+
+def fetch_latest_commit_sha_and_date(owner, repo):
+    url = f"https://api.github.com/repos/{owner}/{repo}/commits"
+    try:
+        response = requests.get(url)
+        if response.status_code == 200:
+            latest_commit = response.json()[0]
+            latest_commit_sha = latest_commit['sha']
+            latest_commit_date = latest_commit['commit']['committer']['date']
+            return latest_commit_sha, latest_commit_date
+        else:
+            print(f"[{params['branding']}Startup] \033[92m{params['branding']}Github updated :\033[91m Failed to fetch the latest commits due to an unexpected response from GitHub")
+            return None, None
+    except ConnectionError:
+        # This block is executed when a connection error occurs
+        print(f"[{params['branding']}Startup] \033[92m{params['branding']}Github updated :\033[91m Could not reach GitHub to check for updates\033[0m")
+        return None, None
+
+def read_or_initialize_sha(file_path):
+    if os.path.exists(file_path):
+        with open(file_path, 'r') as file:
+            data = json.load(file)
+            return data.get("last_known_commit_sha")
+    else:
+        # File doesn't exist, fetch the latest SHA and create the file
+        latest_commit_sha = fetch_latest_commit_sha_and_date(github_site, github_repository)
+        if latest_commit_sha:
+            with open(file_path, 'w') as file:
+                json.dump({"last_known_commit_sha": latest_commit_sha}, file)
+            return latest_commit_sha
+        else:
+            # Handle the case where GitHub couldn't be reached
+            return None
+
+def update_sha_file(file_path, new_sha):
+    with open(file_path, 'w') as file:
+        json.dump({"last_known_commit_sha": new_sha}, file)
 
 # Check and create directories
 if str(base_path) == "models":
     create_directory_if_not_exists(this_dir / base_path / model_path)
 else:
     create_directory_if_not_exists(base_path / model_path)
-    print(
-        f"[{params['branding']}Startup] \033[94mInfo\033[0m Custom path set in \033[93mmodeldownload.json\033[0m. Using the following settings:"
-    )
-    print(
-        f"[{params['branding']}Startup] \033[94mInfo\033[0m Base folder Path:\033[93m",
-        base_path,
-        "\033[0m",
-    )
-    print(
-        f"[{params['branding']}Startup] \033[94mInfo\033[0m Model folder Path:\033[93m",
-        model_path,
-        "\033[0m",
-    )
-    print(
-        f"[{params['branding']}Startup] \033[94mInfo\033[0m Full Path:\033[93m",
-        base_path / model_path,
-        "\033[0m",
-    )
+    print(f"[{params['branding']}Startup] \033[94mInfo\033[0m Custom path set in \033[93mmodeldownload.json\033[0m. Using the following settings:")
+    print(f"[{params['branding']}Startup] \033[94mInfo\033[0m Base folder Path:\033[93m",base_path,"\033[0m",)
+    print(f"[{params['branding']}Startup] \033[94mInfo\033[0m Model folder Path:\033[93m",model_path,"\033[0m",)
+    print(f"[{params['branding']}Startup] \033[94mInfo\033[0m Full Path:\033[93m",base_path / model_path,"\033[0m",)
 
 # Download files if they don't exist
-print("[" + params["branding"] + "Startup] Checking Model is Downloaded.")
+print(f"[{params['branding']}Startup] \033[92mModel is available     :\033[93m Checking\033[0m")
 for filename, url in files_to_download.items():
     if str(base_path) == "models":
         destination = this_dir / base_path / model_path / filename
     else:
         destination = Path(base_path) / model_path / filename
-
     if not destination.exists():
-        print(f"[{params['branding']}Startup] Downloading " + filename + "...")
+        print(f"[{params['branding']}Startup] \033[92mModel Downloading file : \033[93m" + filename + "\033[0m")
         download_file(url, destination)
+print(f"[{params['branding']}Startup] \033[92mModel is available     :\033[93m Checked\033[0m")
 
+github_site = "erew123"
+github_repository = "alltalk_tts"
+
+check_torch_version()
 check_tts_version()
+# Define the file path based on your directory structure
+sha_file_path = this_dir / "system" / "config" / "at_github_sha.json"
+
+# Read or initialize the SHA (adjusted for handling both SHA and date)
+last_known_commit_sha = read_or_initialize_sha(sha_file_path)  # Assuming adjustment for date
+
+# Assuming you have fetched the latest commit SHA and date
+latest_commit_sha, latest_commit_date = fetch_latest_commit_sha_and_date(github_site, github_repository)
+
+formatted_date = format_datetime(latest_commit_date) if latest_commit_date else "an unknown date"
+
+if latest_commit_sha and latest_commit_sha != last_known_commit_sha:
+    #print(f"There's an update available for alltalk_tts.")
+    print(f"[{params['branding']}Startup] \033[92m{params['branding']}Github updated :\033[93m {formatted_date}\033[0m")
+    # Update the file with the new SHA
+    update_sha_file(sha_file_path, latest_commit_sha)
+elif latest_commit_sha == last_known_commit_sha:
+    #print(f"Your alltalk_tts software is up to date.")
+    print(f"[{params['branding']}Startup] \033[92m{params['branding']}Github updated :\033[93m {formatted_date}\033[0m")

nvidia.Dockerfile

@@ -1,20 +1,22 @@
-FROM nvidia/cuda:12.1.1-devel-ubuntu22.04
-ENV HOST 0.0.0.0
-RUN apt-get update && apt-get upgrade -y \
-    && apt-get install -y git build-essential portaudio19-dev \
-    python3 python3-pip gcc wget \
-    ocl-icd-opencl-dev opencl-headers clinfo \
-    libclblast-dev libopenblas-dev \
-    && mkdir -p /etc/OpenCL/vendors && echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd \
-    && ln -s /usr/bin/python3 /usr/bin/python
-WORKDIR /app
-COPY . .
-ENV CUDA_DOCKER_ARCH=all
-
-RUN pip install --no-cache-dir -r requirements_nvidia.txt && \
-    pip install --no-cache-dir -r requirements_finetune.txt && \
-    pip install --no-cache-dir -r requirements_other.txt && \
-    pip install --no-cache-dir deepspeed
-EXPOSE 7851
-RUN chmod +x launch.sh
+FROM nvidia/cuda:12.1.1-devel-ubuntu22.04
+ENV HOST 0.0.0.0
+RUN apt-get update && apt-get upgrade -y \
+    && apt-get install -y git build-essential portaudio19-dev \
+    python3 python3-pip gcc wget \
+    ocl-icd-opencl-dev opencl-headers clinfo \
+    libclblast-dev libopenblas-dev \
+    && mkdir -p /etc/OpenCL/vendors && echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd \
+    && ln -s /usr/bin/python3 /usr/bin/python
+
+RUN mkdir /app/pip_cache
+ENV PIP_CACHE_DIR=/app/pip_cache
+
+WORKDIR /app
+COPY . .
+ENV CUDA_DOCKER_ARCH=all
+RUN pip install --no-cache-dir --no-deps -r system/requirements/requirements_standalone.txt --cache-dir=/app/pip_cache && \
+    pip install --no-cache-dir deepspeed --cache-dir=/app/pip_cache
+
+EXPOSE 7851
+RUN chmod +x launch.sh
 ENTRYPOINT ["sh", "-c", "./launch.sh"]

requirements_finetune.txt

@@ -1,7 +0,0 @@
-gradio>=3.50.2
-torch>=2.1.0+cu118
-torchaudio>=2.1.0+cu118
-TTS==0.21.3
-faster-whisper>=0.10.0
-tqdm>=4.66.0
-pandas>=1.5.0

requirements_nvidia.txt

@@ -1,18 +0,0 @@
-numpy>=1.22.0
-soundfile>=0.12.1
-uvicorn>=0.24.0.post1
-transformers>=4.37.1
-TTS>=0.21.3
-torch>=2.1.0+cu118
-torchaudio>=2.1.0+cu118
-fastapi>=0.104.1
-Jinja2>=3.1.2
-requests>=2.31.0
-tqdm>=4.66.1
-importlib-metadata>=4.8.1
-packaging>=23.2
-pydantic>=1.10.13
-sounddevice>=0.4.6
-python-multipart>=0.0.6
-cutlet>=0.3.0
-unidic-lite>=1.0.8

script.py

@@ -9,12 +9,16 @@ import threading
 import signal
 import sys
 import atexit
+import shutil
 from pathlib import Path
 from datetime import datetime, timedelta
 import re
 import numpy as np
 import soundfile as sf
 import uuid
+import logging
+# Store the current disable level
+current_disable_level = logging.getLogger().manager.disable
 
 ######################################
 #### ALLTALK ALLOWED STARTUP TIME ####
@@ -30,43 +34,109 @@ startup_wait_time = 120
 # STARTUP VARIABLE - Create "this_dir" variable as the current script directory
 this_dir = Path(__file__).parent.resolve()
 
-
 # load config file in and get settings
 def load_config(file_path):
     with open(file_path, "r") as config_file:
         config = json.load(config_file)
     return config
-
-
+                               
 config_file_path = this_dir / "confignew.json"
 # Load the params dictionary from the confignew.json file
 params = load_config(config_file_path)
 
+print(f"[{params['branding']}Startup]\033[94m     _    _ _ \033[1;35m_____     _ _     \033[0m  _____ _____ ____  ")
+print(f"[{params['branding']}Startup]\033[94m    / \  | | |\033[1;35m_   _|_ _| | | __ \033[0m |_   _|_   _/ ___| ")
+print(f"[{params['branding']}Startup]\033[94m   / _ \ | | |\033[1;35m | |/ _` | | |/ / \033[0m   | |   | | \___ \ ")
+print(f"[{params['branding']}Startup]\033[94m  / ___ \| | |\033[1;35m | | (_| | |   <  \033[0m   | |   | |  ___) |")
+print(f"[{params['branding']}Startup]\033[94m /_/   \_\_|_|\033[1;35m |_|\__,_|_|_|\_\ \033[0m   |_|   |_| |____/ ")
+print(f"[{params['branding']}Startup]")
+
+##############################################
+#### Update any changes to confignew.json ####
+##############################################
+
+update_config_path = this_dir / "system" / "config" / "at_configupdate.json"
+downgrade_config_path = this_dir / "system" / "config" / "at_configdowngrade.json"
+
+def changes_needed(main_config, update_config, downgrade_config):
+    """Check if there are any changes to be made to the main configuration."""
+    for key in downgrade_config.keys():
+        if key in main_config:
+            return True
+    for key, value in update_config.items():
+        if key not in main_config:
+            return True
+    return False
+
+def update_config(config_file_path, update_config_path, downgrade_config_path):
+    try:
+        with open(config_file_path, 'r') as file:
+            main_config = json.load(file)
+        with open(update_config_path, 'r') as file:
+            update_config = json.load(file)
+        with open(downgrade_config_path, 'r') as file:
+            downgrade_config = json.load(file)
+
+        # Determine if changes are needed
+        if changes_needed(main_config, update_config, downgrade_config):
+            # Backup with timestamp to avoid overwriting
+            timestamp = datetime.now().strftime("%Y%m%d%H%M%S")
+            backup_path = config_file_path.with_suffix(f".{timestamp}.bak")
+            logging.info(f"Creating backup of the main config to {backup_path}")
+            shutil.copy(config_file_path, backup_path)
+
+            # Proceed with updates and downgrades
+            for key, value in update_config.items():
+                if key not in main_config:
+                    main_config[key] = value
+            for key in downgrade_config.keys():
+                if key in main_config:
+                    del main_config[key]
+
+            # Save the updated configuration
+            with open(config_file_path, 'w') as file:
+                json.dump(main_config, file, indent=4)
+
+            print(f"[{params['branding']}Startup] \033[92mConfig file check      : \033[91mUpdates applied\033[0m")
+        else:
+            print(f"[{params['branding']}Startup] \033[92mConfig file check      : \033[93mNo Updates required\033[0m")
+
+    except Exception as e:
+        print(f"[{params['branding']}Startup] \033[92mConfig file check      : \033[91mError updating\033[0m")
+
+# Update the configuration
+update_config(config_file_path, update_config_path, downgrade_config_path)
+# Re-Load the params dictionary from the confignew.json file
+params = load_config(config_file_path)
+
+#########################################
+#### Continue on with Startup Checks ####
+#########################################
+            
 # Required for sentence splitting
 try:
     from TTS.api import TTS
     from TTS.utils.synthesizer import Synthesizer
 except ModuleNotFoundError:
-    logger.error(
-        f"[{params['branding']}]\033[91mWarning\033[0m Could not find the TTS module. Make sure to install the requirements for the {params['branding']} extension."
-        f"[{params['branding']}]\033[91mWarning\033[0m Linux / Mac:\npip install -r /alltalk_tts/requirements.txt\n"
-        f"[{params['branding']}]\033[91mWarning\033[0m Windows:\npip install -r \\alltalk_tts\\requirements.txt\n"
-        f"[{params['branding']}]\033[91mWarning\033[0m If you used the one-click installer, paste the command above in the terminal window launched after running the cmd_ script. On Windows, that's cmd_windows.bat."
-    )
-    raise
+    # Inform the user about the missing module and suggest next steps
+    print(f"[{params['branding']}]\033[91mWarning\033[0m Could not find the TTS module. Make sure to install the requirements for the {params['branding']} extension.")
+    print(f"[{params['branding']}]\033[91mWarning\033[0m Please use the ATSetup utility or check the Github installation instructions.")
+    # Re-raise the ModuleNotFoundError to stop the program and print the traceback
+    raise 
 
-# IMPORT - Attempt Importing DeepSpeed (required for displaying Deepspeed checkbox in gradio)
+# Suppress logging
+logging.disable(logging.ERROR)
 try:
     import deepspeed
-
     deepspeed_installed = True
 except ImportError:
     deepspeed_installed = False
+# Restore previous logging level
+logging.disable(current_disable_level)
 
 # Import gradio if being used within text generation webUI
 try:
     import gradio as gr
-
     from modules import chat, shared, ui_chat
     from modules.logging_colors import logger
     from modules.ui import create_refresh_button
@@ -75,9 +145,10 @@ try:
     # This is set to check if the script is being run within text generation webui or as a standalone script. False is running as part of text gen web ui or a gradio interface
     running_in_standalone = False
     output_folder_wav = params["output_folder_wav"]
+    print(f"[{params['branding']}Startup] \033[92m{params['branding']}startup Mode   : \033[93mText-Gen-webui mode\033[0m")
 except ModuleNotFoundError:
     output_folder_wav = params["output_folder_wav_standalone"]
-    print(f"[{params['branding']}Startup] Running script.py in standalone mode")
+    print(f"[{params['branding']}Startup] \033[92m{params['branding']}startup Mode   : \033[93mStandalone mode\033[0m")
     # This is set to check if the script is being run within text generation webui or as a standalone script. true means standalone
     running_in_standalone = True
 
@@ -85,7 +156,7 @@ except ModuleNotFoundError:
 #### STARTUP VARIABLES ####
 ###########################
 # STARTUP VARIABLE - Import languges file for Gradio to be able to display them in the interface
-with open(this_dir / "languages.json", encoding="utf8") as f:
+with open(this_dir / "system" / "config" / "languages.json", encoding="utf8") as f:
     languages = json.load(f)
 # Create a global lock
 process_lock = threading.Lock()
@@ -98,23 +169,12 @@ def get_available_voices():
     return sorted([voice.name for voice in Path(f"{this_dir}/voices").glob("*.wav")])
 
 
-#########################
-#### LICENSE DISPLAY ####
-#########################
-# STARTUP Display Licence Information
-print(f"[{params['branding']}Startup] \033[94mCoqui Public Model License\033[0m")
-print(f"[{params['branding']}Startup] \033[94mhttps://coqui.ai/cpml.txt\033[0m")
-
-
 ############################################
 #### DELETE OLD OUTPUT WAV FILES IF SET ####
 ############################################
 def delete_old_files(folder_path, days_to_keep):
     current_time = datetime.now()
-    print(
-        f"[{params['branding']}Startup] Deletion of old output folder WAV files is currently enabled and set at",
-        delete_output_wavs_setting,
-    )
+    print(f"[{params['branding']}Startup] \033[92mWAV file deletion      :\033[93m", delete_output_wavs_setting,"\033[0m")
     for file_name in os.listdir(folder_path):
         file_path = os.path.join(folder_path, file_name)
         if os.path.isfile(file_path):
@@ -130,20 +190,18 @@ output_folder_wav = os.path.normpath(output_folder_wav)
 
 # Check and perform file deletion
 if delete_output_wavs_setting.lower() == "disabled":
-    print(
-        "["
-        + params["branding"]
-        + "Startup] Old output wav file deletion is set to disabled."
-    )
+    print("["+ params["branding"]+"Startup] \033[92mWAV file deletion      :\033[93m Disabled\033[0m")
 else:
     try:
         days_to_keep = int(delete_output_wavs_setting.split()[0])
         delete_old_files(output_folder_wav, days_to_keep)
     except ValueError:
-        print(
-            f"[{params['branding']}Startup] Invalid setting for deleting old wav files. Please use 'Disabled' or 'X Days' format."
-        )
+        print(f"[{params['branding']}Startup] \033[92mWAV file deletion      :\033[93m Invalid setting for deleting old wav files. Please use 'Disabled' or 'X Days' format\033[0m")
 
+if deepspeed_installed:
+    print(f"[{params['branding']}Startup] \033[92mDeepSpeed version      :\033[93m",deepspeed.__version__,"\033[0m")
+else:
+    print(f"[{params['branding']}Startup] \033[92mDeepSpeed version      :\033[91m Not Detected\033[0m")
 
 ########################
 #### STARTUP CHECKS ####
@@ -153,8 +211,6 @@ def check_required_files():
     this_dir = Path(__file__).parent.resolve()
     download_script_path = this_dir / "modeldownload.py"
     subprocess.run(["python", str(download_script_path)])
-    print(f"[{params['branding']}Startup] All required files are present.")
-
 
 # STARTUP Call Check routine
 check_required_files()
@@ -174,7 +230,7 @@ if finetuned_model:
         (trained_model_directory / file).exists() for file in required_files
     )
 if finetuned_model:
-    print(f"[{params['branding']}Startup] Finetuned model \033[93mDetected\033[0m")
+    print(f"[{params['branding']}Startup] \033[92mFinetuned model        :\033[93m Detected\033[0m")
 
 ####################################################
 #### SET GRADIO BUTTONS BASED ON confignew.json ####
@@ -190,7 +246,6 @@ elif params["tts_method_xtts_local"] == True:
 # Set the default for Narrated text without asterisk or quotes to be Narrator
 non_quoted_text_is = True
 
-
 ######################
 #### GRADIO STUFF ####
 ######################
@@ -237,9 +292,7 @@ script_path = this_dir / "tts_server.py"
 
 
 def signal_handler(sig, frame):
-    print(
-        f"[{params['branding']}Shutdown] \033[94mReceived Ctrl+C, terminating subprocess\033[92m"
-    )
+    print(f"[{params['branding']}Shutdown] \033[94mReceived Ctrl+C, terminating subprocess\033[92m")
     if process.poll() is None:
         process.terminate()
         process.wait()  # Wait for the subprocess to finish
@@ -258,33 +311,20 @@ else:
     process = subprocess.Popen(["python", script_path])
     # Check if the subprocess has started successfully
     if process.poll() is None:
-        print(f"[{params['branding']}Startup] TTS Subprocess starting")
+        print(f"[{params['branding']}Startup] \033[92mTTS Subprocess         :\033[93m Starting up\033[0m")
         print(f"[{params['branding']}Startup]")
         print(
-            f"[{params['branding']}Startup] \033[94m {params['branding']}Settings & Documentation:\033[00m",
+            f"[{params['branding']}Startup] \033[94m{params['branding']}Settings & Documentation:\033[00m",
             f"\033[92mhttp://{params['ip_address']}:{params['port_number']}\033[00m",
         )
         print(f"[{params['branding']}Startup]")
     else:
-        print(
-            f"[{params['branding']}Startup] \033[91mWarning\033[0m TTS Subprocess Webserver failing to start process"
-        )
-        print(
-            f"[{params['branding']}Startup] \033[91mWarning\033[0m It could be that you have something on port:",
-            params["port_number"],
-        )
-        print(
-            f"[{params['branding']}Startup] \033[91mWarning\033[0m Or you have not started in a Python environement with all the necesssary bits installed"
-        )
-        print(
-            f"[{params['branding']}Startup] \033[91mWarning\033[0m Check you are starting Text-generation-webui with either the start_xxxxx file or the Python environment with cmd_xxxxx file."
-        )
-        print(
-            f"[{params['branding']}Startup] \033[91mWarning\033[0m xxxxx is the type of OS you are on e.g. windows, linux or mac."
-        )
-        print(
-            f"[{params['branding']}Startup] \033[91mWarning\033[0m Alternatively, you could check no other Python processes are running that shouldnt be e.g. Restart your computer is the simple way."
-        )
+        print(f"[{params['branding']}Startup] \033[91mWarning\033[0m TTS Subprocess Webserver failing to start process")
+        print(f"[{params['branding']}Startup] \033[91mWarning\033[0m It could be that you have something on port:",params["port_number"],)
+        print(f"[{params['branding']}Startup] \033[91mWarning\033[0m Or you have not started in a Python environement with all the necesssary bits installed")
+        print(f"[{params['branding']}Startup] \033[91mWarning\033[0m Check you are starting Text-generation-webui with either the start_xxxxx file or the Python environment with cmd_xxxxx file.")
+        print(f"[{params['branding']}Startup] \033[91mWarning\033[0m xxxxx is the type of OS you are on e.g. windows, linux or mac.")
+        print(f"[{params['branding']}Startup] \033[91mWarning\033[0m Alternatively, you could check no other Python processes are running that shouldnt be e.g. Restart your computer is the simple way.")
         # Cleanly kill off this script, but allow text-generation-webui to keep running, albeit without this alltalk_tts
         sys.exit(1)
 
@@ -300,26 +340,14 @@ else:
                 break
         except requests.RequestException as e:
             # Print the exception for debugging purposes
-            print(
-                f"[{params['branding']}Startup] \033[91mWarning\033[0m TTS Subprocess has NOT started up yet, Will keep trying for {timeout} seconds maximum. Please wait."
-            )
+            print(f"[{params['branding']}Startup] \033[91mWarning\033[0m TTS Subprocess has NOT started up yet, Will keep trying for {timeout} seconds maximum. Please wait.")
         time.sleep(5)
     else:
-        print(
-            f"\n[{params['branding']}Startup] Startup timed out. Full help available here \033[92mhttps://github.com/erew123/alltalk_tts#-help-with-problems\033[0m"
-        )
-        print(
-            f"[{params['branding']}Startup] On older system you may wish to open and edit \033[94mscript.py\033[0m with a text editor and changing the"
-        )
-        print(
-            f"[{params['branding']}Startup] \033[94mstartup_wait_time = 120\033[0m setting to something like \033[94mstartup_wait_time = 240\033[0m as this will allow"
-        )
-        print(
-            f"[{params['branding']}Startup] AllTalk more time to try load the model into your VRAM. Otherise please visit the Github for"
-        )
-        print(
-            f"[{params['branding']}Startup] a list of other possible troubleshooting options."
-        )
+        print(f"\n[{params['branding']}Startup] Startup timed out. Full help available here \033[92mhttps://github.com/erew123/alltalk_tts#-help-with-problems\033[0m")
+        print(f"[{params['branding']}Startup] On older system you may wish to open and edit \033[94mscript.py\033[0m with a text editor and changing the")
+        print(f"[{params['branding']}Startup] \033[94mstartup_wait_time = 120\033[0m setting to something like \033[94mstartup_wait_time = 240\033[0m as this will allow")
+        print(f"[{params['branding']}Startup] AllTalk more time to try load the model into your VRAM. Otherise please visit the Github for")
+        print(f"[{params['branding']}Startup] a list of other possible troubleshooting options.")
         # Cleanly kill off this script, but allow text-generation-webui to keep running, albeit without this alltalk_tts
         sys.exit(1)
 
@@ -347,33 +375,31 @@ def send_reload_request(tts_method):
                 params["tts_method_xtts_local"] = False
                 params["tts_method_api_tts"] = True
                 params["deepspeed_activate"] = False
-                audio_path = this_dir / "templates" / "apitts.wav"
+                audio_path = this_dir / "system" / "at_sounds" / "apitts.wav"
                 tts_method_xtts_ft = False
             elif tts_method == "API Local":
                 params["tts_method_api_tts"] = False
                 params["tts_method_xtts_local"] = False
                 params["tts_method_api_local"] = True
                 params["deepspeed_activate"] = False
-                audio_path = this_dir / "templates" / "apilocal.wav"
+                audio_path = this_dir / "system" / "at_sounds" / "apilocal.wav"
                 tts_method_xtts_ft = False
             elif tts_method == "XTTSv2 Local":
                 params["tts_method_api_tts"] = False
                 params["tts_method_api_local"] = False
                 params["tts_method_xtts_local"] = True
-                audio_path = this_dir / "templates" / "xttslocal.wav"
+                audio_path = this_dir / "system" / "at_sounds" / "xttslocal.wav"
                 tts_method_xtts_ft = False
             elif tts_method == "XTTSv2 FT":
                 params["tts_method_api_tts"] = False
                 params["tts_method_api_local"] = False
                 params["tts_method_xtts_local"] = False
-                audio_path = this_dir / "templates" / "xttsfinetuned.wav"
+                audio_path = this_dir / "system" / "at_sounds" / "xttsfinetuned.wav"
                 tts_method_xtts_ft = True
         return f'<audio src="file/{audio_path}" controls autoplay></audio>'
     except requests.exceptions.RequestException as e:
         # Handle the HTTP request error
-        print(
-            f"[{params['branding']}Server] \033[91mWarning\033[0m Error during request to webserver process: {e}"
-        )
+        print(f"[{params['branding']}Server] \033[91mWarning\033[0m Error during request to webserver process: {e}")
         return {"status": "error", "message": str(e)}
 
 
@@ -385,9 +411,9 @@ def send_lowvram_request(low_vram):
     try:
         params["tts_model_loaded"] = False
         if low_vram:
-            audio_path = this_dir / "templates" / "lowvramenabled.wav"
+            audio_path = this_dir / "system" / "at_sounds" / "lowvramenabled.wav"
         else:
-            audio_path = this_dir / "templates" / "lowvramdisabled.wav"
+            audio_path = this_dir / "system" / "at_sounds" / "lowvramdisabled.wav"
         url = f"{base_url}/api/lowvramsetting?new_low_vram_value={low_vram}"
         headers = {"Content-Type": "application/json"}
         response = requests.post(url, headers=headers)
@@ -400,9 +426,7 @@ def send_lowvram_request(low_vram):
         return f'<audio src="file/{audio_path}" controls autoplay></audio>'
     except requests.exceptions.RequestException as e:
         # Handle the HTTP request error
-        print(
-            f"[{params['branding']}Server] \033[91mWarning\033[0m Error during request to webserver process: {e}"
-        )
+        print(f"[{params['branding']}Server] \033[91mWarning\033[0m Error during request to webserver process: {e}")
         return {"status": "error", "message": str(e)}
 
 
@@ -414,10 +438,9 @@ def send_deepspeed_request(deepspeed_param):
     try:
         params["tts_model_loaded"] = False
         if deepspeed_param:
-            audio_path = this_dir / "templates" / "deepspeedenabled.wav"
+            audio_path = this_dir / "system" / "at_sounds" / "deepspeedenabled.wav"
         else:
-            audio_path = this_dir / "templates" / "deepspeeddisabled.wav"
-
+            audio_path = this_dir / "system" / "at_sounds" / "deepspeeddisabled.wav"
         url = f"{base_url}/api/deepspeed?new_deepspeed_value={deepspeed_param}"
         headers = {"Content-Type": "application/json"}
         response = requests.post(url, headers=headers)
@@ -430,9 +453,7 @@ def send_deepspeed_request(deepspeed_param):
         return f'<audio src="file/{audio_path}" controls autoplay></audio>'
     except requests.exceptions.RequestException as e:
         # Handle the HTTP request error
-        print(
-            f"[{params['branding']}Server] \033[91mWarning\033[0m Error during request to webserver process: {e}"
-        )
+        print(f"[{params['branding']}Server] \033[91mWarning\033[0m Error during request to webserver process: {e}")
         return {"status": "error", "message": str(e)}
 
 
@@ -465,9 +486,7 @@ Synthesizer.split_into_sentences = new_split_into_sentences
 def before_audio_generation(string, params):
     # Check Model is loaded into cuda or cpu and error if not
     if not params["tts_model_loaded"]:
-        print(
-            f"[{params['branding']}Model] \033[91mWarning\033[0m Model is still loading, please wait before trying to generate TTS"
-        )
+        print(f"[{params['branding']}Model] \033[91mWarning\033[0m Model is still loading, please wait before trying to generate TTS")
         return
     string = html.unescape(string) or random_sentence()
     if string == "":
@@ -491,13 +510,9 @@ def combine(audio_files, output_folder, state):
 
     # Save the combined audio to a file with a specified sample rate
     if "character_menu" in state:
-        output_file_path = os.path.join(
-            output_folder, f'{state["character_menu"]}_{int(time.time())}_combined.wav'
-        )
+        output_file_path = os.path.join(output_folder, f'{state["character_menu"]}_{int(time.time())}_combined.wav')
     else:
-        output_file_path = os.path.join(
-            output_folder, f"TTSOUT_{int(time.time())}_combined.wav"
-        )
+        output_file_path = os.path.join(output_folder, f"TTSOUT_{int(time.time())}_combined.wav")
     sf.write(output_file_path, audio, samplerate=sample_rate)
     # Clean up unnecessary files
     for audio_file in audio_files:
@@ -511,7 +526,7 @@ def combine(audio_files, output_folder, state):
 ################################
 # PREVIEW VOICE - Generate Random Sentence if Voice Preview box is empty
 def random_sentence():
-    with open(this_dir / "harvard_sentences.txt") as f:
+    with open(this_dir / "system" / "config" / "harvard_sentences.txt") as f:
         return random.choice(list(f))
 
 
@@ -544,9 +559,7 @@ def voice_preview(string):
         )
     # Check if lock is already acquired
     if process_lock.locked():
-        print(
-            f"[{params['branding']}Model] \033[91mWarning\033[0m Audio generation is already in progress. Please wait."
-        )
+        print(f"[{params['branding']}Model] \033[91mWarning\033[0m Audio generation is already in progress. Please wait.")
         return
     if generate_response.get("status") == "generate-success":
         # Handle Gradio and playback
@@ -557,6 +570,10 @@ def voice_preview(string):
         return f"[{params['branding']}Server] Audio generation failed. Status: {generate_response.get('status')}"
 
 
+#######################
+#### TEXT CLEANING ####
+#######################
+
 def process_text(text):
     # Normalize HTML encoded quotes
     text = html.unescape(text)
@@ -606,6 +623,30 @@ def process_text(text):
     return ordered_parts
 
 
+########################
+#### IMAGE CLEANING ####
+########################
+
+img_pattern = r'<img[^>]*src\s*=\s*["\'][^"\'>]+["\'][^>]*>'
+
+def extract_and_remove_images(text):
+    """
+    Extracts all image data from the text and removes it for clean TTS processing.
+    Returns the cleaned text and the extracted image data.
+    """
+    img_matches = re.findall(img_pattern, text)
+    img_info = "\n".join(img_matches)  # Store extracted image data
+    cleaned_text = re.sub(img_pattern, '', text)  # Remove images from text
+    return cleaned_text, img_info
+
+def reinsert_images(text, img_info):
+    """
+    Reinserts the previously extracted image data back into the text.
+    """
+    if img_info:  # Check if there are images to reinsert
+        text += f"\n\n{img_info}"
+    return text
+
 #################################
 #### TTS STANDARD GENERATION ####
 #################################
@@ -613,12 +654,12 @@ def process_text(text):
 def output_modifier(string, state):
     if not params["activate"]:
         return string
-    original_string = string
-    # print("ORIGINAL STRING IS:", original_string)
-    cleaned_string = before_audio_generation(string, params)
+    img_info = ""
+    cleaned_text, img_info = extract_and_remove_images(string)
+    # print("Cleaned STRING IS:", cleaned_text)
+    cleaned_string = before_audio_generation(cleaned_text, params)
     if cleaned_string is None:
         return
-    string = cleaned_string
     language_code = languages.get(params["language"])
     temperature = params["local_temperature"]
     repetition_penalty = params["local_repetition_penalty"]
@@ -627,7 +668,7 @@ def output_modifier(string, state):
     if process_lock.acquire(blocking=False):
         try:
             if params["narrator_enabled"]:
-                processed_parts = process_text(original_string)
+                processed_parts = process_text(cleaned_string)
 
                 audio_files_all_paragraphs = []
                 for part_type, part in processed_parts:
@@ -638,14 +679,10 @@ def output_modifier(string, state):
                     # Determine the voice to use based on the part type
                     if part_type == "narrator":
                         voice_to_use = params["narrator_voice"]
-                        print(
-                            f"[{params['branding']}TTSGen] \033[92mNarrator\033[0m"
-                        )  # Green
+                        print(f"[{params['branding']}TTSGen] \033[92mNarrator\033[0m")  # Green
                     elif part_type == "character":
                         voice_to_use = params["voice"]
-                        print(
-                            f"[{params['branding']}TTSGen] \033[36mCharacter\033[0m"
-                        )  # Yellow
+                        print(f"[{params['branding']}TTSGen] \033[36mCharacter\033[0m")  # Yellow
                     else:
                         # Handle ambiguous parts based on user preference
                         voice_to_use = (
@@ -661,9 +698,11 @@ def output_modifier(string, state):
                         print(f"[{params['branding']}TTSGen] {voice_description}")
 
                     # Replace multiple exclamation marks, question marks, or other punctuation with a single instance
-                    cleaned_part = re.sub(r"([!?.])\1+", r"\1", part)
+                    cleaned_part = re.sub(r"([!?.\u3002\uFF1F\uFF01\uFF0C])\1+", r"\1", part)
+                    # Replace "Chinese ellipsis" with a single dot
+                    cleaned_part = re.sub(r"\u2026{1,2}", ". ", cleaned_part)
                     # Further clean to remove any other unwanted characters
-                    cleaned_part = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0100-\u017F\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\u4E00-\u9FFF\u3400-\u4DBF\u20000-\u2A6DF\u3000-\u303F\$]', '', cleaned_part)
+                    cleaned_part = re.sub(r'[^a-zA-Z0-9\s.,;:!?\-\'"$\u0400-\u04FF\u00C0-\u00FF\u0150\u0151\u0170\u0171\u0900-\u097F\u2018\u2019\u201C\u201D\u3001\u3002\u3040-\u309F\u30A0-\u30FF\u4E00-\u9FFF\u3400-\u4DBF\uF900-\uFAFF\u0600-\u06FF\u0750-\u077F\uFB50-\uFDFF\uFE70-\uFEFF\uAC00-\uD7A3\u1100-\u11FF\u3130-\u318F\uFF01\uFF0c\uFF1A\uFF1B\uFF1F]', '', cleaned_part)
                     # Remove all newline characters (single or multiple)
                     cleaned_part = re.sub(r"\n+", " ", cleaned_part)
 
@@ -686,11 +725,13 @@ def output_modifier(string, state):
                 )
             else:
                 # Decode HTML entities first
-                cleaned_part = html.unescape(original_string)
+                cleaned_part = html.unescape(cleaned_string)
                 # Replace multiple instances of certain punctuation marks with a single instance
-                cleaned_part = re.sub(r"([!?.])\1+", r"\1", cleaned_part)
+                cleaned_part = re.sub(r"([!?.\u3002\uFF1F\uFF01\uFF0C])\1+", r"\1", cleaned_part)
+                # Replace "Chinese ellipsis" with a single dot
+                cleaned_part = re.sub(r"\u2026{1,2}", ". ", cleaned_part)
                 # Further clean to remove any other unwanted characters
-                cleaned_part = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0100-\u017F\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\u4E00-\u9FFF\u3400-\u4DBF\u20000-\u2A6DF\u3000-\u303F\$]', '', cleaned_part)
+                cleaned_part = re.sub(r'[^a-zA-Z0-9\s.,;:!?\-\'"$\u0400-\u04FF\u00C0-\u00FF\u0150\u0151\u0170\u0171\u0900-\u097F\u2018\u2019\u201C\u201D\u3001\u3002\u3040-\u309F\u30A0-\u30FF\u4E00-\u9FFF\u3400-\u4DBF\uF900-\uFAFF\u0600-\u06FF\u0750-\u077F\uFB50-\uFDFF\uFE70-\uFEFF\uAC00-\uD7A3\u1100-\u11FF\u3130-\u318F\uFF01\uFF0c\uFF1A\uFF1B\uFF1F]', '', cleaned_part)
                 # Remove all newline characters (single or multiple)
                 cleaned_part = re.sub(r"\n+", " ", cleaned_part)
                 # Process the part and give it a non-character name if being used vai API or standalone.
@@ -729,25 +770,15 @@ def output_modifier(string, state):
         if audio_path:
             # Handle Gradio and playback
             autoplay = "autoplay" if params["autoplay"] else ""
-            string = (
-                f'<audio src="file/{final_output_file}" controls {autoplay}></audio>'
-            )
-
+            string = (f'<audio src="file/{final_output_file}" controls {autoplay}></audio>')
             if params["show_text"]:
-                string += f"\n\n{original_string}"
+                string += reinsert_images(cleaned_string, img_info)
                 shared.processing_message = "*Is typing...*"
-
             return string
         else:
-            print(
-                f"[{params['branding']}Server] \033[91mWarning\033[0m No audio path in the response."
-            )
+            print(f"[{params['branding']}Server] \033[91mWarning\033[0m No audio path in the response.")
     else:
-        print(
-            f"[{params['branding']}Server] \033[91mWarning\033[0m Audio generation failed. Status:",
-            generate_response.get("message"),
-        )
-
+        print(f"[{params['branding']}Server] \033[91mWarning\033[0m Audio generation failed. Status:", generate_response.get("message"),)
 
 def get_output_filename(state):
     if "character_menu" in state:

system/at_admin/at_settings.html

@@ -89,25 +89,25 @@
     <h3>AllTalk Startup Settings</h3><br>
     <form action="/update-settings" method="post">
 
-        <label for="activate" style="color: #33cc33;">Activate TTS:</label>
+        <label for="activate" style="color: #b273fa;">TG-webui Activate TTS:</label>
         <select id="activate" name="activate" required="">
             <option {% if data.activate %}selected{% endif %} value="true">True</option>
             <option {% if not data.activate %}selected{% endif %} value="false">False</option>
         </select>
 
-        <label for="autoplay" style="color: #33cc33;">&nbsp; &nbsp; Autoplay TTS output:</label>
+        <label for="autoplay" style="color: #b273fa;">&nbsp; &nbsp; TG-webui Autoplay TTS:</label>
         <select id="autoplay" name="autoplay" required="">
             <option {% if data.autoplay %}selected{% endif %} value="true">True</option>
             <option {% if not data.autoplay %}selected{% endif %} value="false">False</option>
         </select>
 
-        <label for="show_text" style="color: #33cc33;"> Show Text on generation:</label>
+        <label for="show_text" style="color: #b273fa;">TG-webui Show Text:</label>
         <select id="show_text" name="show_text" required="">
             <option {% if data.show_text %}selected{% endif %} value="true">True</option>
             <option {% if not data.show_text %}selected{% endif %} value="false">False</option>
         </select>
 
-        <label for="voice" style="color: #33cc33;">&nbsp; &nbsp; Default voice:</label>
+        <label for="voice" style="color: #b273fa;">&nbsp; &nbsp;  TG-webui Default voice:</label>
         <select id="voice" name="voice" required="">
             {% for file in wav_files %}
             <option value="{{ file }}" {% if data.voice==file %}selected{% endif %}>{{ file }}</option>
@@ -115,7 +115,7 @@
         </select>
 
 
-        <label for="language" style="color: #33cc33;">Default Language:</label>
+        <label for="language" style="color: #b273fa;">TG-webui Default Language:</label>
         <select id="language" name="language" required="">
             <option value="Arabic" {% if data.language=='Arabic' %}selected{% endif %}>Arabic</option>
             <option value="Chinese" {% if data.language=='Chinese' %}selected{% endif %}>Chinese</option>
@@ -124,6 +124,7 @@
             <option value="English" {% if data.language=='English' %}selected{% endif %}>English</option>
             <option value="French" {% if data.language=='French' %}selected{% endif %}>French</option>
             <option value="German" {% if data.language=='German' %}selected{% endif %}>German</option>
+            <option value="Hindi" {% if data.language=='Hindi' %}selected{% endif %}>Hindi</option>
             <option value="Hungarian" {% if data.language=='Hungarian' %}selected{% endif %}>Hungarian</option>
             <option value="Italian" {% if data.language=='Italian' %}selected{% endif %}>Italian</option>
             <option value="Japanese" {% if data.language=='Japanese' %}selected{% endif %}>Japanese</option>
@@ -135,20 +136,20 @@
             <option value="Turkish" {% if data.language=='Turkish' %}selected{% endif %}>Turkish</option>
         </select>
 
-        <label for="narrator_voice" style="color: #33cc33;">&nbsp; &nbsp; Narrator voice:</label>
+        <label for="narrator_voice" style="color: #b273fa;">&nbsp; &nbsp; TG-webui Narrator voice:</label>
         <select id="narrator_voice" name="narrator_voice" required="">
             {% for file in wav_files %}
             <option value="{{ file }}" {% if data.narrator_voice==file %}selected{% endif %}>{{ file }}</option>
             {% endfor %}
         </select>
 
-        <label for="remove_trailing_dots" style="color: #33cc33;"> Remove Trailing Dots:</label>
+        <label for="remove_trailing_dots" style="color: #b273fa;">TG-webui Remove Trailing Dots:</label>
         <select id="remove_trailing_dots" name="remove_trailing_dots" required="">
             <option {% if data.remove_trailing_dots %}selected{% endif %} value="true">True</option>
             <option {% if not data.remove_trailing_dots %}selected{% endif %} value="false">False</option>
         </select>
 
-        <label for="narrator_enabled" style="color: #33cc33;">&nbsp; &nbsp; Narrator enabled:</label>
+        <label for="narrator_enabled" style="color: #b273fa;">&nbsp; &nbsp; TG-webui Narrator enabled:</label>
         <select id="narrator_enabled" name="narrator_enabled" required="">
             <option {% if data.narrator_enabled %}selected{% endif %} value="true">True</option>
             <option {% if not data.narrator_enabled %}selected{% endif %} value="false">False</option>

system/config/at_configdowngrade.json

@@ -0,0 +1,2 @@
+{
+}

system/config/at_configupdate.json

@@ -0,0 +1,2 @@
+{
+}

system/config/languages.json

@@ -6,6 +6,7 @@
   "English": "en",
   "French": "fr",
   "German": "de",
+  "Hindi": "hi",
   "Hungarian": "hu",
   "Italian": "it",
   "Japanese": "ja",

system/ft_tokenizer/tokenizer.py

@@ -0,0 +1,869 @@
+import os
+import re
+import textwrap
+from functools import cached_property
+
+import pypinyin
+import torch
+from hangul_romanize import Transliter
+from hangul_romanize.rule import academic
+from num2words import num2words
+from spacy.lang.ar import Arabic
+from spacy.lang.en import English
+from spacy.lang.es import Spanish
+from spacy.lang.ja import Japanese
+from spacy.lang.zh import Chinese
+from tokenizers import Tokenizer
+
+from TTS.tts.layers.xtts.zh_num2words import TextNorm as zh_num2words
+
+
+def get_spacy_lang(lang):
+    if lang == "zh":
+        return Chinese()
+    elif lang == "ja":
+        return Japanese()
+    elif lang == "ar":
+        return Arabic()
+    elif lang == "es":
+        return Spanish()
+    else:
+        # For most languages, Enlish does the job
+        return English()
+
+
+def split_sentence(text, lang, text_split_length=250):
+    """Preprocess the input text"""
+    text_splits = []
+    if text_split_length is not None and len(text) >= text_split_length:
+        text_splits.append("")
+        nlp = get_spacy_lang(lang)
+        nlp.add_pipe("sentencizer")
+        doc = nlp(text)
+        for sentence in doc.sents:
+            if len(text_splits[-1]) + len(str(sentence)) <= text_split_length:
+                # if the last sentence + the current sentence is less than the text_split_length
+                # then add the current sentence to the last sentence
+                text_splits[-1] += " " + str(sentence)
+                text_splits[-1] = text_splits[-1].lstrip()
+            elif len(str(sentence)) > text_split_length:
+                # if the current sentence is greater than the text_split_length
+                for line in textwrap.wrap(
+                    str(sentence),
+                    width=text_split_length,
+                    drop_whitespace=True,
+                    break_on_hyphens=False,
+                    tabsize=1,
+                ):
+                    text_splits.append(str(line))
+            else:
+                text_splits.append(str(sentence))
+
+        if len(text_splits) > 1:
+            if text_splits[0] == "":
+                del text_splits[0]
+    else:
+        text_splits = [text.lstrip()]
+
+    return text_splits
+
+
+_whitespace_re = re.compile(r"\s+")
+
+# List of (regular expression, replacement) pairs for abbreviations:
+_abbreviations = {
+    "en": [
+        (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
+        for x in [
+            ("mrs", "misess"),
+            ("mr", "mister"),
+            ("dr", "doctor"),
+            ("st", "saint"),
+            ("co", "company"),
+            ("jr", "junior"),
+            ("maj", "major"),
+            ("gen", "general"),
+            ("drs", "doctors"),
+            ("rev", "reverend"),
+            ("lt", "lieutenant"),
+            ("hon", "honorable"),
+            ("sgt", "sergeant"),
+            ("capt", "captain"),
+            ("esq", "esquire"),
+            ("ltd", "limited"),
+            ("col", "colonel"),
+            ("ft", "fort"),
+        ]
+    ],
+    "es": [
+        (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
+        for x in [
+            ("sra", "señora"),
+            ("sr", "señor"),
+            ("dr", "doctor"),
+            ("dra", "doctora"),
+            ("st", "santo"),
+            ("co", "compañía"),
+            ("jr", "junior"),
+            ("ltd", "limitada"),
+        ]
+    ],
+    "fr": [
+        (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
+        for x in [
+            ("mme", "madame"),
+            ("mr", "monsieur"),
+            ("dr", "docteur"),
+            ("st", "saint"),
+            ("co", "compagnie"),
+            ("jr", "junior"),
+            ("ltd", "limitée"),
+        ]
+    ],
+    "de": [
+        (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
+        for x in [
+            ("fr", "frau"),
+            ("dr", "doktor"),
+            ("st", "sankt"),
+            ("co", "firma"),
+            ("jr", "junior"),
+        ]
+    ],
+    "pt": [
+        (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
+        for x in [
+            ("sra", "senhora"),
+            ("sr", "senhor"),
+            ("dr", "doutor"),
+            ("dra", "doutora"),
+            ("st", "santo"),
+            ("co", "companhia"),
+            ("jr", "júnior"),
+            ("ltd", "limitada"),
+        ]
+    ],
+    "it": [
+        (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
+        for x in [
+            # ("sig.ra", "signora"),
+            ("sig", "signore"),
+            ("dr", "dottore"),
+            ("st", "santo"),
+            ("co", "compagnia"),
+            ("jr", "junior"),
+            ("ltd", "limitata"),
+        ]
+    ],
+    "pl": [
+        (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
+        for x in [
+            ("p", "pani"),
+            ("m", "pan"),
+            ("dr", "doktor"),
+            ("sw", "święty"),
+            ("jr", "junior"),
+        ]
+    ],
+    "ar": [
+        (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
+        for x in [
+            # There are not many common abbreviations in Arabic as in English.
+        ]
+    ],
+    "zh": [
+        (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
+        for x in [
+            # Chinese doesn't typically use abbreviations in the same way as Latin-based scripts.
+        ]
+    ],
+    "cs": [
+        (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
+        for x in [
+            ("dr", "doktor"),  # doctor
+            ("ing", "inženýr"),  # engineer
+            ("p", "pan"),  # Could also map to pani for woman but no easy way to do it
+            # Other abbreviations would be specialized and not as common.
+        ]
+    ],
+    "ru": [
+        (re.compile("\\b%s\\b" % x[0], re.IGNORECASE), x[1])
+        for x in [
+            ("г-жа", "госпожа"),  # Mrs.
+            ("г-н", "господин"),  # Mr.
+            ("д-р", "доктор"),  # doctor
+            # Other abbreviations are less common or specialized.
+        ]
+    ],
+    "nl": [
+        (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
+        for x in [
+            ("dhr", "de heer"),  # Mr.
+            ("mevr", "mevrouw"),  # Mrs.
+            ("dr", "dokter"),  # doctor
+            ("jhr", "jonkheer"),  # young lord or nobleman
+            # Dutch uses more abbreviations, but these are the most common ones.
+        ]
+    ],
+    "tr": [
+        (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
+        for x in [
+            ("b", "bay"),  # Mr.
+            ("byk", "büyük"),  # büyük
+            ("dr", "doktor"),  # doctor
+            # Add other Turkish abbreviations here if needed.
+        ]
+    ],
+    "hu": [
+        (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
+        for x in [
+            ("dr", "doktor"),  # doctor
+            ("b", "bácsi"),  # Mr.
+            ("nőv", "nővér"),  # nurse
+            # Add other Hungarian abbreviations here if needed.
+        ]
+    ],
+    "ko": [
+        (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
+        for x in [
+            # Korean doesn't typically use abbreviations in the same way as Latin-based scripts.
+        ]
+    ],
+    "ja": [
+        (re.compile("\\b%s\\b" % x[0]), x[1])
+        for x in [
+            ("氏", "さん"),  # Mr.
+            ("夫人", "おんなのひと"),  # Mrs.
+            ("博士", "はかせ"),  # Doctor or PhD
+            ("株", "株式会社"),  # Corporation
+            ("有", "有限会社"),  # Limited company
+            ("大学", "だいがく"),   # University
+            ("先生", "せんせい"),   # Teacher/Professor/Master
+            ("君", "くん")   # Used at the end of boys' names to express familiarity or affection.
+        ]
+    ],
+}
+
+
+def expand_abbreviations_multilingual(text, lang="en"):
+    for regex, replacement in _abbreviations[lang]:
+        text = re.sub(regex, replacement, text)
+    return text
+
+
+_symbols_multilingual = {
+    "en": [
+        (re.compile(r"%s" % re.escape(x[0]), re.IGNORECASE), x[1])
+        for x in [
+            ("&", " and "),
+            ("@", " at "),
+            ("%", " percent "),
+            ("#", " hash "),
+            ("$", " dollar "),
+            ("£", " pound "),
+            ("°", " degree "),
+        ]
+    ],
+    "es": [
+        (re.compile(r"%s" % re.escape(x[0]), re.IGNORECASE), x[1])
+        for x in [
+            ("&", " y "),
+            ("@", " arroba "),
+            ("%", " por ciento "),
+            ("#", " numeral "),
+            ("$", " dolar "),
+            ("£", " libra "),
+            ("°", " grados "),
+        ]
+    ],
+    "fr": [
+        (re.compile(r"%s" % re.escape(x[0]), re.IGNORECASE), x[1])
+        for x in [
+            ("&", " et "),
+            ("@", " arobase "),
+            ("%", " pour cent "),
+            ("#", " dièse "),
+            ("$", " dollar "),
+            ("£", " livre "),
+            ("°", " degrés "),
+        ]
+    ],
+    "de": [
+        (re.compile(r"%s" % re.escape(x[0]), re.IGNORECASE), x[1])
+        for x in [
+            ("&", " und "),
+            ("@", " at "),
+            ("%", " prozent "),
+            ("#", " raute "),
+            ("$", " dollar "),
+            ("£", " pfund "),
+            ("°", " grad "),
+        ]
+    ],
+    "pt": [
+        (re.compile(r"%s" % re.escape(x[0]), re.IGNORECASE), x[1])
+        for x in [
+            ("&", " e "),
+            ("@", " arroba "),
+            ("%", " por cento "),
+            ("#", " cardinal "),
+            ("$", " dólar "),
+            ("£", " libra "),
+            ("°", " graus "),
+        ]
+    ],
+    "it": [
+        (re.compile(r"%s" % re.escape(x[0]), re.IGNORECASE), x[1])
+        for x in [
+            ("&", " e "),
+            ("@", " chiocciola "),
+            ("%", " per cento "),
+            ("#", " cancelletto "),
+            ("$", " dollaro "),
+            ("£", " sterlina "),
+            ("°", " gradi "),
+        ]
+    ],
+    "pl": [
+        (re.compile(r"%s" % re.escape(x[0]), re.IGNORECASE), x[1])
+        for x in [
+            ("&", " i "),
+            ("@", " małpa "),
+            ("%", " procent "),
+            ("#", " krzyżyk "),
+            ("$", " dolar "),
+            ("£", " funt "),
+            ("°", " stopnie "),
+        ]
+    ],
+    "ar": [
+        # Arabic
+        (re.compile(r"%s" % re.escape(x[0]), re.IGNORECASE), x[1])
+        for x in [
+            ("&", " و "),
+            ("@", " على "),
+            ("%", " في المئة "),
+            ("#", " رقم "),
+            ("$", " دولار "),
+            ("£", " جنيه "),
+            ("°", " درجة "),
+        ]
+    ],
+    "zh": [
+        # Chinese
+        (re.compile(r"%s" % re.escape(x[0]), re.IGNORECASE), x[1])
+        for x in [
+            ("&", " 和 "),
+            ("@", " 在 "),
+            ("%", " 百分之 "),
+            ("#", " 号 "),
+            ("$", " 美元 "),
+            ("£", " 英镑 "),
+            ("°", " 度 "),
+        ]
+    ],
+    "cs": [
+        # Czech
+        (re.compile(r"%s" % re.escape(x[0]), re.IGNORECASE), x[1])
+        for x in [
+            ("&", " a "),
+            ("@", " na "),
+            ("%", " procento "),
+            ("#", " křížek "),
+            ("$", " dolar "),
+            ("£", " libra "),
+            ("°", " stupně "),
+        ]
+    ],
+    "ru": [
+        # Russian
+        (re.compile(r"%s" % re.escape(x[0]), re.IGNORECASE), x[1])
+        for x in [
+            ("&", " и "),
+            ("@", " собака "),
+            ("%", " процентов "),
+            ("#", " номер "),
+            ("$", " доллар "),
+            ("£", " фунт "),
+            ("°", " градус "),
+        ]
+    ],
+    "nl": [
+        # Dutch
+        (re.compile(r"%s" % re.escape(x[0]), re.IGNORECASE), x[1])
+        for x in [
+            ("&", " en "),
+            ("@", " bij "),
+            ("%", " procent "),
+            ("#", " hekje "),
+            ("$", " dollar "),
+            ("£", " pond "),
+            ("°", " graden "),
+        ]
+    ],
+    "tr": [
+        (re.compile(r"%s" % re.escape(x[0]), re.IGNORECASE), x[1])
+        for x in [
+            ("&", " ve "),
+            ("@", " at "),
+            ("%", " yüzde "),
+            ("#", " diyez "),
+            ("$", " dolar "),
+            ("£", " sterlin "),
+            ("°", " derece "),
+        ]
+    ],
+    "hu": [
+        (re.compile(r"%s" % re.escape(x[0]), re.IGNORECASE), x[1])
+        for x in [
+            ("&", " és "),
+            ("@", " kukac "),
+            ("%", " százalék "),
+            ("#", " kettőskereszt "),
+            ("$", " dollár "),
+            ("£", " font "),
+            ("°", " fok "),
+        ]
+    ],
+    "ko": [
+        # Korean
+        (re.compile(r"%s" % re.escape(x[0]), re.IGNORECASE), x[1])
+        for x in [
+            ("&", " 그리고 "),
+            ("@", " 에 "),
+            ("%", " 퍼센트 "),
+            ("#", " 번호 "),
+            ("$", " 달러 "),
+            ("£", " 파운드 "),
+            ("°", " 도 "),
+        ]
+    ],
+    "ja": [
+        (re.compile(r"%s" % re.escape(x[0])), x[1])
+        for x in [
+            ("&", " と "),
+            ("@", " アットマーク "),
+            ("%", " パーセント "),
+            ("#", " ナンバー "),
+            ("$", " ドル "),
+            ("£", " ポンド "),
+            ("°", " 度"),
+            ]
+    ],
+}
+
+
+def expand_symbols_multilingual(text, lang="en"):
+    for regex, replacement in _symbols_multilingual[lang]:
+        text = re.sub(regex, replacement, text)
+        text = text.replace("  ", " ")  # Ensure there are no double spaces
+    return text.strip()
+
+
+_ordinal_re = {
+    "en": re.compile(r"([0-9]+)(st|nd|rd|th)"),
+    "es": re.compile(r"([0-9]+)(º|ª|er|o|a|os|as)"),
+    "fr": re.compile(r"([0-9]+)(º|ª|er|re|e|ème)"),
+    "de": re.compile(r"([0-9]+)(st|nd|rd|th|º|ª|\.(?=\s|$))"),
+    "pt": re.compile(r"([0-9]+)(º|ª|o|a|os|as)"),
+    "it": re.compile(r"([0-9]+)(º|°|ª|o|a|i|e)"),
+    "pl": re.compile(r"([0-9]+)(º|ª|st|nd|rd|th)"),
+    "ar": re.compile(r"([0-9]+)(ون|ين|ث|ر|ى)"),
+    "cs": re.compile(r"([0-9]+)\.(?=\s|$)"),  # In Czech, a dot is often used after the number to indicate ordinals.
+    "ru": re.compile(r"([0-9]+)(-й|-я|-е|-ое|-ье|-го)"),
+    "nl": re.compile(r"([0-9]+)(de|ste|e)"),
+    "tr": re.compile(r"([0-9]+)(\.|inci|nci|uncu|üncü|\.)"),
+    "hu": re.compile(r"([0-9]+)(\.|adik|edik|odik|edik|ödik|ödike|ik)"),
+    "ko": re.compile(r"([0-9]+)(번째|번|차|째)"),
+    "ja": re.compile(r"([0-9]+)(番|回|つ|目|等|位)")
+}
+_number_re = re.compile(r"[0-9]+")
+_currency_re = {
+    "USD": re.compile(r"((\$[0-9\.\,]*[0-9]+)|([0-9\.\,]*[0-9]+\$))"),
+    "GBP": re.compile(r"((£[0-9\.\,]*[0-9]+)|([0-9\.\,]*[0-9]+£))"),
+    "EUR": re.compile(r"(([0-9\.\,]*[0-9]+€)|((€[0-9\.\,]*[0-9]+)))"),
+}
+
+_comma_number_re = re.compile(r"\b\d{1,3}(,\d{3})*(\.\d+)?\b")
+_dot_number_re = re.compile(r"\b\d{1,3}(.\d{3})*(\,\d+)?\b")
+_decimal_number_re = re.compile(r"([0-9]+[.,][0-9]+)")
+
+
+def _remove_commas(m):
+    text = m.group(0)
+    if "," in text:
+        text = text.replace(",", "")
+    return text
+
+
+def _remove_dots(m):
+    text = m.group(0)
+    if "." in text:
+        text = text.replace(".", "")
+    return text
+
+
+def _expand_decimal_point(m, lang="en"):
+    amount = m.group(1).replace(",", ".")
+    return num2words(float(amount), lang=lang if lang != "cs" else "cz")
+
+
+def _expand_currency(m, lang="en", currency="USD"):
+    amount = float((re.sub(r"[^\d.]", "", m.group(0).replace(",", "."))))
+    full_amount = num2words(amount, to="currency", currency=currency, lang=lang if lang != "cs" else "cz")
+
+    and_equivalents = {
+        "en": ", ",
+        "es": " con ",
+        "fr": " et ",
+        "de": " und ",
+        "pt": " e ",
+        "it": " e ",
+        "pl": ", ",
+        "cs": ", ",
+        "ru": ", ",
+        "nl": ", ",
+        "ar": ", ",
+        "tr": ", ",
+        "hu": ", ",
+        "ko": ", ",
+    }
+
+    if amount.is_integer():
+        last_and = full_amount.rfind(and_equivalents[lang])
+        if last_and != -1:
+            full_amount = full_amount[:last_and]
+
+    return full_amount
+
+
+def _expand_ordinal(m, lang="en"):
+    return num2words(int(m.group(1)), ordinal=True, lang=lang if lang != "cs" else "cz")
+
+
+def _expand_number(m, lang="en"):
+    return num2words(int(m.group(0)), lang=lang if lang != "cs" else "cz")
+
+
+def expand_numbers_multilingual(text, lang="en"):
+    if lang == "zh":
+        text = zh_num2words()(text)
+    else:
+        if lang in ["en", "ru"]:
+            text = re.sub(_comma_number_re, _remove_commas, text)
+        else:
+            text = re.sub(_dot_number_re, _remove_dots, text)
+        try:
+            text = re.sub(_currency_re["GBP"], lambda m: _expand_currency(m, lang, "GBP"), text)
+            text = re.sub(_currency_re["USD"], lambda m: _expand_currency(m, lang, "USD"), text)
+            text = re.sub(_currency_re["EUR"], lambda m: _expand_currency(m, lang, "EUR"), text)
+        except:
+            pass
+        if lang != "tr":
+            text = re.sub(_decimal_number_re, lambda m: _expand_decimal_point(m, lang), text)
+        text = re.sub(_ordinal_re[lang], lambda m: _expand_ordinal(m, lang), text)
+        text = re.sub(_number_re, lambda m: _expand_number(m, lang), text)
+    return text
+
+
+def lowercase(text):
+    return text.lower()
+
+
+def collapse_whitespace(text):
+    return re.sub(_whitespace_re, " ", text)
+
+
+def multilingual_cleaners(text, lang):
+    text = text.replace('"', "")
+    if lang == "tr":
+        text = text.replace("İ", "i")
+        text = text.replace("Ö", "ö")
+        text = text.replace("Ü", "ü")
+    text = lowercase(text)
+    text = expand_numbers_multilingual(text, lang)
+    text = expand_abbreviations_multilingual(text, lang)
+    text = expand_symbols_multilingual(text, lang=lang)
+    text = collapse_whitespace(text)
+    return text
+
+
+def basic_cleaners(text):
+    """Basic pipeline that lowercases and collapses whitespace without transliteration."""
+    text = lowercase(text)
+    text = collapse_whitespace(text)
+    return text
+
+
+def chinese_transliterate(text):
+    return "".join(
+        [p[0] for p in pypinyin.pinyin(text, style=pypinyin.Style.TONE3, heteronym=False, neutral_tone_with_five=True)]
+    )
+
+
+def japanese_cleaners(text, katsu):
+    text = katsu.romaji(text)
+    text = lowercase(text)
+    return text
+
+
+def korean_transliterate(text):
+    r = Transliter(academic)
+    return r.translit(text)
+
+
+DEFAULT_VOCAB_FILE = os.path.join(os.path.dirname(os.path.realpath(__file__)), "../data/tokenizer.json")
+
+
+class VoiceBpeTokenizer:
+    def __init__(self, vocab_file=None):
+        self.tokenizer = None
+        if vocab_file is not None:
+            self.tokenizer = Tokenizer.from_file(vocab_file)
+        self.char_limits = {
+            "en": 250,
+            "de": 253,
+            "fr": 273,
+            "es": 239,
+            "it": 213,
+            "pt": 203,
+            "pl": 224,
+            "zh": 82,
+            "ar": 166,
+            "cs": 186,
+            "ru": 182,
+            "nl": 251,
+            "tr": 226,
+            "ja": 71,
+            "hu": 224,
+            "ko": 95,
+        }
+
+    @cached_property
+    def katsu(self):
+        import cutlet
+
+        return cutlet.Cutlet()
+
+    def check_input_length(self, txt, lang):
+        lang = lang.split("-")[0]  # remove the region
+        limit = self.char_limits.get(lang, 250)
+        if len(txt) > limit:
+            print(
+                f"[!] Warning: The text length exceeds the character limit of {limit} for language '{lang}', this might cause truncated audio."
+            )
+
+    def preprocess_text(self, txt, lang):
+        if lang in {"ar", "cs", "de", "en", "es", "fr", "hu", "it", "nl", "pl", "pt", "ru", "tr", "zh", "ko"}:
+            txt = multilingual_cleaners(txt, lang)
+            if lang == "zh":
+                txt = chinese_transliterate(txt)
+            if lang == "ko":
+                txt = korean_transliterate(txt)
+        elif lang == "ja":
+            txt = japanese_cleaners(txt, self.katsu)
+        elif lang == "hi":
+            # @manmay will implement this
+            txt = basic_cleaners(txt)
+        else:
+            raise NotImplementedError(f"Language '{lang}' is not supported.")
+        return txt
+
+    def encode(self, txt, lang):
+        lang = lang.split("-")[0]  # remove the region
+        self.check_input_length(txt, lang)
+        txt = self.preprocess_text(txt, lang)
+        lang = "zh-cn" if lang == "zh" else lang
+        txt = f"[{lang}]{txt}"
+        txt = txt.replace(" ", "[SPACE]")
+        return self.tokenizer.encode(txt).ids
+
+    def decode(self, seq):
+        if isinstance(seq, torch.Tensor):
+            seq = seq.cpu().numpy()
+        txt = self.tokenizer.decode(seq, skip_special_tokens=False).replace(" ", "")
+        txt = txt.replace("[SPACE]", " ")
+        txt = txt.replace("[STOP]", "")
+        txt = txt.replace("[UNK]", "")
+        return txt
+
+    def __len__(self):
+        return self.tokenizer.get_vocab_size()
+
+    def get_number_tokens(self):
+        return max(self.tokenizer.get_vocab().values()) + 1
+
+
+def test_expand_numbers_multilingual():
+    test_cases = [
+        # English
+        ("In 12.5 seconds.", "In twelve point five seconds.", "en"),
+        ("There were 50 soldiers.", "There were fifty soldiers.", "en"),
+        ("This is a 1st test", "This is a first test", "en"),
+        ("That will be $20 sir.", "That will be twenty dollars sir.", "en"),
+        ("That will be 20€ sir.", "That will be twenty euro sir.", "en"),
+        ("That will be 20.15€ sir.", "That will be twenty euro, fifteen cents sir.", "en"),
+        ("That's 100,000.5.", "That's one hundred thousand point five.", "en"),
+        # French
+        ("En 12,5 secondes.", "En douze virgule cinq secondes.", "fr"),
+        ("Il y avait 50 soldats.", "Il y avait cinquante soldats.", "fr"),
+        ("Ceci est un 1er test", "Ceci est un premier test", "fr"),
+        ("Cela vous fera $20 monsieur.", "Cela vous fera vingt dollars monsieur.", "fr"),
+        ("Cela vous fera 20€ monsieur.", "Cela vous fera vingt euros monsieur.", "fr"),
+        ("Cela vous fera 20,15€ monsieur.", "Cela vous fera vingt euros et quinze centimes monsieur.", "fr"),
+        ("Ce sera 100.000,5.", "Ce sera cent mille virgule cinq.", "fr"),
+        # German
+        ("In 12,5 Sekunden.", "In zwölf Komma fünf Sekunden.", "de"),
+        ("Es gab 50 Soldaten.", "Es gab fünfzig Soldaten.", "de"),
+        ("Dies ist ein 1. Test", "Dies ist ein erste Test", "de"),  # Issue with gender
+        ("Das macht $20 Herr.", "Das macht zwanzig Dollar Herr.", "de"),
+        ("Das macht 20€ Herr.", "Das macht zwanzig Euro Herr.", "de"),
+        ("Das macht 20,15€ Herr.", "Das macht zwanzig Euro und fünfzehn Cent Herr.", "de"),
+        # Spanish
+        ("En 12,5 segundos.", "En doce punto cinco segundos.", "es"),
+        ("Había 50 soldados.", "Había cincuenta soldados.", "es"),
+        ("Este es un 1er test", "Este es un primero test", "es"),
+        ("Eso le costará $20 señor.", "Eso le costará veinte dólares señor.", "es"),
+        ("Eso le costará 20€ señor.", "Eso le costará veinte euros señor.", "es"),
+        ("Eso le costará 20,15€ señor.", "Eso le costará veinte euros con quince céntimos señor.", "es"),
+        # Italian
+        ("In 12,5 secondi.", "In dodici virgola cinque secondi.", "it"),
+        ("C'erano 50 soldati.", "C'erano cinquanta soldati.", "it"),
+        ("Questo è un 1° test", "Questo è un primo test", "it"),
+        ("Ti costerà $20 signore.", "Ti costerà venti dollari signore.", "it"),
+        ("Ti costerà 20€ signore.", "Ti costerà venti euro signore.", "it"),
+        ("Ti costerà 20,15€ signore.", "Ti costerà venti euro e quindici centesimi signore.", "it"),
+        # Portuguese
+        ("Em 12,5 segundos.", "Em doze vírgula cinco segundos.", "pt"),
+        ("Havia 50 soldados.", "Havia cinquenta soldados.", "pt"),
+        ("Este é um 1º teste", "Este é um primeiro teste", "pt"),
+        ("Isso custará $20 senhor.", "Isso custará vinte dólares senhor.", "pt"),
+        ("Isso custará 20€ senhor.", "Isso custará vinte euros senhor.", "pt"),
+        (
+            "Isso custará 20,15€ senhor.",
+            "Isso custará vinte euros e quinze cêntimos senhor.",
+            "pt",
+        ),  # "cêntimos" should be "centavos" num2words issue
+        # Polish
+        ("W 12,5 sekundy.", "W dwanaście przecinek pięć sekundy.", "pl"),
+        ("Było 50 żołnierzy.", "Było pięćdziesiąt żołnierzy.", "pl"),
+        ("To będzie kosztować 20€ panie.", "To będzie kosztować dwadzieścia euro panie.", "pl"),
+        ("To będzie kosztować 20,15€ panie.", "To będzie kosztować dwadzieścia euro, piętnaście centów panie.", "pl"),
+        # Arabic
+        ("في الـ 12,5 ثانية.", "في الـ اثنا عشر  , خمسون ثانية.", "ar"),
+        ("كان هناك 50 جنديًا.", "كان هناك خمسون جنديًا.", "ar"),
+        # ("ستكون النتيجة $20 يا سيد.", 'ستكون النتيجة عشرون دولار يا سيد.', 'ar'), # $ and € are mising from num2words
+        # ("ستكون النتيجة 20€ يا سيد.", 'ستكون النتيجة عشرون يورو يا سيد.', 'ar'),
+        # Czech
+        ("Za 12,5 vteřiny.", "Za dvanáct celá pět vteřiny.", "cs"),
+        ("Bylo tam 50 vojáků.", "Bylo tam padesát vojáků.", "cs"),
+        ("To bude stát 20€ pane.", "To bude stát dvacet euro pane.", "cs"),
+        ("To bude 20.15€ pane.", "To bude dvacet euro, patnáct centů pane.", "cs"),
+        # Russian
+        ("Через 12.5 секунды.", "Через двенадцать запятая пять секунды.", "ru"),
+        ("Там было 50 солдат.", "Там было пятьдесят солдат.", "ru"),
+        ("Это будет 20.15€ сэр.", "Это будет двадцать евро, пятнадцать центов сэр.", "ru"),
+        ("Это будет стоить 20€ господин.", "Это будет стоить двадцать евро господин.", "ru"),
+        # Dutch
+        ("In 12,5 seconden.", "In twaalf komma vijf seconden.", "nl"),
+        ("Er waren 50 soldaten.", "Er waren vijftig soldaten.", "nl"),
+        ("Dat wordt dan $20 meneer.", "Dat wordt dan twintig dollar meneer.", "nl"),
+        ("Dat wordt dan 20€ meneer.", "Dat wordt dan twintig euro meneer.", "nl"),
+        # Chinese (Simplified)
+        ("在12.5秒内", "在十二点五秒内", "zh"),
+        ("有50名士兵", "有五十名士兵", "zh"),
+        # ("那将是$20先生", '那将是二十美元先生', 'zh'), currency doesn't work
+        # ("那将是20€先生", '那将是二十欧元先生', 'zh'),
+        # Turkish
+        # ("12,5 saniye içinde.", 'On iki virgül beş saniye içinde.', 'tr'), # decimal doesn't work for TR
+        ("50 asker vardı.", "elli asker vardı.", "tr"),
+        ("Bu 1. test", "Bu birinci test", "tr"),
+        # ("Bu 100.000,5.", 'Bu yüz bin virgül beş.', 'tr'),
+        # Hungarian
+        ("12,5 másodperc alatt.", "tizenkettő egész öt tized másodperc alatt.", "hu"),
+        ("50 katona volt.", "ötven katona volt.", "hu"),
+        ("Ez az 1. teszt", "Ez az első teszt", "hu"),
+        # Korean
+        ("12.5 초 안에.", "십이 점 다섯 초 안에.", "ko"),
+        ("50 명의 병사가 있었다.", "오십 명의 병사가 있었다.", "ko"),
+        ("이것은 1 번째 테스트입니다", "이것은 첫 번째 테스트입니다", "ko"),
+    ]
+    for a, b, lang in test_cases:
+        out = expand_numbers_multilingual(a, lang=lang)
+        assert out == b, f"'{out}' vs '{b}'"
+
+
+def test_abbreviations_multilingual():
+    test_cases = [
+        # English
+        ("Hello Mr. Smith.", "Hello mister Smith.", "en"),
+        ("Dr. Jones is here.", "doctor Jones is here.", "en"),
+        # Spanish
+        ("Hola Sr. Garcia.", "Hola señor Garcia.", "es"),
+        ("La Dra. Martinez es muy buena.", "La doctora Martinez es muy buena.", "es"),
+        # French
+        ("Bonjour Mr. Dupond.", "Bonjour monsieur Dupond.", "fr"),
+        ("Mme. Moreau est absente aujourd'hui.", "madame Moreau est absente aujourd'hui.", "fr"),
+        # German
+        ("Frau Dr. Müller ist sehr klug.", "Frau doktor Müller ist sehr klug.", "de"),
+        # Portuguese
+        ("Olá Sr. Silva.", "Olá senhor Silva.", "pt"),
+        ("Dra. Costa, você está disponível?", "doutora Costa, você está disponível?", "pt"),
+        # Italian
+        ("Buongiorno, Sig. Rossi.", "Buongiorno, signore Rossi.", "it"),
+        # ("Sig.ra Bianchi, posso aiutarti?", 'signora Bianchi, posso aiutarti?', 'it'), # Issue with matching that pattern
+        # Polish
+        ("Dzień dobry, P. Kowalski.", "Dzień dobry, pani Kowalski.", "pl"),
+        ("M. Nowak, czy mogę zadać pytanie?", "pan Nowak, czy mogę zadać pytanie?", "pl"),
+        # Czech
+        ("P. Novák", "pan Novák", "cs"),
+        ("Dr. Vojtěch", "doktor Vojtěch", "cs"),
+        # Dutch
+        ("Dhr. Jansen", "de heer Jansen", "nl"),
+        ("Mevr. de Vries", "mevrouw de Vries", "nl"),
+        # Russian
+        ("Здравствуйте Г-н Иванов.", "Здравствуйте господин Иванов.", "ru"),
+        ("Д-р Смирнов здесь, чтобы увидеть вас.", "доктор Смирнов здесь, чтобы увидеть вас.", "ru"),
+        # Turkish
+        ("Merhaba B. Yılmaz.", "Merhaba bay Yılmaz.", "tr"),
+        ("Dr. Ayşe burada.", "doktor Ayşe burada.", "tr"),
+        # Hungarian
+        ("Dr. Szabó itt van.", "doktor Szabó itt van.", "hu"),
+    ]
+
+    for a, b, lang in test_cases:
+        out = expand_abbreviations_multilingual(a, lang=lang)
+        assert out == b, f"'{out}' vs '{b}'"
+
+
+def test_symbols_multilingual():
+    test_cases = [
+        ("I have 14% battery", "I have 14 percent battery", "en"),
+        ("Te veo @ la fiesta", "Te veo arroba la fiesta", "es"),
+        ("J'ai 14° de fièvre", "J'ai 14 degrés de fièvre", "fr"),
+        ("Die Rechnung beträgt £ 20", "Die Rechnung beträgt pfund 20", "de"),
+        ("O meu email é ana&joao@gmail.com", "O meu email é ana e joao arroba gmail.com", "pt"),
+        ("linguaggio di programmazione C#", "linguaggio di programmazione C cancelletto", "it"),
+        ("Moja temperatura to 36.6°", "Moja temperatura to 36.6 stopnie", "pl"),
+        ("Mám 14% baterie", "Mám 14 procento baterie", "cs"),
+        ("Těším se na tebe @ party", "Těším se na tebe na party", "cs"),
+        ("У меня 14% заряда", "У меня 14 процентов заряда", "ru"),
+        ("Я буду @ дома", "Я буду собака дома", "ru"),
+        ("Ik heb 14% batterij", "Ik heb 14 procent batterij", "nl"),
+        ("Ik zie je @ het feest", "Ik zie je bij het feest", "nl"),
+        ("لدي 14% في البطارية", "لدي 14 في المئة في البطارية", "ar"),
+        ("我的电量为 14%", "我的电量为 14 百分之", "zh"),
+        ("Pilim %14 dolu.", "Pilim yüzde 14 dolu.", "tr"),
+        ("Az akkumulátorom töltöttsége 14%", "Az akkumulátorom töltöttsége 14 százalék", "hu"),
+        ("배터리 잔량이 14%입니다.", "배터리 잔량이 14 퍼센트입니다.", "ko"),
+    ]
+
+    for a, b, lang in test_cases:
+        out = expand_symbols_multilingual(a, lang=lang)
+        assert out == b, f"'{out}' vs '{b}'"
+
+
+if __name__ == "__main__":
+    test_expand_numbers_multilingual()
+    test_abbreviations_multilingual()
+    test_symbols_multilingual()

system/requirements/requirements_docker.txt

@@ -0,0 +1,173 @@
+absl-py==2.1.0
+aiofiles==23.2.1
+aiohttp==3.9.3
+aiosignal==1.3.1
+altair==5.2.0
+annotated-types==0.6.0
+anyascii==0.3.2
+anyio==4.3.0
+attrs==23.2.0
+audioread==3.0.1
+av==11.0.0
+Babel==2.14.0
+bangla==0.0.2
+blinker==1.7.0
+blis==0.7.11
+bnnumerizer==0.0.2
+bnunicodenormalizer==0.1.6
+catalogue==2.0.10
+certifi==2024.2.2
+cffi==1.16.0
+charset-normalizer==3.3.2
+click==8.1.7
+cloudpathlib==0.16.0
+colorama==0.4.6
+coloredlogs==15.0.1
+confection==0.1.4
+contourpy==1.2.0
+coqpit==0.0.17
+ctranslate2==4.1.0
+cutlet==0.4.0
+cycler==0.12.1
+cymem==2.0.8
+Cython==3.0.9
+dateparser==1.1.8
+decorator==5.1.1
+docopt==0.6.2
+einops==0.7.0
+encodec==0.1.1
+exceptiongroup
+fastapi==0.110.0
+faster-whisper==1.0.1
+ffmpy==0.3.2
+filelock==3.13.3
+Flask==3.0.2
+flatbuffers==24.3.25
+fonttools==4.50.0
+frozenlist==1.4.1
+fsspec==2024.3.1
+fugashi==1.3.1
+fuzzywuzzy>=0.18.0
+g2pkk==0.1.2
+gradio==3.50.2
+gradio_client==0.6.1
+grpcio==1.62.1
+gruut==2.2.3
+gruut-ipa==0.13.0
+gruut-lang-de==2.0.0
+gruut-lang-en==2.0.0
+gruut-lang-es==2.0.0
+gruut-lang-fr==2.0.2
+h11==0.14.0
+hangul-romanize==0.1.0
+httpcore==1.0.4
+httpx==0.27.0
+huggingface-hub==0.22.1
+humanfriendly==10.0
+idna==3.6
+importlib_metadata==7.1.0
+importlib_resources==6.4.0
+inflect==7.0.0
+itsdangerous==2.1.2
+jaconv==0.3.4
+jamo==0.4.1
+jieba==0.42.1
+Jinja2==3.1.3
+joblib==1.3.2
+jsonlines==1.2.0
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+kiwisolver==1.4.5
+langcodes==3.3.0
+lazy_loader==0.3
+librosa==0.10.1
+llvmlite==0.42.0
+Markdown==3.6
+MarkupSafe==2.1.5
+matplotlib==3.8.3
+mojimoji==0.0.13
+mpmath==1.3.0
+msgpack==1.0.8
+multidict==6.0.5
+murmurhash==1.0.10
+networkx==2.8.8
+nltk==3.8.1
+num2words==0.5.13
+numba==0.59.1
+numpy==1.26.4
+nvidia-cublas-cu11>=11.11.3.6
+nvidia-cudnn-cu11>=9.0.0.312
+onnxruntime==1.17.1
+orjson==3.9.15
+packaging==24.0
+pandas==1.5.3
+pillow==10.2.0
+platformdirs==4.2.0
+pooch==1.8.1
+preshed==3.0.9
+protobuf==5.26.0
+psutil==5.9.8
+pycparser==2.21
+pydantic==2.6.4
+pydantic_core==2.16.3
+pydub==0.25.1
+pynndescent==0.5.11
+pyparsing==3.1.2
+pypinyin==0.51.0
+pyreadline3==3.4.1
+pysbd==0.3.4
+python-crfsuite==0.9.10
+python-dateutil==2.9.0.post0
+python-Levenshtein>=0.25.0
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.34.0
+regex==2023.12.25
+requests==2.31.0
+rpds-py==0.18.0
+safetensors==0.4.2
+scikit-learn==1.4.1.post1
+scipy==1.12.0
+semantic-version==2.10.0
+six==1.16.0
+smart-open==6.4.0
+sniffio==1.3.1
+sounddevice==0.4.6
+soundfile==0.12.1
+soxr==0.3.7
+spacy==3.7.4
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+srsly==2.4.8
+starlette==0.36.3
+SudachiDict-core==20240109
+SudachiPy==0.6.8
+sympy==1.12
+tensorboard==2.16.2
+tensorboard-data-server==0.7.2
+thinc==8.2.3
+threadpoolctl==3.4.0
+tokenizers==0.15.2
+toolz==0.12.1
+torch>=2.2.0
+torchaudio>=2.2.0
+tqdm==4.66.2
+trainer==0.0.36
+transformers==4.39.1
+TTS==0.22.0
+typer==0.9.4
+typing_extensions==4.10.0
+tzdata==2024.1
+tzlocal==5.2
+umap-learn==0.5.5
+Unidecode==1.3.8
+unidic-lite==1.0.8
+urllib3==2.2.1
+uvicorn==0.29.0
+wasabi==1.1.2
+weasel==0.3.4
+websockets==11.0.3
+Werkzeug==3.0.1
+yarl==1.9.4
+zipp==3.18.1

system/requirements/requirements_googlecolab.txt

@@ -0,0 +1,171 @@
+absl-py==2.1.0
+aiofiles==23.2.1
+aiohttp==3.9.3
+aiosignal==1.3.1
+altair==5.2.0
+annotated-types==0.6.0
+anyascii==0.3.2
+anyio==4.3.0
+attrs==23.2.0
+audioread==3.0.1
+av==11.0.0
+Babel==2.14.0
+bangla==0.0.2
+blinker==1.7.0
+blis==0.7.11
+bnnumerizer==0.0.2
+bnunicodenormalizer==0.1.6
+catalogue==2.0.10
+certifi==2024.2.2
+cffi==1.16.0
+charset-normalizer==3.3.2
+click==8.1.7
+cloudpathlib==0.16.0
+colorama==0.4.6
+coloredlogs==15.0.1
+confection==0.1.4
+contourpy==1.2.0
+coqpit==0.0.17
+ctranslate2==4.1.0
+cutlet==0.4.0
+cycler==0.12.1
+cymem==2.0.8
+Cython==3.0.9
+dateparser==1.1.8
+decorator==5.1.1
+docopt==0.6.2
+einops==0.7.0
+encodec==0.1.1
+fastapi==0.110.0
+faster-whisper==1.0.1
+ffmpy==0.3.2
+filelock==3.13.3
+Flask==3.0.2
+flatbuffers==24.3.25
+fonttools==4.50.0
+frozenlist==1.4.1
+fsspec==2024.3.1
+fugashi==1.3.1
+fuzzywuzzy>=0.18.0
+g2pkk==0.1.2
+gradio==3.50.2
+gradio_client==0.6.1
+grpcio==1.62.1
+gruut==2.2.3
+gruut-ipa==0.13.0
+gruut-lang-de==2.0.0
+gruut-lang-en==2.0.0
+gruut-lang-es==2.0.0
+gruut-lang-fr==2.0.2
+h11==0.14.0
+hangul-romanize==0.1.0
+httpcore==1.0.4
+httpx==0.27.0
+huggingface-hub==0.22.1
+humanfriendly==10.0
+idna==3.6
+importlib_metadata==7.1.0
+importlib_resources==6.4.0
+inflect==7.0.0
+itsdangerous==2.1.2
+jaconv==0.3.4
+jamo==0.4.1
+jieba==0.42.1
+Jinja2==3.1.3
+joblib==1.3.2
+jsonlines==1.2.0
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+kiwisolver==1.4.5
+langcodes==3.3.0
+lazy_loader==0.3
+librosa==0.10.1
+llvmlite==0.42.0
+Markdown==3.6
+MarkupSafe==2.1.5
+matplotlib==3.8.3
+mojimoji==0.0.13
+mpmath==1.3.0
+msgpack==1.0.8
+multidict==6.0.5
+murmurhash==1.0.10
+networkx==2.8.8
+nltk==3.8.1
+num2words==0.5.13
+numba==0.59.1
+numpy>=1.17.0,<1.29.0
+nvidia-cublas-cu11>=11.11.3.6
+nvidia-cudnn-cu11>=9.0.0.312
+onnxruntime==1.17.1
+orjson==3.9.15
+packaging==24.0
+pandas==1.5.3
+pillow==10.2.0
+platformdirs==4.2.0
+pooch==1.8.1
+preshed==3.0.9
+protobuf==5.26.0
+psutil==5.9.8
+pycparser==2.21
+pydantic==2.6.4
+pydantic_core==2.16.3
+pydub==0.25.1
+pynndescent==0.5.11
+pyparsing==3.1.2
+pypinyin==0.51.0
+pyreadline3==3.4.1
+pysbd==0.3.4
+python-crfsuite==0.9.10
+python-dateutil==2.9.0.post0
+python-Levenshtein>=0.25.0
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.34.0
+regex==2023.12.25
+requests==2.31.0
+rpds-py==0.18.0
+safetensors==0.4.2
+scikit-learn==1.4.1.post1
+scipy==1.12.0
+semantic-version==2.10.0
+six==1.16.0
+smart-open==6.4.0
+sniffio==1.3.1
+sounddevice==0.4.6
+soundfile==0.12.1
+soxr==0.3.7
+spacy==3.7.4
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+srsly==2.4.8
+starlette==0.36.3
+SudachiDict-core==20240109
+SudachiPy==0.6.8
+sympy==1.12
+tensorboard==2.16.2
+tensorboard-data-server==0.7.2
+thinc==8.2.3
+threadpoolctl==3.4.0
+tokenizers==0.15.2
+toolz==0.12.1
+torch>=2.2.0
+torchaudio>=2.2.0
+tqdm==4.66.2
+trainer==0.0.36
+transformers==4.39.1
+typer==0.9.4
+typing_extensions==4.10.0
+tzdata==2024.1
+tzlocal==5.2
+umap-learn==0.5.5
+Unidecode==1.3.8
+unidic-lite==1.0.8
+urllib3==2.2.1
+uvicorn==0.29.0
+wasabi==1.1.2
+weasel==0.3.4
+websockets==11.0.3
+Werkzeug==3.0.1
+yarl==1.9.4
+zipp==3.18.1

system/requirements/requirements_standalone.txt

@@ -0,0 +1,172 @@
+absl-py==2.1.0
+aiofiles==23.2.1
+aiohttp==3.9.3
+aiosignal==1.3.1
+altair==5.2.0
+annotated-types==0.6.0
+anyascii==0.3.2
+anyio==4.3.0
+attrs==23.2.0
+audioread==3.0.1
+av==11.0.0
+Babel==2.14.0
+bangla==0.0.2
+blinker==1.7.0
+blis==0.7.11
+bnnumerizer==0.0.2
+bnunicodenormalizer==0.1.6
+catalogue==2.0.10
+certifi==2024.2.2
+cffi==1.16.0
+charset-normalizer==3.3.2
+click==8.1.7
+cloudpathlib==0.16.0
+colorama==0.4.6
+coloredlogs==15.0.1
+confection==0.1.4
+contourpy==1.2.0
+coqpit==0.0.17
+ctranslate2==4.1.0
+cutlet==0.4.0
+cycler==0.12.1
+cymem==2.0.8
+Cython==3.0.9
+dateparser==1.1.8
+decorator==5.1.1
+docopt==0.6.2
+einops==0.7.0
+encodec==0.1.1
+fastapi==0.110.0
+faster-whisper==1.0.1
+ffmpy==0.3.2
+filelock==3.13.3
+Flask==3.0.2
+flatbuffers==24.3.25
+fonttools==4.50.0
+frozenlist==1.4.1
+fsspec==2024.3.1
+fugashi==1.3.1
+fuzzywuzzy>=0.18.0
+g2pkk==0.1.2
+gradio==3.50.2
+gradio_client==0.6.1
+grpcio==1.62.1
+gruut==2.2.3
+gruut-ipa==0.13.0
+gruut-lang-de==2.0.0
+gruut-lang-en==2.0.0
+gruut-lang-es==2.0.0
+gruut-lang-fr==2.0.2
+h11==0.14.0
+hangul-romanize==0.1.0
+httpcore==1.0.4
+httpx==0.27.0
+huggingface-hub==0.22.1
+humanfriendly==10.0
+idna==3.6
+importlib_metadata==7.1.0
+importlib_resources==6.4.0
+inflect==7.0.0
+itsdangerous==2.1.2
+jaconv==0.3.4
+jamo==0.4.1
+jieba==0.42.1
+Jinja2==3.1.3
+joblib==1.3.2
+jsonlines==1.2.0
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+kiwisolver==1.4.5
+langcodes==3.3.0
+lazy_loader==0.3
+librosa==0.10.1
+llvmlite==0.42.0
+Markdown==3.6
+MarkupSafe==2.1.5
+matplotlib==3.8.3
+mojimoji==0.0.13
+mpmath==1.3.0
+msgpack==1.0.8
+multidict==6.0.5
+murmurhash==1.0.10
+networkx==2.8.8
+nltk==3.8.1
+num2words==0.5.13
+numba==0.59.1
+numpy==1.26.4
+nvidia-cublas-cu11>=11.11.3.6
+nvidia-cudnn-cu11>=9.0.0.312
+onnxruntime==1.17.1
+orjson==3.9.15
+packaging==24.0
+pandas==1.5.3
+pillow==10.2.0
+platformdirs==4.2.0
+pooch==1.8.1
+preshed==3.0.9
+protobuf==5.26.0
+psutil==5.9.8
+pycparser==2.21
+pydantic==2.6.4
+pydantic_core==2.16.3
+pydub==0.25.1
+pynndescent==0.5.11
+pyparsing==3.1.2
+pypinyin==0.51.0
+pyreadline3==3.4.1
+pysbd==0.3.4
+python-crfsuite==0.9.10
+python-dateutil==2.9.0.post0
+python-Levenshtein>=0.25.0
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.34.0
+regex==2023.12.25
+requests==2.31.0
+rpds-py==0.18.0
+safetensors==0.4.2
+scikit-learn==1.4.1.post1
+scipy==1.12.0
+semantic-version==2.10.0
+six==1.16.0
+smart-open==6.4.0
+sniffio==1.3.1
+sounddevice==0.4.6
+soundfile==0.12.1
+soxr==0.3.7
+spacy==3.7.4
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+srsly==2.4.8
+starlette==0.36.3
+SudachiDict-core==20240109
+SudachiPy==0.6.8
+sympy==1.12
+tensorboard==2.16.2
+tensorboard-data-server==0.7.2
+thinc==8.2.3
+threadpoolctl==3.4.0
+tokenizers==0.15.2
+toolz==0.12.1
+torch>=2.2.0
+torchaudio>=2.2.0
+tqdm==4.66.2
+trainer==0.0.36
+transformers==4.39.1
+TTS==0.22.0
+typer==0.9.4
+typing_extensions==4.10.0
+tzdata==2024.1
+tzlocal==5.2
+umap-learn==0.5.5
+Unidecode==1.3.8
+unidic-lite==1.0.8
+urllib3==2.2.1
+uvicorn==0.29.0
+wasabi==1.1.2
+weasel==0.3.4
+websockets==11.0.3
+Werkzeug==3.0.1
+yarl==1.9.4
+zipp==3.18.1

system/requirements/requirements_textgen.txt

@@ -2,7 +2,7 @@ numpy>=1.22.0
 soundfile>=0.12.1
 uvicorn>=0.24.0.post1
 transformers>=4.37.1
-TTS>=0.21.3
+TTS>=0.22.0
 torch>=2.1.0
 torchaudio>=2.1.0
 fastapi>=0.104.1
@@ -16,3 +16,10 @@ sounddevice>=0.4.6
 python-multipart>=0.0.6
 cutlet>=0.3.0
 unidic-lite>=1.0.8
+faster-whisper>=0.10.0
+pandas>=1.5.0
+nvidia-cublas-cu11>=11.11.3.6
+nvidia-cudnn-cu11>=9.0.0.312
+fuzzywuzzy>=0.18.0
+python-Levenshtein>=0.25.0
+spacy>=3.7.2

system/st_files/alltalk.js

@@ -281,7 +281,7 @@ class AllTalkTtsProvider {
             if (narratorVoiceSelect) narratorVoiceSelect.disabled = !this.settings.narrator_enabled;
         }
         const modelSelect = document.getElementById('switch_model');
-        if (this.settings.finetuned_model === 'true') {
+        if (this.settings.finetuned_model === true) {
             const ftOption = document.createElement('option');
             ftOption.value = 'XTTSv2 FT';
             ftOption.textContent = 'XTTSv2 FT';
@@ -830,4 +830,4 @@ function updateStatus(message) {
                 break;
         }
     }
-}
+}

system/st_files/style.css

@@ -1,159 +1,159 @@
-#tts_media_control {
-    /* order: 100; */
-    /*     width: 40px;
-    height: 40px;
-    margin: 0;
-    padding: 1px; */
-    outline: none;
-    border: none;
-    cursor: pointer;
-    /*     transition: 0.3s;
-    opacity: 0.7; */
-    display: flex;
-    align-items: center;
-    /* justify-content: center; */
-
-}
-
-#ttsExtensionMenuItem {
-    transition: 0.3s;
-    opacity: 0.7;
-}
-
-#ttsExtensionMenuItem:hover {
-    opacity: 1;
-    filter: brightness(1.2);
-}
-
-#tts_media_control:hover {
-    opacity: 1;
-    filter: brightness(1.2);
-}
-
-.voice_preview {
-    margin: 0.25rem 0.5rem;
-    display: flex;
-    justify-content: space-between;
-    align-items: center;
-    gap: 0.5rem;
-}
-
-.voice_preview .voice_name {
-    text-align: left;
-    flex: 1;
-}
-
-.voice_preview .voice_lang {
-    width: 4rem;
-    text-align: left;
-}
-
-.voice_preview .fa-play {
-    cursor: pointer;
-}
-
-.tts-button {
-    margin: 0;
-    outline: none;
-    border: none;
-    cursor: pointer;
-    transition: 0.3s;
-    opacity: 0.7;
-    align-items: center;
-    justify-content: center;
-
-}
-
-.tts-button:hover {
-    opacity: 1;
-}
-
-.tts_block {
-    display: flex;
-    align-items: baseline;
-    column-gap: 5px;
-    flex-wrap: wrap;
-}
-
-.tts_custom_voices {
-    display: flex;
-    align-items: baseline;
-    gap: 5px;
-}
-
-.novel_tts_hints {
-    font-size: calc(0.9 * var(--mainFontSize));
-    display: flex;
-    flex-direction: column;
-    gap: 5px;
-    margin-bottom: 5px;
-}
-
-.at-settings-row {
-    display: flex;
-    justify-content: space-between;
-    align-items: center;
-    width: 100%;
-}
-
-.at-settings-option {
-    flex: 1;
-    margin: 0 10px;
-}
-
-.at-endpoint-option {
-    flex: 1; 
-    margin: 0 10px;
-    margin-right: 25px;
-    width: 38%;
-}
-
-.at-website-row {
-    display: flex;
-    justify-content: start;
-    align-items: center;
-    margin-top: 10px; 
-    margin-bottom: 10px;
-}
-
-.at-website-option {
-    flex: 1; 
-    margin-right: 10px; 
-    margin-left: 10px; 
-}
-
-.at-settings-separator {
-    margin-top: 10px;
-    margin-bottom: 10px;
-    padding: 18x;
-    font-weight: bold;
-    border-top: 1px solid #e1e1e1; /* Grey line */
-    border-bottom: 1px solid #e1e1e1; /* Grey line */
-    text-align: center;
-}
-
-.at-status-message {
-    flex: 1;
-    margin: 0 10px;
-}
-
-.at-model-endpoint-row {
-    display: flex;
-    justify-content: space-between;
-    align-items: center;
-    width: 100%;
-}
-
-.at-model-option, .endpoint-option {
-    flex: 1;
-    margin: 0 10px;
-    margin-left: 10px; 
-}
-
-.at-endpoint-option {
-    width: 38%;
-}
-
-#at-status_info {
-    color: lightgreen; 
+#tts_media_control {
+    /* order: 100; */
+    /*     width: 40px;
+    height: 40px;
+    margin: 0;
+    padding: 1px; */
+    outline: none;
+    border: none;
+    cursor: pointer;
+    /*     transition: 0.3s;
+    opacity: 0.7; */
+    display: flex;
+    align-items: center;
+    /* justify-content: center; */
+
+}
+
+#ttsExtensionMenuItem {
+    transition: 0.3s;
+    opacity: 0.7;
+}
+
+#ttsExtensionMenuItem:hover {
+    opacity: 1;
+    filter: brightness(1.2);
+}
+
+#tts_media_control:hover {
+    opacity: 1;
+    filter: brightness(1.2);
+}
+
+.voice_preview {
+    margin: 0.25rem 0.5rem;
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    gap: 0.5rem;
+}
+
+.voice_preview .voice_name {
+    text-align: left;
+    flex: 1;
+}
+
+.voice_preview .voice_lang {
+    width: 4rem;
+    text-align: left;
+}
+
+.voice_preview .fa-play {
+    cursor: pointer;
+}
+
+.tts-button {
+    margin: 0;
+    outline: none;
+    border: none;
+    cursor: pointer;
+    transition: 0.3s;
+    opacity: 0.7;
+    align-items: center;
+    justify-content: center;
+
+}
+
+.tts-button:hover {
+    opacity: 1;
+}
+
+.tts_block {
+    display: flex;
+    align-items: baseline;
+    column-gap: 5px;
+    flex-wrap: wrap;
+}
+
+.tts_custom_voices {
+    display: flex;
+    align-items: baseline;
+    gap: 5px;
+}
+
+.novel_tts_hints {
+    font-size: calc(0.9 * var(--mainFontSize));
+    display: flex;
+    flex-direction: column;
+    gap: 5px;
+    margin-bottom: 5px;
+}
+
+.at-settings-row {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    width: 100%;
+}
+
+.at-settings-option {
+    flex: 1;
+    margin: 0 10px;
+}
+
+.at-endpoint-option {
+    flex: 1; 
+    margin: 0 10px;
+    margin-right: 25px;
+    width: 38%;
+}
+
+.at-website-row {
+    display: flex;
+    justify-content: start;
+    align-items: center;
+    margin-top: 10px; 
+    margin-bottom: 10px;
+}
+
+.at-website-option {
+    flex: 1; 
+    margin-right: 10px; 
+    margin-left: 10px; 
+}
+
+.at-settings-separator {
+    margin-top: 10px;
+    margin-bottom: 10px;
+    padding: 18x;
+    font-weight: bold;
+    border-top: 1px solid #e1e1e1; /* Grey line */
+    border-bottom: 1px solid #e1e1e1; /* Grey line */
+    text-align: center;
+}
+
+.at-status-message {
+    flex: 1;
+    margin: 0 10px;
+}
+
+.at-model-endpoint-row {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    width: 100%;
+}
+
+.at-model-option, .endpoint-option {
+    flex: 1;
+    margin: 0 10px;
+    margin-left: 10px; 
+}
+
+.at-endpoint-option {
+    width: 38%;
+}
+
+#at-status_info {
+    color: lightgreen; 
 }

system/tts_diff/tts_diff.py

@@ -0,0 +1,269 @@
+import json
+import argparse
+from pathlib import Path
+import os
+import glob
+import platform
+import site
+import subprocess
+import sys
+# version 0.8
+
+def find_files_in_path_with_wildcard(pattern):
+    # Get the site-packages directory of the current Python environment
+    site_packages_path = site.getsitepackages()
+    found_paths = []
+    # Adjust the sub-directory based on the operating system
+    sub_directory = "nvidia/cublas"
+    if platform.system() == "Linux":
+        sub_directory = os.path.join(sub_directory, "lib")
+    else:
+        sub_directory = os.path.join(sub_directory, "bin")
+    
+    # Iterate over each site-packages directory (there can be more than one)
+    for directory in site_packages_path:
+        # Construct the search directory path
+        search_directory = os.path.join(directory, sub_directory)
+        # Use glob to find all files matching the pattern in this directory
+        for file_path in glob.glob(os.path.join(search_directory, pattern)):
+            if os.path.isfile(file_path):  # Ensure it's a file
+                found_paths.append(file_path)
+    return found_paths
+
+def detect_cublas():
+    # Use different file patterns based on the operating system
+    file_name_pattern = 'cublas64_11.*' if platform.system() == "Windows" else 'libcublas.so.11*'
+    found_paths = find_files_in_path_with_wildcard(file_name_pattern)
+    if found_paths:
+        print("[AllTalk TTSDiff] \033[94mCublas:\033[0m \033[92mDetected\033[0m", found_paths)
+    else:
+        print("[AllTalk TTSDiff] \033[94mCublas:\033[0m \033[91mERROR Not Detected\033[0m")
+        print("[AllTalk TTSDiff] \033[94mPlease install Cublas from the Nvidia CUDA Toolkit \033[0mhttps://developer.nvidia.com/cuda-downloads")
+        exit(1)
+        
+
+parser = argparse.ArgumentParser(description="Compare TTS output with the original text using detailed comparison.")
+parser.add_argument("--threshold", type=int, default=98, help="Similarity threshold for considering a match (default: 98)")
+parser.add_argument("--ttslistpath", help="Path to the ttsList.json file")
+parser.add_argument("--wavfilespath", help="Path to the wav outputs folder")
+args = parser.parse_args()
+
+if not args.ttslistpath:
+    parser.error("[AllTalk TTSDiff] Please specify the path to the ttslist.json file using the --ttslistpath argument.")
+if not args.wavfilespath:
+    parser.error("[AllTalk TTSDiff] Please specify the path to the wavs output folder file using the --wavfilespath argument.")
+
+json_file_path = Path(args.ttslistpath).resolve()
+wav_file_path = Path(args.wavfilespath).resolve()
+accuracy_threshold = args.threshold
+
+def disclaimer_text():
+    print(f"\nDESCRIPTION: ")
+    print(f"  This script is designed to assist in identifying bad TTS generation ID's from the TTS Generator.\n")
+    print(f"  This will download the Whisper Large-v2 model (if not already downloaded), and use it to compare your text to")
+    print(f"  to the generated TTS. If it finds an issue, it will flag the ID number that has the issue. This does NOT 100%")
+    print(f"  ensure that all TTS generated is perfect, sounds good etc, but it should flag up glaring issues and help with")
+    print(f"  the process of identifying bad TTS generations.")
+    print(f"\nNOTES ON USE: ")
+    print(f"  - Ensure AllTalk is running in its own command prompt/terminal.")
+    print(f"  - This script should be running in its own command prompt/terminal window in the same Python Environment that")
+    print(f"    AllTalk is running in.")
+    print(f"  - After generating your text in the TTS Generator, you need to `Export List to JSON` and save the file in the")
+    print(f"    same folder/directory this script is running from.")
+    print(f"  - You can use `--threshold` with a numerical value from 1 to 100 to set accuracy detection. For example it may")
+    print(f"    detect/transcribe `their` as `there`, which of course, both words sound the same. If you want 100% accuracy")
+    print(f"    you will set 100 as the threshold. You will more than likely want a number in the high 90's. Default is set")
+    print(f"    at 98, which gives a little flexibility.")
+    print(f"  - The JSON file must be named \033[93mttsList.json\033[0m")
+    print(f"  - When you have your ID list, go back into the TTS Generator, correct any lines and regenerate them. If you")
+    print(f"    want to re-test everthing again after re-generating, you will need to export your list again and re-run this")
+    print(f"    script again, against your newly exported JSON list.")
+    print(f"  - This requires access to \033[93mcublas64_11\033[0m, the same as Finetuning.")
+    print(f"    https://github.com/erew123/alltalk_tts/tree/main?#-important-requirements-cuda-118\n")
+    return
+
+try:
+    from faster_whisper import WhisperModel
+    import re
+    import string
+    import spacy
+    import torch
+    from fuzzywuzzy import fuzz
+except ImportError as e:
+    print(f"[AllTalk TTSDiff] ERROR STARTING SCRIPT:")
+    print("[AllTalk TTSDiff] An error occurred importing one or more required libraries.")
+    print("[AllTalk TTSDiff] Please ensure you have \033[94mactivated your Python environment \033[0mand \033[94minstalled all requirements.\033[0m")
+    print("[AllTalk TTSDiff] \033[94mMissing library:\033[93m", str(e), "\033[0m")
+    exit(1)
+
+# Attempt to load the spaCy model
+try:
+    # Load a medium-sized spaCy model, adjust to "en_core_web_md" or "en_core_web_lg" as needed
+    nlp = spacy.load("en_core_web_md")
+except Exception as e:
+    print(f"[AllTalk TTSDiff] ERROR STARTING SCRIPT:")
+    print("[AllTalk TTSDiff] Failed to load the spaCy language model.")
+    
+    # Attempt to download the spaCy model automatically
+    try:
+        print("[AllTalk TTSDiff] Attempting to automatically download the spaCy language model...")
+        subprocess.run([sys.executable, "-m", "spacy", "download", "en_core_web_md"], check=True)
+        
+        # Try to load the model again after downloading
+        nlp = spacy.load("en_core_web_md")
+        print("[AllTalk TTSDiff] Model downloaded and loaded successfully.")
+    except Exception as download_exception:
+        print("[AllTalk TTSDiff] Automatic download failed.")
+        print("[AllTalk TTSDiff] Please manually install the spaCy language model by running:")
+        print("[AllTalk TTSDiff] \033[93mpython -m spacy download en_core_web_md\033[0m")
+        exit(1)
+
+def texts_are_similar(text1, text2, threshold=0.8):
+    # Preliminary check for short texts
+    if len(text1) < 10 or len(text2) < 10:
+        ratio = fuzz.ratio(text1, text2) / 100.0  # Use FuzzyWuzzy for short texts
+        return ratio > threshold
+
+    # Process the texts through the NLP model for longer texts
+    doc1 = nlp(text1)
+    doc2 = nlp(text2)
+    
+    # Compute semantic similarity
+    similarity = doc1.similarity(doc2)
+    
+    return similarity >= threshold
+
+def normalize_text(text):
+    # Normalize or remove CRLF and other non-standard whitespaces
+    text = text.replace("\r\n", " ").replace("\n", " ").replace("\r", " ")
+    
+    # Convert to lowercase
+    text = text.lower()
+    
+    # Standardize and then remove quotation marks
+    text = text.replace("“", '"').replace("”", '"').replace("‘", "'").replace("’", "'")
+    text = text.translate(str.maketrans('', '', '"\''))
+    
+    # Remove all other punctuation except hyphens to preserve compound words
+    text = text.translate(str.maketrans('', '', string.punctuation.replace("-", "")))
+    
+    # Collapse any sequence of whitespace (including spaces) into a single space
+    text = re.sub(r'\s+', ' ', text)
+    
+    return text.strip()
+
+spoken_punctuation_mapping = {
+    "dot": ".",
+    "comma": ",",
+    # Add more mappings as needed
+}
+
+def contains_spoken_punctuation(transcribed_text):
+    for spoken, punctuation in spoken_punctuation_mapping.items():
+        if spoken in transcribed_text:
+            return True
+    return False
+
+def detailed_comparison(original_text, transcribed_text, threshold=98):
+    original_clean = normalize_text(original_text)
+    transcribed_clean = normalize_text(transcribed_text)
+    ratio = fuzz.ratio(original_clean, transcribed_clean)
+    return ratio > threshold
+
+def access_local_file(url):
+    # Extract the file name from the URL
+    file_name = url.split('/')[-1]
+    # Construct the full path to the file on disk
+    file_path = wav_file_path / file_name
+    # Check if the file exists
+    if not file_path.exists():
+        print(f"[AllTalk TTSDiff] File does not exist: {file_path}")
+        return None
+    return file_path
+
+def transcribe_and_compare(file_url, original_text, model, item_id, flagged_ids):
+    audio_file_path = access_local_file(file_url)
+    if audio_file_path is None:
+        print(f"[AllTalk TTSDiff] Could not access local file for URL: {file_url}")
+        return  # Skip this file if it can't be accessed
+
+    try:
+        segments, info = model.transcribe(str(audio_file_path), beam_size=5)
+        transcribed_text = " ".join([segment.text for segment in segments])
+    except Exception as e:
+        print(f"[AllTalk TTSDiff] Error transcribing file {audio_file_path}: {e}")
+        return  # Skip this file if transcription fails
+    
+    segments, info = model.transcribe(str(audio_file_path), beam_size=5)
+    transcribed_text = " ".join([segment.text for segment in segments])
+    
+    # Normalize texts for comparison
+    original_text_normalized = normalize_text(original_text)
+    transcribed_text_normalized = normalize_text(transcribed_text)
+    
+    # Enhanced comparison using detailed fuzzy matching
+    is_detailed_match = detailed_comparison(original_text_normalized, transcribed_text_normalized, args.threshold)
+    has_spoken_punctuation = contains_spoken_punctuation(transcribed_text_normalized) and not contains_spoken_punctuation(original_text_normalized)
+    
+    # Adjust is_match based on detailed comparison and spoken punctuation check
+    is_match = is_detailed_match and not has_spoken_punctuation
+    
+    # Only log and flag IDs for review if there's a mismatch or detected issues
+    if not is_match:
+        #print(f"\033[93mMismatch Detected - ID:\033[0m {item_id}")
+        print(f"[AllTalk TTSDiff] \033[93mText:\033[0m {original_text}")
+        print(f"[AllTalk TTSDiff] \033[91mTTS :\033[0m{transcribed_text}")
+        if has_spoken_punctuation:
+            print(f"[AllTalk TTSDiff] Note: Potential incorrect spoken punctuation detected.")
+        flagged_ids.append(item_id)  # Track the ID for review
+
+def main():
+    print(f"[AllTalk TTSDiff]")
+    print(f"[AllTalk TTSDiff]")
+    print("[AllTalk TTSDiff] \033[92mStarting Compare of Text vs TTS:\033[0m")
+    print("[AllTalk TTSDiff]")
+    print("[AllTalk TTSDiff] \033[94mJSON file  :\033[92m", json_file_path, "\033[0m")
+    print("[AllTalk TTSDiff] \033[94mWAV files  :\033[92m", wav_file_path, "\033[0m")
+    print("[AllTalk TTSDiff] \033[94mAccuracy   :\033[92m", accuracy_threshold, "%", "\033[0m")
+    detect_cublas()
+    model_size = "large-v2"
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    model = WhisperModel(model_size, device=device, compute_type="float32")
+    
+    flagged_ids = []  # Initialize the list to track IDs needing review
+
+    try:
+        with open(json_file_path, "r", encoding="utf-8") as f:
+            tts_list = json.load(f)
+    except FileNotFoundError:
+        print(f"[AllTalk TTSDiff] ERROR STARTING SCRIPT:")
+        print("[AllTalk TTSDiff] Error: \033[93mttsList.json\033[0m file not found.")
+        print("[AllTalk TTSDiff] Please ensure you follow these steps:")
+        print("[AllTalk TTSDiff] After generating your text in the TTS Generator, you need to `Export List to JSON` and save the file in the")
+        print("[AllTalk TTSDiff] same folder/directory this script is running from.")
+        print("[AllTalk TTSDiff] The JSON file must be named \033[93mttsList.json\033[0m")
+        exit(1)
+
+    print(f"[AllTalk TTSDiff]")
+
+    for item in tts_list:
+        print(f"[AllTalk TTSDiff] Processing ID: {item['id']}")
+        transcribe_and_compare(item['fileUrl'], item['text'], model, item['id'], flagged_ids)
+    
+    print(f"[AllTalk TTSDiff]")
+    # Print summary information at the end
+    if flagged_ids:
+        print(f"[AllTalk TTSDiff] \033[94mIDs needing review:\033[0m", ', '.join(map(str, flagged_ids)))
+        print(f"[AllTalk TTSDiff]")
+        print(f"[AllTalk TTSDiff] Review ID's and correct any lines by editing & regenerating as necessary.")
+    else:
+        print("[AllTalk TTSDiff] \033[94mIDs needing review:\033[0m No issues detected.")
+    summary_data = {
+        "flagged_ids": flagged_ids
+    }
+    with open(wav_file_path / "analysis_summary.json", "w") as summary_file:
+        json.dump(summary_data, summary_file)
+    print("[AllTalk TTSDiff]")
+
+if __name__ == "__main__":
+    main()

system/tts_generator/crunker.d.ts

@@ -1,179 +1,179 @@
-export interface CrunkerConstructorOptions {
-    /**
-     * Sample rate for Crunker's internal audio context.
-     *
-     * @default 44100
-     */
-    sampleRate: number;
-}
-export type CrunkerInputTypes = string | File | Blob;
-/**
- * An exported Crunker audio object.
- */
-export interface ExportedCrunkerAudio {
-    blob: Blob;
-    url: string;
-    element: HTMLAudioElement;
-}
-/**
- * Crunker is the simple way to merge, concatenate, play, export and download audio files using the Web Audio API.
- */
-export default class Crunker {
-    private readonly _sampleRate;
-    private readonly _context;
-    /**
-     * Creates a new instance of Crunker with the provided options.
-     *
-     * If `sampleRate` is not defined, it will auto-select an appropriate sample rate
-     * for the device being used.
-     */
-    constructor({ sampleRate }?: Partial<CrunkerConstructorOptions>);
-    /**
-     * Creates Crunker's internal AudioContext.
-     *
-     * @internal
-     */
-    private _createContext;
-    /**
-     *
-     * The internal AudioContext used by Crunker.
-     */
-    get context(): AudioContext;
-    /**
-     * Asynchronously fetches multiple audio files and returns an array of AudioBuffers.
-     */
-    fetchAudio(...filepaths: CrunkerInputTypes[]): Promise<AudioBuffer[]>;
-    /**
-     * Merges (layers) multiple AudioBuffers into a single AudioBuffer.
-     *
-     * **Visual representation:**
-     *
-     * ![](https://user-images.githubusercontent.com/12958674/88806278-968f0680-d186-11ea-9cb5-8ef2606ffcc7.png)
-     */
-    mergeAudio(buffers: AudioBuffer[]): AudioBuffer;
-    /**
-     * Concatenates multiple AudioBuffers into a single AudioBuffer.
-     *
-     * **Visual representation:**
-     *
-     * ![](https://user-images.githubusercontent.com/12958674/88806297-9d1d7e00-d186-11ea-8cd2-c64cb0324845.png)
-     */
-    concatAudio(buffers: AudioBuffer[]): AudioBuffer;
-    /**
-     * Pads a specified AudioBuffer with silence from a specified start time,
-     * for a specified length of time.
-     *
-     * Accepts float values as well as whole integers.
-     *
-     * @param buffer AudioBuffer to pad
-     * @param padStart Time to start padding (in seconds)
-     * @param seconds Duration to pad for (in seconds)
-     */
-    padAudio(buffer: AudioBuffer, padStart?: number, seconds?: number): AudioBuffer;
-    /**
-     * Slices an AudioBuffer from the specified start time to the end time, with optional fade in and out.
-     *
-     * @param buffer AudioBuffer to slice
-     * @param start Start time (in seconds)
-     * @param end End time (in seconds)
-     * @param fadeIn Fade in duration (in seconds, default is 0)
-     * @param fadeOut Fade out duration (in seconds, default is 0)
-     */
-    sliceAudio(buffer: AudioBuffer, start: number, end: number, fadeIn?: number, fadeOut?: number): AudioBuffer;
-    /**
-     * Plays the provided AudioBuffer in an AudioBufferSourceNode.
-     */
-    play(buffer: AudioBuffer): AudioBufferSourceNode;
-    /**
-     * Exports the specified AudioBuffer to a Blob, Object URI and HTMLAudioElement.
-     *
-     * Note that changing the MIME type does not change the actual file format. The
-     * file format will **always** be a WAVE file due to how audio is stored in the
-     * browser.
-     *
-     * @param buffer Buffer to export
-     * @param type MIME type (default: `audio/wav`)
-     */
-    export(buffer: AudioBuffer, type?: string): ExportedCrunkerAudio;
-    /**
-     * Downloads the provided Blob.
-     *
-     * @param blob Blob to download
-     * @param filename An optional file name to use for the download (default: `crunker`)
-     */
-    download(blob: Blob, filename?: string): HTMLAnchorElement;
-    /**
-     * Executes a callback if the browser does not support the Web Audio API.
-     *
-     * Returns the result of the callback, or `undefined` if the Web Audio API is supported.
-     *
-     * @param callback callback to run if the browser does not support the Web Audio API
-     */
-    notSupported<T>(callback: () => T): T | undefined;
-    /**
-     * Closes Crunker's internal AudioContext.
-     */
-    close(): this;
-    /**
-     * Returns the largest duration of the longest AudioBuffer.
-     *
-     * @internal
-     */
-    private _maxDuration;
-    /**
-     * Returns the largest number of channels in an array of AudioBuffers.
-     *
-     * @internal
-     */
-    private _maxNumberOfChannels;
-    /**
-     * Returns the sum of the lengths of an array of AudioBuffers.
-     *
-     * @internal
-     */
-    private _totalLength;
-    /**
-     * Returns whether the browser supports the Web Audio API.
-     *
-     * @internal
-     */
-    private _isSupported;
-    /**
-     * Writes the WAV headers for the specified Float32Array.
-     *
-     * Returns a DataView containing the WAV headers and file content.
-     *
-     * @internal
-     */
-    private _writeHeaders;
-    /**
-     * Converts a Float32Array to 16-bit PCM.
-     *
-     * @internal
-     */
-    private _floatTo16BitPCM;
-    /**
-     * Writes a string to a DataView at the specified offset.
-     *
-     * @internal
-     */
-    private _writeString;
-    /**
-     * Converts an AudioBuffer to a Float32Array.
-     *
-     * @internal
-     */
-    private _interleave;
-    /**
-     * Creates an HTMLAudioElement whose source is the specified Blob.
-     *
-     * @internal
-     */
-    private _renderAudioElement;
-    /**
-     * Creates an Object URL for the specified Blob.
-     *
-     * @internal
-     */
-    private _renderURL;
-}
+export interface CrunkerConstructorOptions {
+    /**
+     * Sample rate for Crunker's internal audio context.
+     *
+     * @default 44100
+     */
+    sampleRate: number;
+}
+export type CrunkerInputTypes = string | File | Blob;
+/**
+ * An exported Crunker audio object.
+ */
+export interface ExportedCrunkerAudio {
+    blob: Blob;
+    url: string;
+    element: HTMLAudioElement;
+}
+/**
+ * Crunker is the simple way to merge, concatenate, play, export and download audio files using the Web Audio API.
+ */
+export default class Crunker {
+    private readonly _sampleRate;
+    private readonly _context;
+    /**
+     * Creates a new instance of Crunker with the provided options.
+     *
+     * If `sampleRate` is not defined, it will auto-select an appropriate sample rate
+     * for the device being used.
+     */
+    constructor({ sampleRate }?: Partial<CrunkerConstructorOptions>);
+    /**
+     * Creates Crunker's internal AudioContext.
+     *
+     * @internal
+     */
+    private _createContext;
+    /**
+     *
+     * The internal AudioContext used by Crunker.
+     */
+    get context(): AudioContext;
+    /**
+     * Asynchronously fetches multiple audio files and returns an array of AudioBuffers.
+     */
+    fetchAudio(...filepaths: CrunkerInputTypes[]): Promise<AudioBuffer[]>;
+    /**
+     * Merges (layers) multiple AudioBuffers into a single AudioBuffer.
+     *
+     * **Visual representation:**
+     *
+     * ![](https://user-images.githubusercontent.com/12958674/88806278-968f0680-d186-11ea-9cb5-8ef2606ffcc7.png)
+     */
+    mergeAudio(buffers: AudioBuffer[]): AudioBuffer;
+    /**
+     * Concatenates multiple AudioBuffers into a single AudioBuffer.
+     *
+     * **Visual representation:**
+     *
+     * ![](https://user-images.githubusercontent.com/12958674/88806297-9d1d7e00-d186-11ea-8cd2-c64cb0324845.png)
+     */
+    concatAudio(buffers: AudioBuffer[]): AudioBuffer;
+    /**
+     * Pads a specified AudioBuffer with silence from a specified start time,
+     * for a specified length of time.
+     *
+     * Accepts float values as well as whole integers.
+     *
+     * @param buffer AudioBuffer to pad
+     * @param padStart Time to start padding (in seconds)
+     * @param seconds Duration to pad for (in seconds)
+     */
+    padAudio(buffer: AudioBuffer, padStart?: number, seconds?: number): AudioBuffer;
+    /**
+     * Slices an AudioBuffer from the specified start time to the end time, with optional fade in and out.
+     *
+     * @param buffer AudioBuffer to slice
+     * @param start Start time (in seconds)
+     * @param end End time (in seconds)
+     * @param fadeIn Fade in duration (in seconds, default is 0)
+     * @param fadeOut Fade out duration (in seconds, default is 0)
+     */
+    sliceAudio(buffer: AudioBuffer, start: number, end: number, fadeIn?: number, fadeOut?: number): AudioBuffer;
+    /**
+     * Plays the provided AudioBuffer in an AudioBufferSourceNode.
+     */
+    play(buffer: AudioBuffer): AudioBufferSourceNode;
+    /**
+     * Exports the specified AudioBuffer to a Blob, Object URI and HTMLAudioElement.
+     *
+     * Note that changing the MIME type does not change the actual file format. The
+     * file format will **always** be a WAVE file due to how audio is stored in the
+     * browser.
+     *
+     * @param buffer Buffer to export
+     * @param type MIME type (default: `audio/wav`)
+     */
+    export(buffer: AudioBuffer, type?: string): ExportedCrunkerAudio;
+    /**
+     * Downloads the provided Blob.
+     *
+     * @param blob Blob to download
+     * @param filename An optional file name to use for the download (default: `crunker`)
+     */
+    download(blob: Blob, filename?: string): HTMLAnchorElement;
+    /**
+     * Executes a callback if the browser does not support the Web Audio API.
+     *
+     * Returns the result of the callback, or `undefined` if the Web Audio API is supported.
+     *
+     * @param callback callback to run if the browser does not support the Web Audio API
+     */
+    notSupported<T>(callback: () => T): T | undefined;
+    /**
+     * Closes Crunker's internal AudioContext.
+     */
+    close(): this;
+    /**
+     * Returns the largest duration of the longest AudioBuffer.
+     *
+     * @internal
+     */
+    private _maxDuration;
+    /**
+     * Returns the largest number of channels in an array of AudioBuffers.
+     *
+     * @internal
+     */
+    private _maxNumberOfChannels;
+    /**
+     * Returns the sum of the lengths of an array of AudioBuffers.
+     *
+     * @internal
+     */
+    private _totalLength;
+    /**
+     * Returns whether the browser supports the Web Audio API.
+     *
+     * @internal
+     */
+    private _isSupported;
+    /**
+     * Writes the WAV headers for the specified Float32Array.
+     *
+     * Returns a DataView containing the WAV headers and file content.
+     *
+     * @internal
+     */
+    private _writeHeaders;
+    /**
+     * Converts a Float32Array to 16-bit PCM.
+     *
+     * @internal
+     */
+    private _floatTo16BitPCM;
+    /**
+     * Writes a string to a DataView at the specified offset.
+     *
+     * @internal
+     */
+    private _writeString;
+    /**
+     * Converts an AudioBuffer to a Float32Array.
+     *
+     * @internal
+     */
+    private _interleave;
+    /**
+     * Creates an HTMLAudioElement whose source is the specified Blob.
+     *
+     * @internal
+     */
+    private _renderAudioElement;
+    /**
+     * Creates an Object URL for the specified Blob.
+     *
+     * @internal
+     */
+    private _renderURL;
+}

system/tts_generator/crunker.esm.js

@@ -1,2 +1,2 @@
-var e={d:(t,n)=>{for(var r in n)e.o(n,r)&&!e.o(t,r)&&Object.defineProperty(t,r,{enumerable:!0,get:n[r]})},o:(e,t)=>Object.prototype.hasOwnProperty.call(e,t)},t={};function n(e){return n="function"==typeof Symbol&&"symbol"==typeof Symbol.iterator?function(e){return typeof e}:function(e){return e&&"function"==typeof Symbol&&e.constructor===Symbol&&e!==Symbol.prototype?"symbol":typeof e},n(e)}function r(e){return function(e){if(Array.isArray(e))return a(e)}(e)||function(e){if("undefined"!=typeof Symbol&&null!=e[Symbol.iterator]||null!=e["@@iterator"])return Array.from(e)}(e)||function(e,t){if(!e)return;if("string"==typeof e)return a(e,t);var n=Object.prototype.toString.call(e).slice(8,-1);"Object"===n&&e.constructor&&(n=e.constructor.name);if("Map"===n||"Set"===n)return Array.from(e);if("Arguments"===n||/^(?:Ui|I)nt(?:8|16|32)(?:Clamped)?Array$/.test(n))return a(e,t)}(e)||function(){throw new TypeError("Invalid attempt to spread non-iterable instance.\nIn order to be iterable, non-array objects must have a [Symbol.iterator]() method.")}()}function a(e,t){(null==t||t>e.length)&&(t=e.length);for(var n=0,r=new Array(t);n<t;n++)r[n]=e[n];return r}function o(e,t){if(!(e instanceof t))throw new TypeError("Cannot call a class as a function")}function i(e,t){for(var r=0;r<t.length;r++){var a=t[r];a.enumerable=a.enumerable||!1,a.configurable=!0,"value"in a&&(a.writable=!0),Object.defineProperty(e,(o=a.key,i=void 0,i=function(e,t){if("object"!==n(e)||null===e)return e;var r=e[Symbol.toPrimitive];if(void 0!==r){var a=r.call(e,t||"default");if("object"!==n(a))return a;throw new TypeError("@@toPrimitive must return a primitive value.")}return("string"===t?String:Number)(e)}(o,"string"),"symbol"===n(i)?i:String(i)),a)}var o,i}e.d(t,{Z:()=>u});var u=function(){function e(){var t=arguments.length>0&&void 0!==arguments[0]?arguments[0]:{},n=t.sampleRate;o(this,e),this._context=this._createContext(n),n||(n=this._context.sampleRate),this._sampleRate=n}var t,n,a;return t=e,n=[{key:"_createContext",value:function(){var e=arguments.length>0&&void 0!==arguments[0]?arguments[0]:44100;return window.AudioContext=window.AudioContext||window.webkitAudioContext||window.mozAudioContext,new AudioContext({sampleRate:e})}},{key:"context",get:function(){return this._context}},{key:"fetchAudio",value:async function(){for(var e=this,t=arguments.length,n=new Array(t),r=0;r<t;r++)n[r]=arguments[r];return await Promise.all(n.map((async function(t){var n;return n=t instanceof File||t instanceof Blob?await t.arrayBuffer():await fetch(t).then((function(e){return e.headers.has("Content-Type")&&!e.headers.get("Content-Type").includes("audio/")&&console.warn("Crunker: Attempted to fetch an audio file, but its MIME type is `".concat(e.headers.get("Content-Type").split(";")[0],"`. We'll try and continue anyway. (file: \"").concat(t,'")')),e.arrayBuffer()})),await e._context.decodeAudioData(n)})))}},{key:"mergeAudio",value:function(e){var t=this._context.createBuffer(this._maxNumberOfChannels(e),this._sampleRate*this._maxDuration(e),this._sampleRate);return e.forEach((function(e){for(var n=0;n<e.numberOfChannels;n++){for(var r=t.getChannelData(n),a=e.getChannelData(n),o=e.getChannelData(n).length-1;o>=0;o--)r[o]+=a[o];t.getChannelData(n).set(r)}})),t}},{key:"concatAudio",value:function(e){var t=this._context.createBuffer(this._maxNumberOfChannels(e),this._totalLength(e),this._sampleRate),n=0;return e.forEach((function(e){for(var r=0;r<e.numberOfChannels;r++)t.getChannelData(r).set(e.getChannelData(r),n);n+=e.length})),t}},{key:"padAudio",value:function(e){var t=arguments.length>1&&void 0!==arguments[1]?arguments[1]:0,n=arguments.length>2&&void 0!==arguments[2]?arguments[2]:0;if(0===n)return e;if(t<0)throw new Error('Crunker: Parameter "padStart" in padAudio must be positive');if(n<0)throw new Error('Crunker: Parameter "seconds" in padAudio must be positive');for(var r=this._context.createBuffer(e.numberOfChannels,Math.ceil(e.length+n*e.sampleRate),e.sampleRate),a=0;a<e.numberOfChannels;a++){var o=e.getChannelData(a);r.getChannelData(a).set(o.subarray(0,Math.ceil(t*e.sampleRate)+1),0),r.getChannelData(a).set(o.subarray(Math.ceil(t*e.sampleRate)+2,r.length+1),Math.ceil((t+n)*e.sampleRate))}return r}},{key:"sliceAudio",value:function(e,t,n){var r=arguments.length>3&&void 0!==arguments[3]?arguments[3]:0,a=arguments.length>4&&void 0!==arguments[4]?arguments[4]:0;if(t>=n)throw new Error('Crunker: "start" time should be less than "end" time in sliceAudio method');for(var o=Math.round((n-t)*this._sampleRate),i=Math.round(t*this._sampleRate),u=this._context.createBuffer(e.numberOfChannels,o,this._sampleRate),l=0;l<e.numberOfChannels;l++)for(var s=e.getChannelData(l),c=u.getChannelData(l),f=0;f<o;f++)c[f]=s[i+f],f<r*this._sampleRate&&(c[f]*=f/(r*this._sampleRate)),f>o-a*this._sampleRate&&(c[f]*=(o-f)/(a*this._sampleRate));return u}},{key:"play",value:function(e){var t=this._context.createBufferSource();return t.buffer=e,t.connect(this._context.destination),t.start(),Line truncated
+var e={d:(t,n)=>{for(var r in n)e.o(n,r)&&!e.o(t,r)&&Object.defineProperty(t,r,{enumerable:!0,get:n[r]})},o:(e,t)=>Object.prototype.hasOwnProperty.call(e,t)},t={};function n(e){return n="function"==typeof Symbol&&"symbol"==typeof Symbol.iterator?function(e){return typeof e}:function(e){return e&&"function"==typeof Symbol&&e.constructor===Symbol&&e!==Symbol.prototype?"symbol":typeof e},n(e)}function r(e){return function(e){if(Array.isArray(e))return a(e)}(e)||function(e){if("undefined"!=typeof Symbol&&null!=e[Symbol.iterator]||null!=e["@@iterator"])return Array.from(e)}(e)||function(e,t){if(!e)return;if("string"==typeof e)return a(e,t);var n=Object.prototype.toString.call(e).slice(8,-1);"Object"===n&&e.constructor&&(n=e.constructor.name);if("Map"===n||"Set"===n)return Array.from(e);if("Arguments"===n||/^(?:Ui|I)nt(?:8|16|32)(?:Clamped)?Array$/.test(n))return a(e,t)}(e)||function(){throw new TypeError("Invalid attempt to spread non-iterable instance.\nIn order to be iterable, non-array objects must have a [Symbol.iterator]() method.")}()}function a(e,t){(null==t||t>e.length)&&(t=e.length);for(var n=0,r=new Array(t);n<t;n++)r[n]=e[n];return r}function o(e,t){if(!(e instanceof t))throw new TypeError("Cannot call a class as a function")}function i(e,t){for(var r=0;r<t.length;r++){var a=t[r];a.enumerable=a.enumerable||!1,a.configurable=!0,"value"in a&&(a.writable=!0),Object.defineProperty(e,(o=a.key,i=void 0,i=function(e,t){if("object"!==n(e)||null===e)return e;var r=e[Symbol.toPrimitive];if(void 0!==r){var a=r.call(e,t||"default");if("object"!==n(a))return a;throw new TypeError("@@toPrimitive must return a primitive value.")}return("string"===t?String:Number)(e)}(o,"string"),"symbol"===n(i)?i:String(i)),a)}var o,i}e.d(t,{Z:()=>u});var u=function(){function e(){var t=arguments.length>0&&void 0!==arguments[0]?arguments[0]:{},n=t.sampleRate;o(this,e),this._context=this._createContext(n),n||(n=this._context.sampleRate),this._sampleRate=n}var t,n,a;return t=e,n=[{key:"_createContext",value:function(){var e=arguments.length>0&&void 0!==arguments[0]?arguments[0]:44100;return window.AudioContext=window.AudioContext||window.webkitAudioContext||window.mozAudioContext,new AudioContext({sampleRate:e})}},{key:"context",get:function(){return this._context}},{key:"fetchAudio",value:async function(){for(var e=this,t=arguments.length,n=new Array(t),r=0;r<t;r++)n[r]=arguments[r];return await Promise.all(n.map((async function(t){var n;return n=t instanceof File||t instanceof Blob?await t.arrayBuffer():await fetch(t).then((function(e){return e.headers.has("Content-Type")&&!e.headers.get("Content-Type").includes("audio/")&&console.warn("Crunker: Attempted to fetch an audio file, but its MIME type is `".concat(e.headers.get("Content-Type").split(";")[0],"`. We'll try and continue anyway. (file: \"").concat(t,'")')),e.arrayBuffer()})),await e._context.decodeAudioData(n)})))}},{key:"mergeAudio",value:function(e){var t=this._context.createBuffer(this._maxNumberOfChannels(e),this._sampleRate*this._maxDuration(e),this._sampleRate);return e.forEach((function(e){for(var n=0;n<e.numberOfChannels;n++){for(var r=t.getChannelData(n),a=e.getChannelData(n),o=e.getChannelData(n).length-1;o>=0;o--)r[o]+=a[o];t.getChannelData(n).set(r)}})),t}},{key:"concatAudio",value:function(e){var t=this._context.createBuffer(this._maxNumberOfChannels(e),this._totalLength(e),this._sampleRate),n=0;return e.forEach((function(e){for(var r=0;r<e.numberOfChannels;r++)t.getChannelData(r).set(e.getChannelData(r),n);n+=e.length})),t}},{key:"padAudio",value:function(e){var t=arguments.length>1&&void 0!==arguments[1]?arguments[1]:0,n=arguments.length>2&&void 0!==arguments[2]?arguments[2]:0;if(0===n)return e;if(t<0)throw new Error('Crunker: Parameter "padStart" in padAudio must be positive');if(n<0)throw new Error('Crunker: Parameter "seconds" in padAudio must be positive');for(var r=this._context.createBuffer(e.numberOfChannels,Math.ceil(e.length+n*e.sampleRate),e.sampleRate),a=0;a<e.numberOfChannels;a++){var o=e.getChannelData(a);r.getChannelData(a).set(o.subarray(0,Math.ceil(t*e.sampleRate)+1),0),r.getChannelData(a).set(o.subarray(Math.ceil(t*e.sampleRate)+2,r.length+1),Math.ceil((t+n)*e.sampleRate))}return r}},{key:"sliceAudio",value:function(e,t,n){var r=arguments.length>3&&void 0!==arguments[3]?arguments[3]:0,a=arguments.length>4&&void 0!==arguments[4]?arguments[4]:0;if(t>=n)throw new Error('Crunker: "start" time should be less than "end" time in sliceAudio method');for(var o=Math.round((n-t)*this._sampleRate),i=Math.round(t*this._sampleRate),u=this._context.createBuffer(e.numberOfChannels,o,this._sampleRate),l=0;l<e.numberOfChannels;l++)for(var s=e.getChannelData(l),c=u.getChannelData(l),f=0;f<o;f++)c[f]=s[i+f],f<r*this._sampleRate&&(c[f]*=f/(r*this._sampleRate)),f>o-a*this._sampleRate&&(c[f]*=(o-f)/(a*this._sampleRate));return u}},{key:"play",value:function(e){var t=this._context.createBufferSource();return t.buffer=e,t.connect(this._context.destination),t.start(),Line truncated
 //# sourceMappingURL=crunker.esm.js.map

system/tts_generator/crunker.esm.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"crunker.esm.js","mappings":"AACA,IAAIA,EAAsB,CCA1BA,EAAwB,CAACC,EAASC,KACjC,IAAI,IAAIC,KAAOD,EACXF,EAAoBI,EAAEF,EAAYC,KAASH,EAAoBI,EAAEH,EAASE,IAC5EE,OAAOC,eAAeL,EAASE,EAAK,CAAEI,YAAY,EAAMC,IAAKN,EAAWC,IAE1E,ECNDH,EAAwB,CAACS,EAAKC,IAAUL,OAAOM,UAAUC,eAAeC,KAAKJ,EAAKC,I,8jDCoBlF,IAGqBI,EAAO,WAU1B,aAAqE,6DAAJ,CAAC,EAApDC,EAAU,EAAVA,WAAU,UACtBC,KAAKC,SAAWD,KAAKE,eAAeH,GAEpCA,IAAAA,EAAeC,KAAKC,SAASF,YAE7BC,KAAKG,YAAcJ,CACrB,C,UAoZC,O,EAlZD,E,EAAA,6BAKA,WAAkE,IAA3CA,EAAqB,UAAH,6CAAG,MAE1C,OADAK,OAAOC,aAAeD,OAAOC,cAAiBD,OAAeE,oBAAuBF,OAAeG,gBAC5F,IAAIF,aAAa,CAAEN,WAAAA,GAC5B,GAEA,mBAIA,WACE,OAAOC,KAAKC,QACd,GAEA,wBAGAO,iBAA4E,kCAAxDC,EAAS,yBAATA,EAAS,gBAC3B,aAAaC,QAAQC,IACnBF,EAAUG,KAAIJ,eAAOK,GACnB,IAAIC,EAkBJ,OAfEA,EADED,aAAoBE,MAAQF,aAAoBG,WACnCH,EAASI,oBAETC,MAAML,GAAUM,MAAK,SAACC,GASnC,OARIA,EAASC,QAAQC,IAAI,kBAAoBF,EAASC,QAAQ7B,IAAI,gBAAiB+B,SAAS,WAC1FC,QAAQC,KAAK,oEAAD,OAERL,EAASC,QAAQ7B,IAAI,gBAAiBkC,MAAM,KAAK,GAAE,sDACPb,EAAQ,OAInDO,EAASH,aAClB,UAGW,EAAKhB,SAAS0B,gBAAgBb,EAC7C,IAEJ,GAEA,wBAOA,SAAWc,GACT,IAAMC,EAAS7B,KAAKC,SAAS6B,aAC3B9B,KAAK+B,qBAAqBH,GAC1B5B,KAAKG,YAAcH,KAAKgC,aAAaJ,GACrC5B,KAAKG,aAgBP,OAbAyB,EAAQK,SAAQ,SAACnB,GACf,IAAK,IAAIoB,EAAgB,EAAGA,EAAgBpB,EAAOqB,iBAAkBD,IAAiB,CAIpF,IAHA,IAAME,EAAaP,EAAOQ,eAAeH,GACnCI,EAAaxB,EAAOuB,eAAeH,GAEhCK,EAAIzB,EAAOuB,eAAeH,GAAeM,OAAS,EAAGD,GAAK,EAAGA,IACpEH,EAAWG,IAAMD,EAAWC,GAG9BV,EAAOQ,eAAeH,GAAeO,IAAIL,EAC3C,CACF,IAEOP,CACT,GAEA,yBAOA,SAAYD,GACV,IAAMC,EAAS7B,KAAKC,SAAS6B,aAC3B9B,KAAK+B,qBAAqBH,GAC1B5B,KAAK0C,aAAad,GAClB5B,KAAKG,aAEHwC,EAAS,EAUb,OARAf,EAAQK,SAAQ,SAACnB,GACf,IAAK,IAAIoB,EAAgB,EAAGA,EAAgBpB,EAAOqB,iBAAkBD,IACnEL,EAAOQ,eAAeH,GAAeO,IAAI3B,EAAOuB,eAAeH,GAAgBS,GAGjFA,GAAU7B,EAAO0B,MACnB,IAEOX,CACT,GAEA,sBAUA,SAASf,GAA6E,IAAxD8B,EAAmB,UAAH,6CAAG,EAAGC,EAAkB,UAAH,6CAAG,EACpE,GAAgB,IAAZA,EAAe,OAAO/B,EAE1B,GAAI8B,EAAW,EAAG,MAAM,IAAIE,MAAM,8DAClC,GAAID,EAAU,EAAG,MAAM,IAAIC,MAAM,6DAQjC,IANA,IAAMC,EAAgB/C,KAAKC,SAAS6B,aAClChB,EAAOqB,iBACPa,KAAKC,KAAKnC,EAAO0B,OAASK,EAAU/B,EAAOf,YAC3Ce,EAAOf,YAGAmC,EAAgB,EAAGA,EAAgBpB,EAAOqB,iBAAkBD,IAAiB,CACpF,IAAMgB,EAAcpC,EAAOuB,eAAeH,GAC1Ca,EACGV,eAAeH,GACfO,IAAIS,EAAYC,SAAS,EAAGH,KAAKC,KAAKL,EAAW9B,EAAOf,YAAc,GAAI,GAE7EgD,EACGV,eAAeH,GACfO,IACCS,EAAYC,SAASH,KAAKC,KAAKL,EAAW9B,EAAOf,YAAc,EAAGgD,EAAcP,OAAS,GACzFQ,KAAKC,MAAML,EAAWC,GAAW/B,EAAOf,YAE9C,CAEA,OAAOgD,CACT,GAEA,wBASA,SAAWjC,EAAqBsC,EAAeC,GAAmE,IAAtDC,EAAiB,UAAH,6CAAG,EAAGC,EAAkB,UAAH,6CAAG,EAChG,GAAIH,GAASC,EAAK,MAAM,IAAIP,MAAM,6EAMlC,IAJA,IAAMN,EAASQ,KAAKQ,OAAOH,EAAMD,GAASpD,KAAKG,aACzCwC,EAASK,KAAKQ,MAAMJ,EAAQpD,KAAKG,aACjCsD,EAAYzD,KAAKC,SAAS6B,aAAahB,EAAOqB,iBAAkBK,EAAQxC,KAAKG,aAE1EuD,EAAU,EAAGA,EAAU5C,EAAOqB,iBAAkBuB,IAIvD,IAHA,IAAMC,EAAY7C,EAAOuB,eAAeqB,GAClCtB,EAAaqB,EAAUpB,eAAeqB,GAEnCnB,EAAI,EAAGA,EAAIC,EAAQD,IAC1BH,EAAWG,GAAKoB,EAAUhB,EAASJ,GAG/BA,EAAIe,EAAStD,KAAKG,cACpBiC,EAAWG,IAAMA,GAAKe,EAAStD,KAAKG,cAIlCoC,EAAIC,EAASe,EAAUvD,KAAKG,cAC9BiC,EAAWG,KAAOC,EAASD,IAAMgB,EAAUvD,KAAKG,cAKtD,OAAOsD,CACT,GAEA,kBAGA,SAAK3C,GACH,IAAM8C,EAAS5D,KAAKC,SAAS4D,qBAM7B,OAJAD,EAAO9C,OAASA,EAChB8C,EAAOE,QAAQ9D,KAAKC,SAAS8D,aAC7BH,EAAOR,QAEAQ,CACT,GAEA,oBAUA,SAAO9C,GAAuE,IAAlDkD,EAAe,UAAH,6CAAG,YACnCC,EAAWjE,KAAKkE,YAAYpD,GAC5BqD,EAAWnE,KAAKoE,cAAcH,EAAUnD,EAAOqB,iBAAkBrB,EAAOf,YACxEsE,EAAY,IAAIrD,KAAK,CAACmD,GAAW,CAAEH,KAAAA,IAEzC,MAAO,CACLM,KAAMD,EACNE,IAAKvE,KAAKwE,WAAWH,GACrBI,QAASzE,KAAK0E,oBAAoBL,GAEtC,GAEA,sBAMA,SAASC,GAA6D,IAAjDK,EAAmB,UAAH,6CAAG,UAChCC,EAAIC,SAASC,cAAc,KAOjC,OALAF,EAAEG,MAAMC,QAAU,OAClBJ,EAAEK,KAAOjF,KAAKwE,WAAWF,GACzBM,EAAEM,SAAW,GAAH,OAAMP,EAAQ,YAAIL,EAAKN,KAAKtC,MAAM,KAAK,IACjDkD,EAAEO,QAEKP,CACT,GAEA,0BAOA,SAAgBQ,GACd,OAAOpF,KAAKqF,oBAAiBC,EAAYF,GAC3C,GAEA,mBAGA,WAEE,OADApF,KAAKC,SAASsF,QACPvF,IACT,GAEA,0BAKA,SAAqB4B,GACnB,OAAOoB,KAAKwC,IAAG,MAARxC,KAAI,EAAQpB,EAAQhB,KAAI,SAACE,GAAM,OAAKA,EAAO2E,QAAQ,KAC5D,GAEA,kCAKA,SAA6B7D,GAC3B,OAAOoB,KAAKwC,IAAG,MAARxC,KAAI,EAAQpB,EAAQhB,KAAI,SAACE,GAAM,OAAKA,EAAOqB,gBAAgB,KACpE,GAEA,0BAKA,SAAqBP,GACnB,OAAOA,EAAQhB,KAAI,SAACE,GAAM,OAAKA,EAAO0B,MAAM,IAAEkD,QAAO,SAACd,EAAGe,GAAC,OAAKf,EAAIe,CAAC,GAAE,EACxE,GAEA,0BAKA,WACE,MAAO,iBAAkBvF,QAAU,uBAAwBA,QAAU,oBAAqBA,MAC5F,GAEA,2BAOA,SAAsBU,EAAsB8E,EAAuB7F,GACjE,IAEM8F,EADiBC,EACJF,EAIbG,EALiBD,EAKDhF,EAAO0B,OACvBwD,EAFkB,GAEiBD,EAEnC9E,EAAc,IAAIgF,YALD,EAK8BD,GAC/CE,EAAO,IAAIC,SAASlF,GAgB1B,OAdAjB,KAAKoG,aAAaF,EAAM,EAAG,QAC3BA,EAAKG,UAAU,EAAGL,GAAgB,GAClChG,KAAKoG,aAAaF,EAAM,EAAG,QAC3BlG,KAAKoG,aAAaF,EAAM,GAAI,QAC5BA,EAAKG,UAAU,GAAI,IAAI,GACvBH,EAAKI,UAAU,GAAI,GAAG,GACtBJ,EAAKI,UAAU,GAAIV,GAAe,GAClCM,EAAKG,UAAU,GAAItG,GAAY,GAC/BmG,EAAKG,UAAU,GAAItG,EAAa8F,GAAY,GAC5CK,EAAKI,UAAU,GAAIT,GAAY,GAC/BK,EAAKI,UAAU,GAtBE,IAsBY,GAC7BtG,KAAKoG,aAAaF,EAAM,GAAI,QAC5BA,EAAKG,UAAU,GAAIN,GAAe,GAE3B/F,KAAKuG,iBAAiBL,EAAMpF,EAAQ0F,GAC7C,GAEA,8BAKA,SAAyBrC,EAAoBrD,EAAsB6B,GACjE,IAAK,IAAIJ,EAAI,EAAGA,EAAIzB,EAAO0B,OAAQD,IAAKI,GAAU,EAAG,CACnD,IAAM8D,EAAMzD,KAAKwC,KAAK,EAAGxC,KAAK0D,IAAI,EAAG5F,EAAOyB,KAC5C4B,EAASwC,SAAShE,EAAQ8D,EAAM,EAAU,MAANA,EAAqB,MAANA,GAAc,EACnE,CAEA,OAAOtC,CACT,GAEA,0BAKA,SAAqBA,EAAoBxB,EAAgBiE,GACvD,IAAK,IAAIrE,EAAI,EAAGA,EAALine truncated

system/tts_generator/howler.min.js

@@ -1,4 +1,4 @@
-/*! howler.js v2.2.4 | (c) 2013-2020, James Simpson of GoldFire Studios | MIT License | howlerjs.com */
-!function(){"use strict";var e=function(){this.init()};e.prototype={init:function(){var e=this||n;return e._counter=1e3,e._html5AudioPool=[],e.html5PoolSize=10,e._codecs={},e._howls=[],e._muted=!1,e._volume=1,e._canPlayEvent="canplaythrough",e._navigator="undefined"!=typeof window&&window.navigator?window.navigator:null,e.masterGain=null,e.noAudio=!1,e.usingWebAudio=!0,e.autoSuspend=!0,e.ctx=null,e.autoUnlock=!0,e._setup(),e},volume:function(e){var o=this||n;if(e=parseFloat(e),o.ctx||_(),void 0!==e&&e>=0&&e<=1){if(o._volume=e,o._muted)return o;o.usingWebAudio&&o.masterGain.gain.setValueAtTime(e,n.ctx.currentTime);for(var t=0;t<o._howls.length;t++)if(!o._howls[t]._webAudio)for(var r=o._howls[t]._getSoundIds(),a=0;a<r.length;a++){var u=o._howls[t]._soundById(r[a]);u&&u._node&&(u._node.volume=u._volume*e)}return o}return o._volume},mute:function(e){var o=this||n;o.ctx||_(),o._muted=e,o.usingWebAudio&&o.masterGain.gain.setValueAtTime(e?0:o._volume,n.ctx.currentTime);for(var t=0;t<o._howls.length;t++)if(!o._howls[t]._webAudio)for(var r=o._howls[t]._getSoundIds(),a=0;a<r.length;a++){var u=o._howls[t]._soundById(r[a]);u&&u._node&&(u._node.muted=!!e||u._muted)}return o},stop:function(){for(var e=this||n,o=0;o<e._howls.length;o++)e._howls[o].stop();return e},unload:function(){for(var e=this||n,o=e._howls.length-1;o>=0;o--)e._howls[o].unload();return e.usingWebAudio&&e.ctx&&void 0!==e.ctx.close&&(e.ctx.close(),e.ctx=null,_()),e},codecs:function(e){return(this||n)._codecs[e.replace(/^x-/,"")]},_setup:function(){var e=this||n;if(e.state=e.ctx?e.ctx.state||"suspended":"suspended",e._autoSuspend(),!e.usingWebAudio)if("undefined"!=typeof Audio)try{var o=new Audio;void 0===o.oncanplaythrough&&(e._canPlayEvent="canplay")}catch(n){e.noAudio=!0}else e.noAudio=!0;try{var o=new Audio;o.muted&&(e.noAudio=!0)}catch(e){}return e.noAudio||e._setupCodecs(),e},_setupCodecs:function(){var e=this||n,o=null;try{o="undefined"!=typeof Audio?new Audio:null}catch(n){return e}if(!o||"function"!=typeof o.canPlayType)return e;var t=o.canPlayType("audio/mpeg;").replace(/^no$/,""),r=e._navigator?e._navigator.userAgent:"",a=r.match(/OPR\/(\d+)/g),u=a&&parseInt(a[0].split("/")[1],10)<33,d=-1!==r.indexOf("Safari")&&-1===r.indexOf("Chrome"),i=r.match(/Version\/(.*?) /),_=d&&i&&parseInt(i[1],10)<15;return e._codecs={mp3:!(u||!t&&!o.canPlayType("audio/mp3;").replace(/^no$/,"")),mpeg:!!t,opus:!!o.canPlayType('audio/ogg; codecs="opus"').replace(/^no$/,""),ogg:!!o.canPlayType('audio/ogg; codecs="vorbis"').replace(/^no$/,""),oga:!!o.canPlayType('audio/ogg; codecs="vorbis"').replace(/^no$/,""),wav:!!(o.canPlayType('audio/wav; codecs="1"')||o.canPlayType("audio/wav")).replace(/^no$/,""),aac:!!o.canPlayType("audio/aac;").replace(/^no$/,""),caf:!!o.canPlayType("audio/x-caf;").replace(/^no$/,""),m4a:!!(o.canPlayType("audio/x-m4a;")||o.canPlayType("audio/m4a;")||o.canPlayType("audio/aac;")).replace(/^no$/,""),m4b:!!(o.canPlayType("audio/x-m4b;")||o.canPlayType("audio/m4b;")||o.canPlayType("audio/aac;")).replace(/^no$/,""),mp4:!!(o.canPlayType("audio/x-mp4;")||o.canPlayType("audio/mp4;")||o.canPlayType("audio/aac;")).replace(/^no$/,""),weba:!(_||!o.canPlayType('audio/webm; codecs="vorbis"').replace(/^no$/,"")),webm:!(_||!o.canPlayType('audio/webm; codecs="vorbis"').replace(/^no$/,"")),dolby:!!o.canPlayType('audio/mp4; codecs="ec-3"').replace(/^no$/,""),flac:!!(o.canPlayType("audio/x-flac;")||o.canPlayType("audio/flac;")).replace(/^no$/,"")},e},_unlockAudio:function(){var e=this||n;if(!e._audioUnlocked&&e.ctx){e._audioUnlocked=!1,e.autoUnlock=!1,e._mobileUnloaded||44100===e.ctx.sampleRate||(e._mobileUnloaded=!0,e.unload()),e._scratchBuffer=e.ctx.createBuffer(1,1,22050);var o=function(n){for(;e._html5AudioPool.length<e.html5PoolSize;)try{var t=new Audio;t._unlocked=!0,e._releaseHtml5Audio(t)}catch(n){e.noAudio=!0;break}for(var r=0;r<e._howls.length;r++)if(!e._howls[r]._webAudio)for(var a=e._howls[r]._getSoundIds(),u=0;u<a.length;u++){var d=e._howls[r]._soundById(a[u]);d&&d._node&&!d._node._unlocked&&(d._node._unlocked=!0,d._node.load())}e._autoResume();var i=e.ctx.createBufferSource();i.buffer=e._scratchBuffer,i.connect(e.ctx.destination),void 0===i.start?i.noteOn(0):i.start(0),"function"==typeof e.ctx.resume&&e.ctx.resume(),i.onended=function(){i.disconnect(0),e._audioUnlocked=!0,document.removeEventListener("touchstart",o,!0),document.removeEventListener("touchend",o,!0),document.removeEventListener("click",o,!0),document.removeEventListener("keydown",o,!0);for(var n=0;n<e._howls.length;n++)e._howls[n]._emit("unlock")}};return document.addEventListener("touchstart",o,!0),document.addEventListener("touchend",o,!0),document.addEventListener("click",o,!0),document.addEventListener("keydown",o,!0),e}},_obtainHtml5Audio:function(){var e=this||n;if(e._html5AudioPool.length)return e._html5AudioPool.pop();var o=(new Audio).play();return o&&"undefined"!=typeof Promise&&(o instanceof Promise||"function"==typeof o.then)&&o.catch(function(){console.warn("HTML5 Audio pool eLine truncated
-/*! Spatial Plugin */
+/*! howler.js v2.2.4 | (c) 2013-2020, James Simpson of GoldFire Studios | MIT License | howlerjs.com */
+!function(){"use strict";var e=function(){this.init()};e.prototype={init:function(){var e=this||n;return e._counter=1e3,e._html5AudioPool=[],e.html5PoolSize=10,e._codecs={},e._howls=[],e._muted=!1,e._volume=1,e._canPlayEvent="canplaythrough",e._navigator="undefined"!=typeof window&&window.navigator?window.navigator:null,e.masterGain=null,e.noAudio=!1,e.usingWebAudio=!0,e.autoSuspend=!0,e.ctx=null,e.autoUnlock=!0,e._setup(),e},volume:function(e){var o=this||n;if(e=parseFloat(e),o.ctx||_(),void 0!==e&&e>=0&&e<=1){if(o._volume=e,o._muted)return o;o.usingWebAudio&&o.masterGain.gain.setValueAtTime(e,n.ctx.currentTime);for(var t=0;t<o._howls.length;t++)if(!o._howls[t]._webAudio)for(var r=o._howls[t]._getSoundIds(),a=0;a<r.length;a++){var u=o._howls[t]._soundById(r[a]);u&&u._node&&(u._node.volume=u._volume*e)}return o}return o._volume},mute:function(e){var o=this||n;o.ctx||_(),o._muted=e,o.usingWebAudio&&o.masterGain.gain.setValueAtTime(e?0:o._volume,n.ctx.currentTime);for(var t=0;t<o._howls.length;t++)if(!o._howls[t]._webAudio)for(var r=o._howls[t]._getSoundIds(),a=0;a<r.length;a++){var u=o._howls[t]._soundById(r[a]);u&&u._node&&(u._node.muted=!!e||u._muted)}return o},stop:function(){for(var e=this||n,o=0;o<e._howls.length;o++)e._howls[o].stop();return e},unload:function(){for(var e=this||n,o=e._howls.length-1;o>=0;o--)e._howls[o].unload();return e.usingWebAudio&&e.ctx&&void 0!==e.ctx.close&&(e.ctx.close(),e.ctx=null,_()),e},codecs:function(e){return(this||n)._codecs[e.replace(/^x-/,"")]},_setup:function(){var e=this||n;if(e.state=e.ctx?e.ctx.state||"suspended":"suspended",e._autoSuspend(),!e.usingWebAudio)if("undefined"!=typeof Audio)try{var o=new Audio;void 0===o.oncanplaythrough&&(e._canPlayEvent="canplay")}catch(n){e.noAudio=!0}else e.noAudio=!0;try{var o=new Audio;o.muted&&(e.noAudio=!0)}catch(e){}return e.noAudio||e._setupCodecs(),e},_setupCodecs:function(){var e=this||n,o=null;try{o="undefined"!=typeof Audio?new Audio:null}catch(n){return e}if(!o||"function"!=typeof o.canPlayType)return e;var t=o.canPlayType("audio/mpeg;").replace(/^no$/,""),r=e._navigator?e._navigator.userAgent:"",a=r.match(/OPR\/(\d+)/g),u=a&&parseInt(a[0].split("/")[1],10)<33,d=-1!==r.indexOf("Safari")&&-1===r.indexOf("Chrome"),i=r.match(/Version\/(.*?) /),_=d&&i&&parseInt(i[1],10)<15;return e._codecs={mp3:!(u||!t&&!o.canPlayType("audio/mp3;").replace(/^no$/,"")),mpeg:!!t,opus:!!o.canPlayType('audio/ogg; codecs="opus"').replace(/^no$/,""),ogg:!!o.canPlayType('audio/ogg; codecs="vorbis"').replace(/^no$/,""),oga:!!o.canPlayType('audio/ogg; codecs="vorbis"').replace(/^no$/,""),wav:!!(o.canPlayType('audio/wav; codecs="1"')||o.canPlayType("audio/wav")).replace(/^no$/,""),aac:!!o.canPlayType("audio/aac;").replace(/^no$/,""),caf:!!o.canPlayType("audio/x-caf;").replace(/^no$/,""),m4a:!!(o.canPlayType("audio/x-m4a;")||o.canPlayType("audio/m4a;")||o.canPlayType("audio/aac;")).replace(/^no$/,""),m4b:!!(o.canPlayType("audio/x-m4b;")||o.canPlayType("audio/m4b;")||o.canPlayType("audio/aac;")).replace(/^no$/,""),mp4:!!(o.canPlayType("audio/x-mp4;")||o.canPlayType("audio/mp4;")||o.canPlayType("audio/aac;")).replace(/^no$/,""),weba:!(_||!o.canPlayType('audio/webm; codecs="vorbis"').replace(/^no$/,"")),webm:!(_||!o.canPlayType('audio/webm; codecs="vorbis"').replace(/^no$/,"")),dolby:!!o.canPlayType('audio/mp4; codecs="ec-3"').replace(/^no$/,""),flac:!!(o.canPlayType("audio/x-flac;")||o.canPlayType("audio/flac;")).replace(/^no$/,"")},e},_unlockAudio:function(){var e=this||n;if(!e._audioUnlocked&&e.ctx){e._audioUnlocked=!1,e.autoUnlock=!1,e._mobileUnloaded||44100===e.ctx.sampleRate||(e._mobileUnloaded=!0,e.unload()),e._scratchBuffer=e.ctx.createBuffer(1,1,22050);var o=function(n){for(;e._html5AudioPool.length<e.html5PoolSize;)try{var t=new Audio;t._unlocked=!0,e._releaseHtml5Audio(t)}catch(n){e.noAudio=!0;break}for(var r=0;r<e._howls.length;r++)if(!e._howls[r]._webAudio)for(var a=e._howls[r]._getSoundIds(),u=0;u<a.length;u++){var d=e._howls[r]._soundById(a[u]);d&&d._node&&!d._node._unlocked&&(d._node._unlocked=!0,d._node.load())}e._autoResume();var i=e.ctx.createBufferSource();i.buffer=e._scratchBuffer,i.connect(e.ctx.destination),void 0===i.start?i.noteOn(0):i.start(0),"function"==typeof e.ctx.resume&&e.ctx.resume(),i.onended=function(){i.disconnect(0),e._audioUnlocked=!0,document.removeEventListener("touchstart",o,!0),document.removeEventListener("touchend",o,!0),document.removeEventListener("click",o,!0),document.removeEventListener("keydown",o,!0);for(var n=0;n<e._howls.length;n++)e._howls[n]._emit("unlock")}};return document.addEventListener("touchstart",o,!0),document.addEventListener("touchend",o,!0),document.addEventListener("click",o,!0),document.addEventListener("keydown",o,!0),e}},_obtainHtml5Audio:function(){var e=this||n;if(e._html5AudioPool.length)return e._html5AudioPool.pop();var o=(new Audio).play();return o&&"undefined"!=typeof Promise&&(o instanceof Promise||"function"==typeof o.then)&&o.catch(function(){console.warn("HTML5 Audio pool eLine truncated
+/*! Spatial Plugin */
 !function(){"use strict";HowlerGlobal.prototype._pos=[0,0,0],HowlerGlobal.prototype._orientation=[0,0,-1,0,1,0],HowlerGlobal.prototype.stereo=function(e){var n=this;if(!n.ctx||!n.ctx.listener)return n;for(var t=n._howls.length-1;t>=0;t--)n._howls[t].stereo(e);return n},HowlerGlobal.prototype.pos=function(e,n,t){var r=this;return r.ctx&&r.ctx.listener?(n="number"!=typeof n?r._pos[1]:n,t="number"!=typeof t?r._pos[2]:t,"number"!=typeof e?r._pos:(r._pos=[e,n,t],void 0!==r.ctx.listener.positionX?(r.ctx.listener.positionX.setTargetAtTime(r._pos[0],Howler.ctx.currentTime,.1),r.ctx.listener.positionY.setTargetAtTime(r._pos[1],Howler.ctx.currentTime,.1),r.ctx.listener.positionZ.setTargetAtTime(r._pos[2],Howler.ctx.currentTime,.1)):r.ctx.listener.setPosition(r._pos[0],r._pos[1],r._pos[2]),r)):r},HowlerGlobal.prototype.orientation=function(e,n,t,r,o,i){var a=this;if(!a.ctx||!a.ctx.listener)return a;var p=a._orientation;return n="number"!=typeof n?p[1]:n,t="number"!=typeof t?p[2]:t,r="number"!=typeof r?p[3]:r,o="number"!=typeof o?p[4]:o,i="number"!=typeof i?p[5]:i,"number"!=typeof e?p:(a._orientation=[e,n,t,r,o,i],void 0!==a.ctx.listener.forwardX?(a.ctx.listener.forwardX.setTargetAtTime(e,Howler.ctx.currentTime,.1),a.ctx.listener.forwardY.setTargetAtTime(n,Howler.ctx.currentTime,.1),a.ctx.listener.forwardZ.setTargetAtTime(t,Howler.ctx.currentTime,.1),a.ctx.listener.upX.setTargetAtTime(r,Howler.ctx.currentTime,.1),a.ctx.listener.upY.setTargetAtTime(o,Howler.ctx.currentTime,.1),a.ctx.listener.upZ.setTargetAtTime(i,Howler.ctx.currentTime,.1)):a.ctx.listener.setOrientation(e,n,t,r,o,i),a)},Howl.prototype.init=function(e){return function(n){var t=this;return t._orientation=n.orientation||[1,0,0],t._stereo=n.stereo||null,t._pos=n.pos||null,t._pannerAttr={coneInnerAngle:void 0!==n.coneInnerAngle?n.coneInnerAngle:360,coneOuterAngle:void 0!==n.coneOuterAngle?n.coneOuterAngle:360,coneOuterGain:void 0!==n.coneOuterGain?n.coneOuterGain:0,distanceModel:void 0!==n.distanceModel?n.distanceModel:"inverse",maxDistance:void 0!==n.maxDistance?n.maxDistance:1e4,panningModel:void 0!==n.panningModel?n.panningModel:"HRTF",refDistance:void 0!==n.refDistance?n.refDistance:1,rolloffFactor:void 0!==n.rolloffFactor?n.rolloffFactor:1},t._onstereo=n.onstereo?[{fn:n.onstereo}]:[],t._onpos=n.onpos?[{fn:n.onpos}]:[],t._onorientation=n.onorientation?[{fn:n.onorientation}]:[],e.call(this,n)}}(Howl.prototype.init),Howl.prototype.stereo=function(n,t){var r=this;if(!r._webAudio)return r;if("loaded"!==r._state)return r._queue.push({event:"stereo",action:function(){r.stereo(n,t)}}),r;var o=void 0===Howler.ctx.createStereoPanner?"spatial":"stereo";if(void 0===t){if("number"!=typeof n)return r._stereo;r._stereo=n,r._pos=[n,0,0]}for(var i=r._getSoundIds(t),a=0;a<i.length;a++){var p=r._soundById(i[a]);if(p){if("number"!=typeof n)return p._stereo;p._stereo=n,p._pos=[n,0,0],p._node&&(p._pannerAttr.panningModel="equalpower",p._panner&&p._panner.pan||e(p,o),"spatial"===o?void 0!==p._panner.positionX?(p._panner.positionX.setValueAtTime(n,Howler.ctx.currentTime),p._panner.positionY.setValueAtTime(0,Howler.ctx.currentTime),p._panner.positionZ.setValueAtTime(0,Howler.ctx.currentTime)):p._panner.setPosition(n,0,0):p._panner.pan.setValueAtTime(n,Howler.ctx.currentTime)),r._emit("stereo",p._id)}}return r},Howl.prototype.pos=function(n,t,r,o){var i=this;if(!i._webAudio)return i;if("loaded"!==i._state)return i._queue.push({event:"pos",action:function(){i.pos(n,t,r,o)}}),i;if(t="number"!=typeof t?0:t,r="number"!=typeof r?-.5:r,void 0===o){if("number"!=typeof n)return i._pos;i._pos=[n,t,r]}for(var a=i._getSoundIds(o),p=0;p<a.length;p++){var s=i._soundById(a[p]);if(s){if("number"!=typeof n)return s._pos;s._pos=[n,t,r],s._node&&(s._panner&&!s._panner.pan||e(s,"spatial"),void 0!==s._panner.positionX?(s._panner.positionX.setValueAtTime(n,Howler.ctx.currentTime),s._panner.positionY.setValueAtTime(t,Howler.ctx.currentTime),s._panner.positionZ.setValueAtTime(r,Howler.ctx.currentTime)):s._panner.setPosition(n,t,r)),i._emit("pos",s._id)}}return i},Howl.prototype.orientation=function(n,t,r,o){var i=this;if(!i._webAudio)return i;if("loaded"!==i._state)return i._queue.push({event:"orientation",action:function(){i.orientation(n,t,r,o)}}),i;if(t="number"!=typeof t?i._orientation[1]:t,r="number"!=typeof r?i._orientation[2]:r,void 0===o){if("number"!=typeof n)return i._orientation;i._orientation=[n,t,r]}for(var a=i._getSoundIds(o),p=0;p<a.length;p++){var s=i._soundById(a[p]);if(s){if("number"!=typeof n)return s._orientation;s._orientation=[n,t,r],s._node&&(s._panner||(s._pos||(s._pos=i._pos||[0,0,-.5]),e(s,"spatial")),void 0!==s._panner.orientationX?(s._panner.orientationX.setValueAtTime(n,Howler.ctx.currentTime),s._panner.orientationY.setValueAtTime(t,Howler.ctx.currentTime),s._panner.orientationZ.setValueAtTime(r,Howler.ctx.currentTime)):s._panner.setOrientation(n,t,r)),i._emit("orientation",s._id)}}return i},Howl.prototype.pannerAttr=function(){var n,t,r,o=this,i=arguments;if(!o._webAudioLine truncated

system/tts_generator/tts_generator.html

@@ -366,6 +366,11 @@
             /* Other styles for highlighting */
         }
 
+        .problematic {
+            background-color: rgb(179, 104, 104);
+            /* Or any light red color of your choice */
+        }
+
         .highlight-count {
             color: #ff7300;
             /* Change to the color you want */
@@ -390,6 +395,13 @@
             font-size: 0.8em;
         }
 
+        /*Disable and enable buttons*/
+        button:disabled {
+            background-color: #919191;
+            color: #666;
+            cursor: not-allowed;
+        }
+
         .edit-input {
             /* Styles for the edit input field */
             margin-top: 5px;
@@ -520,6 +532,7 @@
                 <option value="en" selected>English</option>
                 <option value="fr">French</option>
                 <option value="de">German</option>
+                <option value="hi">Hindi</option>
                 <option value="hu">Hungarian</option>
                 <option value="it">Italian</option>
                 <option value="ja">Japanese</option>
@@ -562,7 +575,7 @@
         <div class="setting slider-setting-wrapper">
             <label for="volume">Volume:</label>
             <div class="slider-container">
-                <input type="range" id="volume" name="volume" class="slider-setting" min="0.0" max="1.0" step="0.1"
+                <input type="range" id="volume" name="volume" class="slider-setting" min="0.1" max="1.0" step="0.1"
                     value="0.8" oninput="updateVolumeValue(this.value)">
                 <span id="volumeValue">0.8</span>
             </div>
@@ -595,14 +608,17 @@
 <div id="ttsListSection" class="tts-list-section">
     <h2>Generated TTS List</h2>
     <input type="number" id="startFromId" value="1" min="1" autocomplete="off" style="width: 60px; margin-right: 10px;">
-    <button id="playPauseList" onclick="togglePlayPauseList()" style="margin-right: 10px;">Play List</button>
-    <button onclick="stopPlayback()" style="margin-right: 10px;">Stop Playback</button>
-    <button id="clearList" onclick="clearTTSList()" style="margin-right: 10px;">Clear List</button>
-    <button onclick="exportToJSON()" style="margin-right: 10px;">Export List as JSON</button>
-    <button onclick="importFromJSON()" style="margin-right: 10px;">Import JSON to list</button>
-    <button onclick="exportMP3()" style="margin-right: 10px;">Export to Wav</button>
-    <label for="splitEvery">Split every:</label>
-    <select id="splitEvery" name="splitEvery">
+    <button class="conditional-btn" id="playPauseList" onclick="togglePlayPauseList()" style="margin-right: 10px;">Play
+        List</button>
+    <button class="conditional-btn" onclick="stopPlayback()" style="margin-right: 10px;">Stop Playback</button>
+    <button class="conditional-btn" id="clearList" onclick="clearTTSList()" style="margin-right: 40px;">Clear
+        List</button>
+    <button onclick="importFromJSON()" style="margin-right: 10px;">Import JSON</button>
+    <button class="conditional-btn" onclick="exportToJSON()" style="margin-right: 10px;">Export JSON</button>
+    <button class="conditional-btn" id="exportsrttitles" style="margin-right: 10px;">Export SRT</button>
+    <button class="conditional-btn" onclick="exportMP3()" style="margin-right: 10px;">Export to WAV</button>
+    <label for="splitEvery">Export Split:</label>
+    <select id="splitEvery" name="splitEvery" style="margin-right: 40px;">
         <option value="100">100</option>
         <option value="200">200</option>
         <option value="300">300</option>
@@ -610,22 +626,38 @@
         <option value="500" selected>500</option>
         <option value="600">600</option>
     </select>
+    <button class="conditional-btn" id="saveAndAnalyzeTTS" style="margin-right: 10px;">Analyze TTS</button>
+    <label for="AnalyzeAccuracy">% Accuracy:</label>
+    <select id="AnalyzeAccuracy" name="AnalyzeAccuracy" style="margin-right: 10px;">
+        <option value="99">99</option>
+        <option value="98" selected>98</option>
+        <option value="97">97</option>
+        <option value="96">96</option>
+        <option value="95">95</option>
+        <option value="94">94</option>
+        <option value="93">93</option>
+        <option value="92">92</option>
+        <option value="91">91</option>
+        <option value="90">90</option>
+    </select>
     <div id="paginationControls">
-        <button id="prevPage" class="pagination-btn">Previous</button>
+        <button class="conditional-btn pagination-btn" id="prevPage">Previous</button>
         <span id="pageIndicator">Page 1 of X</span>
-        <button id="nextPage" class="pagination-btn">Next</button>
-        <input type="number" id="jumpToPage" class="pagination-input" min="1" placeholder="Jump to Page">
-        <button id="jumpButton" class="pagination-btn">Go</button>
+        <button class="conditional-btn pagination-btn" id="nextPage">Next</button>
+        <input type="number" id="jumpToPage" class="conditional-btn pagination-input" min="1"
+            placeholder="Jump to Page">
+        <button class="conditional-btn pagination-btn" id="jumpButton">Go</button>
     </div>
     <div id="ttsListDisplay" class="tts-list-display">
         <!-- Dynamically populated TTS details will go here -->
     </div>
     <div id="paginationControls1">
-        <button id="prevPage1" class="pagination-btn">Previous</button>
+        <button class="conditional-btn pagination-btn" id="prevPage1">Previous</button>
         <span id="pageIndicator1">Page 1 of X</span>
-        <button id="nextPage1" class="pagination-btn">Next</button>
-        <input type="number" id="jumpToPage1" class="pagination-input" min="1" placeholder="Jump to Page">
-        <button id="jumpButton1" class="pagination-btn">Go</button>
+        <button class="conditional-btn pagination-btn" id="nextPage1">Next</button>
+        <input type="number" id="jumpToPage1" class="conditional-btn pagination-input" min="1"
+            placeholder="Jump to Page">
+        <button class="conditional-btn pagination-btn" id="jumpButton1">Go</button>
     </div>
 </div>
 </div>
@@ -686,8 +718,6 @@
 
 </script>
 
-
-
 <script>
 
     /////////////////////////////////////////
@@ -704,6 +734,7 @@
     let isStreamInitialized = false;
     let characterVoice = document.getElementById("character_voice_gen").value;
     let ttsList = []; // Global list to store TTS details
+    let problematicIds = []; // Global list to store ProblematicIDs
     const howlInstances = {};
     let listPlaying = false;
     let listPlayIndex = 0;
@@ -759,6 +790,123 @@
     }
 
 
+    //////////////////////////////////
+    //////// Compare TTS list ////////
+    //////////////////////////////////
+
+    document.getElementById('saveAndAnalyzeTTS').addEventListener('click', async function () {
+        showProgress(); // Call this function to show the progress indicator at the start of the process
+        try {
+            // Serialize the ttsList data structure to a JSON string
+            const ttsDataJSON = JSON.stringify(ttsList);
+
+            // Send the serialized ttsList to the '/save-tts-data' endpoint
+            const saveResponse = await fetch('/api/save-tts-data', {
+                method: 'POST',
+                headers: { 'Content-Type': 'application/json' },
+                body: ttsDataJSON  // Use the serialized JSON string as the request body
+            });
+
+            const saveData = await saveResponse.json();
+
+            // Log the server's response
+            console.log(saveData.message);
+
+            // If the server confirms the data was saved successfully, trigger analysis
+            if (saveData.message === "Data saved successfully") {
+                const accuracy = parseInt(document.getElementById('AnalyzeAccuracy').value) || 98;
+                const analyzeResponse = await fetch(`/api/trigger-analysis?threshold=${accuracy}`);
+                const analyzeData = await analyzeResponse.json();
+                if (analyzeData.summary.flagged_ids && analyzeData.summary.flagged_ids.length > 0) {
+                    // Update the global problematicIds array with the new flagged IDs
+                    problematicIds = analyzeData.summary.flagged_ids;
+                    console.log("Initial problematicIds from analysis:", problematicIds); // Debugging: Check the initial array after receiving analysis results
+
+                    // Call highlightProblems with the array of flagged IDs
+                    highlightProblems(problematicIds);
+                } else {
+                    console.log("No problematic IDs or error retrieving data.");
+
+                    // Clear the problematicIds array since there are no problematic IDs
+                    problematicIds = [];
+                    highlightProblems(problematicIds);
+                }
+                // Optionally, you might want to provide feedback in the UI about the analysis status
+            } else {
+                throw new Error('Data save was unsuccessful.');
+            }
+        } catch (error) {
+            // Handle any errors that occurred during the fetch process
+            console.error('Error:', error);
+        } finally {
+            hideProgress(); // Hide the progress indicator when the process is complete or if an error occurs
+        }
+    });
+
+    function highlightProblems(idsToHighlight) {
+        // First, clear all previous 'problematic' highlights
+        document.querySelectorAll('.problematic').forEach(item => {
+            item.classList.remove('problematic');
+        });
+
+        // Now, highlight all the IDs that should still be problematic
+        idsToHighlight.forEach(id => {
+            const itemElement = document.getElementById(`item-${id}`);
+            if (itemElement) {
+                itemElement.classList.add('problematic');
+            }
+        });
+    }
+
+    /////////////////////////////////
+    //////// Export SRT Subs ////////
+    /////////////////////////////////
+
+    document.getElementById('exportsrttitles').addEventListener('click', async function () {
+        showProgress(); // Call this function to show the progress indicator at the start of the process
+        try {
+            const ttsDataJSON = JSON.stringify(ttsList);
+
+            const saveResponse = await fetch('/api/save-tts-data', {
+                method: 'POST',
+                headers: { 'Content-Type': 'application/json' },
+                body: ttsDataJSON
+            });
+            const saveData = await saveResponse.json();
+            console.log(saveData.message);
+
+            if (saveData.message === "Data saved successfully") {
+                // Trigger the SRT generation and handle file download
+                const analyzeResponse = await fetch(`/api/srt-generation`);
+                if (analyzeResponse.ok) {
+                    // Create a temporary anchor element
+                    const a = document.createElement('a');
+                    // Create a blob URL from the response
+                    const blob = await analyzeResponse.blob();
+                    const url = window.URL.createObjectURL(blob);
+                    a.href = url;
+                    // Set the download name for the file
+                    a.download = "subtitles.srt";
+                    // Append the anchor to the document
+                    document.body.appendChild(a);
+                    // Trigger the download
+                    a.click();
+                    // Clean up by removing the anchor element and revoking the blob URL
+                    window.URL.revokeObjectURL(url);
+                    a.remove();
+                } else {
+                    console.log("Error running SRT generation.");
+                }
+            } else {
+                throw new Error('Data save was unsuccessful.');
+            }
+        } catch (error) {
+            console.error('Error:', error);
+        } finally {
+            hideProgress(); // Hide the progress indicator when the process is complete or if an error occurs
+        }
+    });
+
     ///////////////////////////////////////////
     //////// TTS Generation Activities ////////
     ///////////////////////////////////////////
@@ -774,11 +922,21 @@
             const playType = document.getElementById('playType').value; // Play type (chunk or stream)
             playModeValue = document.getElementById('playMode').value;
 
-            let cleanedText = textInput.replace(/ \- | \– /g, ' ');
+            let cleanedText = textInput.replace(/ \\- | \\– /g, ' ');
             cleanedText = cleanedText.replace(/%/g, " percent");
-            cleanedText = cleanedText.replace(/\.\s'/g, ".'");
-            cleanedText = cleanedText.replace(/[^a-zA-Z0-9\s\.,;:!?\-\'"À-ÿ\u0400-\u04FF\u0150\u0151\u0170\u0171]\$/g, '');
-            let sentences = cleanedText.split(/(?<=[.!?:])\s+/);
+            cleanedText = cleanedText.replace(/\\.\\s'/g, ".'");
+            cleanedText = cleanedText.replace(/(?<!\\w)\['\]+(?!\\w)/g, '');
+            cleanedText = cleanedText.replace(/"/g, "'");
+            cleanedText = cleanedText.replace(/[^a-zA-Z0-9\s.,;:!?\-'"$À-ÿ\u0400-\u04FF\u0150\u0151\u0170\u0171\u0900-\u097F\u2018\u2019\u201C\u201D\u2026\u3001\u3002\u3040-\u309F\u30A0-\u30FF\u4E00-\u9FFF\u3400-\u4DBF\uF900-\uFAFF\u0600-\u06FF\u0750-\u077F\uFB50-\uFDFF\uFE70-\uFEFF\uAC00-\uD7A3\u1100-\u11FF\u3130-\u318F\uFF01\uFF0c\uFF1A\uFF1B\uFF1F]/g, '');
+            cleanedText = cleanedText.replace(/-\\s/g, '; ');
+            cleanedText = cleanedText.replace(/--/g, '; ');
+            // Split by Fullwidth/CJK punctuation regardless of if there are spaces behind them
+            // Please test if it works properly. In my test they it should be 
+            // (?<=[.!?:])\s+ instead of 
+            // (?<=\[.!?:\])\\s+ 
+            // so I don't know whats going on here
+            // let sentences = cleanedText.split(/(?<=[\[.!?:\]])\s+|(?<=[\u3002\uFF01\uFF1A\uFF1F])/);
+            let sentences = cleanedText.split(/(?<=[\[.!?:\]]['"\u2018\u2019\u201C\u201D]*)\s+|(?<=[\u3002\uFF01\uFF1A\uFF1F])/);
 
             if (!sentences) {
                 console.error("No sentences found in the input text.");
@@ -886,6 +1044,7 @@
 
                 // Refresh the list display to reflect the new pagination state
                 updateUIList();
+                updateButtonStyles()
 
                 // Update the audio queue and UI
                 const sound = new Howl({
@@ -902,11 +1061,50 @@
                     playNextLocalChunk();
                 }
             }
+            return result
         } catch (error) {
             console.error("Error in generateAndCache:", error);
         }
     }
 
+    async function regenerateTTS(id) {
+        console.log("Before regeneration:", problematicIds); // Debugging: Check the array before regeneration
+
+        // Find the details of the TTS to regenerate
+        const ttsDetails = ttsList.find(item => item.id === id);
+        if (!ttsDetails) return;
+
+        // Retrieve the current volume setting from the HTML input
+        const currentVolume = parseFloat(document.getElementById("volume").value);
+
+        // Call the TTS generation with the same details and current volume
+        const result = await generateAndCache(ttsDetails.text, ttsDetails.language, ttsDetails.characterVoice, currentVolume, id);
+
+        if (result && result.status === "generate-success") {
+            const index = problematicIds.indexOf(id);
+            if (index !== -1) {
+                problematicIds.splice(index, 1); // Remove the id from problematicIds
+                console.log(`ID ${id} removed from problematicIds. Updated array:`, problematicIds); // Debugging: Check the array after removing an ID
+            }
+
+            // Find the element for this ID and remove the 'problematic' class
+            const problemItemElement = document.getElementById(`item-${id}`);
+            if (problemItemElement) {
+                problemItemElement.classList.remove('problematic');
+            }
+        } else {
+            console.log(`Regeneration failed for ID ${id}.`, result); // If regeneration fails, log the result
+        }
+
+        // Refresh the UI list to reflect the new data
+        updateUIList(); // Assume this function exists and it updates the display list
+        // Reapply highlighting to the items still in problematicIds
+        highlightProblems(problematicIds);
+        console.log("After regeneration and re-highlighting:", problematicIds); // Debugging: Check the array after re-highlighting
+    }
+
+
+
     async function generateWithoutPlayback(chunk, language, characterVoice, id = null) {
         // Perform the generation process as usual but do not play the audio
         try {
@@ -972,19 +1170,6 @@
         }
     }
 
-
-    async function regenerateTTS(id) {
-        // Find the details of the TTS to regenerate
-        const ttsDetails = ttsList.find(item => item.id === id);
-        if (!ttsDetails) return;
-
-        // Retrieve the current volume setting from the HTML input
-        const currentVolume = parseFloat(document.getElementById("volume").value);
-
-        // Call the TTS generation with the same details and current volume
-        await generateAndCache(ttsDetails.text, ttsDetails.language, ttsDetails.characterVoice, currentVolume, id);
-    }
-
     function updateUIList() {
         const listDisplay = document.getElementById('ttsListDisplay');
         if (!listDisplay) {
@@ -1029,7 +1214,9 @@
         document.getElementById('pageIndicator').innerText = `Page ${currentPage} of ${lastPage}`;
         document.getElementById('pageIndicator1').innerText = `Page ${currentPage} of ${lastPage}`;
         document.getElementById('prevPage').disabled = (currentPage === 1);
+        document.getElementById('prevPage1').disabled = (currentPage === 1);
         document.getElementById('nextPage').disabled = (currentPage === lastPage);
+        document.getElementById('nextPage1').disabled = (currentPage === lastPage);
     }
 
 
@@ -1240,7 +1427,7 @@
         } else {
             // In chunk mode, toggle the chunk play/pause
             if (isPlaying && currentlyPlayingIndex > 0) {
-                let currentSound = audioQueue[currentlyPlayingIndex - 1];
+                let currentSound = audioQueue[currentlyPlayingIndex - 3];
                 if (currentSound.playing()) {
                     currentSound.pause();
                 } else {
@@ -1267,16 +1454,6 @@
         }
     }
 
-
-    function stopPlayback() {
-        Howler.stop();
-        audioQueue = [];
-        // Unload each sound in the queue
-        audioQueue.forEach(sound => sound.unload());
-        currentlyPlayingIndex = 0;
-        isPlaying = false;
-    }
-
     function updatePlaybackButton() {
         const playbackButton = document.querySelector(".toggle-playback");
 
@@ -1451,38 +1628,64 @@
         if (pageIndicator1) {
             pageIndicator1.textContent = 'Page 1 of 1';
         }
+        updateButtonStyles()
+    }
+
+
+    function encodeHtmlEntities(text) {
+        return text.replace(/"/g, '&quot;').replace(/'/g, '&#39;');
+    }
+
+    function decodeHtmlEntities(text) {
+        var textArea = document.createElement('textarea');
+        textArea.innerHTML = text;
+        return textArea.value;
     }
 
     function editText(id) {
+        console.log(`Initiating edit for ID: ${id}`);
+        console.log("Before edit, ttsList:", JSON.parse(JSON.stringify(ttsList)));
         // First, check if we're already editing and should save the current value
         const existingInput = document.getElementById(`edit-input-${id}`);
         if (existingInput) {
+            console.log(`Existing input found for ID: ${id}, triggering blur event to save.`);
             existingInput.blur(); // This will trigger the blur event, saving the current value
             return; // Don't proceed further since we're just saving the existing input
         }
-
         const entryDiv = document.getElementById(`item-${id}`);
         if (!entryDiv) {
             console.error(`Item with ID ${id} not found.`);
             return;
         }
-
         const textPreviewSpan = entryDiv.querySelector('.text-preview');
-        const fullText = textPreviewSpan.getAttribute('data-fulltext');
+        // Retrieve the full text and immediately encode it
+        let fullText = textPreviewSpan.getAttribute('data-fulltext');
+        fullText = decodeHtmlEntities(fullText);
+        //fullText = encodeHtmlEntities(fullText);
+        console.log(`Current full text for ID: ${id} is: ${fullText}`);
 
         // Create an input field for editing
         const inputField = document.createElement('input');
         inputField.type = 'text';
+        // The value is already encoded at this point
         inputField.value = fullText;
         inputField.classList.add('edit-input');
         inputField.id = `edit-input-${id}`; // Assign an ID to the input field for later access
 
         // Handle saving the edited text
         inputField.addEventListener('blur', function () {
+            console.log(`Saving edited text for ID: ${id}: ${this.value}`);
             // Update the text in the ttsList array and the data-fulltext attribute
             const itemIndex = ttsList.findIndex(item => item.id === id);
             if (itemIndex !== -1) {
+                console.log(`Updating ttsList with new text for ID: ${id}`);
                 ttsList[itemIndex].text = this.value;
+                // If this item is in the list of problematic IDs, un-highlight it
+                if (problematicIds.includes(id)) {
+                    console.log(`ID: ${id} is problematic, removing highlight class`);
+                    const problemItemElement = document.getElementById(`item-${id}`);
+                    problemItemElement.classList.remove('problematic');
+                }
             }
 
             // Create a new span element to replace the input field
@@ -1494,15 +1697,18 @@
             newTextPreviewSpan.textContent = displayText;
 
             // Replace the input field with the new span
+            console.log(`Replacing input field with text span for ID: ${id}`);
             inputField.replaceWith(newTextPreviewSpan);
         });
 
         // Replace the span with the input field
+        console.log(`Replacing text span with input field for ID: ${id}`);
         textPreviewSpan.replaceWith(inputField);
 
         // Focus the input field and select its content to facilitate editing
         inputField.focus();
         inputField.select();
+        console.log("After edit, ttsList:", JSON.parse(JSON.stringify(ttsList)));
     }
 
     ////////////////////////////////////////
@@ -1550,6 +1756,7 @@
                         ttsList = jsonData;
                         currentPage = 1; // Reset to the first page
                         updateUIList();
+                        updateButtonStyles()
                         updatePaginationControls(); // Update pagination controls
                     } catch (error) {
                         console.error('Error parsing JSON:', error);
@@ -1563,34 +1770,42 @@
 
     function updatePaginationControls() {
         const lastPage = Math.ceil(ttsList.length / itemsPerPage);
-        const pageIndicator = document.getElementById('pageIndicator');
-        if (pageIndicator) {
-            pageIndicator.textContent = `Page ${currentPage} of ${lastPage}`;
-        }
+        const prevPageButtons = document.querySelectorAll('.pagination-btn[id^="prevPage"]');
+        const nextPageButtons = document.querySelectorAll('.pagination-btn[id^="nextPage"]');
 
-        const prevPageButton = document.getElementById('prevPage');
-        if (prevPageButton) {
-            prevPageButton.disabled = (currentPage === 1);
-        }
+        // Update page indicators and buttons
+        prevPageButtons.forEach(btn => btn.disabled = (currentPage === 1));
+        nextPageButtons.forEach(btn => btn.disabled = (currentPage === lastPage));
 
-        const nextPageButton = document.getElementById('nextPage');
-        if (nextPageButton) {
-            nextPageButton.disabled = (currentPage === lastPage);
-        }
+        // Assuming the page indicators are consistent with button IDs
+        document.querySelectorAll('span[id^="pageIndicator"]').forEach(indicator => {
+            indicator.textContent = `Page ${currentPage} of ${lastPage}`;
+        });
 
-        // Similar updates for any additional pagination controls if you have them
-        // ...
+        // Update 'Jump to Page' inputs and 'Go' buttons
+        const jumpToPageInputs = document.querySelectorAll('.pagination-input[id^="jumpToPage"]');
+        const jumpButtons = document.querySelectorAll('.pagination-btn[id^="jumpButton"]');
+        const moreThanOnePage = lastPage > 1;
+
+        jumpToPageInputs.forEach(input => input.disabled = !moreThanOnePage);
+        jumpButtons.forEach(button => button.disabled = !moreThanOnePage);
     }
 
-
-
-
-
-
     //////////////////////////////
     //////// Other Things ////////
     //////////////////////////////
 
+    function updateButtonStyles() {
+        const ttsList = document.getElementById('ttsListDisplay');
+        const buttons = document.querySelectorAll('.conditional-btn');
+
+        if (!ttsList.hasChildNodes()) { // Check if the list is empty
+            buttons.forEach(button => button.disabled = true); // Disable buttons
+        } else {
+            buttons.forEach(button => button.disabled = false); // Enable buttons
+        }
+    }
+
     function updateLanguage(language) {
         // Update the language in your application logic
         console.log("Selected language:", language);
@@ -1663,10 +1878,10 @@
     function stopPlayback() {
         Howler.stop();
         audioQueue = [];
-        currentlyPlayingIndex = 0;
+        //currentlyPlayingIndex = 0;
         isPlaying = false;
-        highlightPlaying(null);
-        document.getElementById('startFromId').value = '1'; // Reset the startFromId input to 1
+        //highlightPlaying(null);
+        //document.getElementById('startFromId').value = '1'; // Reset the startFromId input to 1
     }
 
     function displayOutput(result) {
@@ -1836,6 +2051,7 @@
     function setupPage() {
         // Fetch voices or other initial data
         fetchVoices();
+        updateButtonStyles()
 
         // Check for dark mode preference in localStorage, default to enabled if not set
         let isDarkModeEnabled = localStorage.getItem('darkMode');
@@ -1989,11 +2205,11 @@
         setupPage();
         hideProgress(); // Ensure the progress indicator is hidden on page load
         if (window.location.protocol !== 'http:' && window.location.protocol !== 'https:') {
-                alert('AllTalk TTS Generator is not designed to be run from your disk folder. Please run it from the correct URL e.g. http://127.0.0.1:7851/static/tts_chunk_player/tts_chunk_player.html');
-            }
+            alert('AllTalk TTS Generator is not designed to be run from your disk folder. Please run it from the correct URL e.g. http://127.0.0.1:7851/static/tts_chunk_player/tts_chunk_player.html');
+        }
     };
 
 </script>
 </body>
 
-</html>
+</html>

system/tts_srt/tts_srt.py

@@ -0,0 +1,77 @@
+import json
+import argparse
+import soundfile as sf
+from pathlib import Path
+
+parser = argparse.ArgumentParser(description="Compare TTS output with the original text using detailed comparison.")
+parser.add_argument("--ttslistpath", help="Path to the ttsList.json file")
+parser.add_argument("--wavfilespath", help="Path to the wav outputs folder")
+args = parser.parse_args()
+
+if not args.ttslistpath:
+    parser.error("[AllTalk TTSSRT] Please specify the path to the ttslist.json file using the --ttslistpath argument.")
+if not args.wavfilespath:
+    parser.error("[AllTalk TTSSRT] Please specify the path to the wavs output folder file using the --wavfilespath argument.")
+
+json_file_path = Path(args.ttslistpath).resolve()
+audio_files_base_path = Path(args.wavfilespath).resolve()
+
+print(f"[AllTalk TTSSRT]")
+print("[AllTalk TTSSRT] \033[92mStarting SRT Subtitle generation:\033[0m")
+print("[AllTalk TTSSRT]")
+print("[AllTalk TTSSRT] \033[94mJSON file  :\033[92m", json_file_path, "\033[0m")
+print("[AllTalk TTSSRT] \033[94mWAV files  :\033[92m", audio_files_base_path, "\033[0m")
+print("[AllTalk TTSSRT]")
+
+# Function to convert time in seconds to SRT time format
+def format_srt_time(seconds):
+    hours = int(seconds // 3600)
+    minutes = int((seconds % 3600) // 60)
+    seconds = seconds % 60
+    milliseconds = int((seconds - int(seconds)) * 1000)
+    return f"{hours:02}:{minutes:02}:{int(seconds):02},{milliseconds:03}"
+
+# Load the JSON data
+with open(json_file_path, 'r') as json_file:
+    data = json.load(json_file)
+
+# Initialize start time and SRT lines
+start_time = 0.0
+srt_lines = []
+
+# Loop through the JSON data to build SRT entries
+for entry in data:
+    file_name = Path(entry['fileUrl']).name  # Get the file name from the URL
+    file_path = audio_files_base_path / file_name
+    print(f"[AllTalk TTSSRT] Processing file: {file_name}")
+
+    if not file_path.exists():
+        print(f"[AllTalk TTSSRT] Audio file does not exist: {file_path}")
+        continue
+
+    try:
+        # Use soundfile to read the duration of the WAV file
+        with sf.SoundFile(str(file_path), 'r') as f:
+            duration = len(f) / f.samplerate
+            end_time = start_time + duration
+            
+            # Format the SRT entry
+            start_timestamp = format_srt_time(start_time)
+            end_timestamp = format_srt_time(end_time)
+            srt_lines.append(f"{len(srt_lines)+1}\n{start_timestamp} --> {end_timestamp}\n{entry['text']}\n")
+            
+            # Update the start time for the next entry
+            start_time = end_time
+    except RuntimeError as e:
+        print(f"[AllTalk TTSSRT] Error reading {file_path}: {e}")
+
+# Join all SRT lines into the final SRT content
+srt_content = "\n".join(srt_lines)
+
+# Save the SRT content to a file
+srt_file_path = audio_files_base_path / "subtitles.srt"
+with open(srt_file_path, "w") as srt_file:
+    srt_file.write(srt_content)
+
+print("[AllTalk TTSSRT]")
+print(f"[AllTalk TTSSRT] \033[94mSRT file created at \033[0m{srt_file_path}")

system/word_addin/1995fcd6d39cade7d871.js

@@ -1,2 +1,2 @@
-/*! For license information please see 1995fcd6d39cade7d871.js.LICENSE.txt */
+/*! For license information please see 1995fcd6d39cade7d871.js.LICENSE.txt */
 function _typeof(t){return _typeof="function"==typeof Symbol&&"symbol"==typeof Symbol.iterator?function(t){return typeof t}:function(t){return t&&"function"==typeof Symbol&&t.constructor===Symbol&&t!==Symbol.prototype?"symbol":typeof t},_typeof(t)}function _regeneratorRuntime(){"use strict";_regeneratorRuntime=function(){return e};var t,e={},r=Object.prototype,n=r.hasOwnProperty,o=Object.defineProperty||function(t,e,r){t[e]=r.value},i="function"==typeof Symbol?Symbol:{},a=i.iterator||"@@iterator",c=i.asyncIterator||"@@asyncIterator",u=i.toStringTag||"@@toStringTag";function l(t,e,r){return Object.defineProperty(t,e,{value:r,enumerable:!0,configurable:!0,writable:!0}),t[e]}try{l({},"")}catch(t){l=function(t,e,r){return t[e]=r}}function f(t,e,r,n){var i=e&&e.prototype instanceof m?e:m,a=Object.create(i.prototype),c=new G(n||[]);return o(a,"_invoke",{value:S(t,r,c)}),a}function s(t,e,r){try{return{type:"normal",arg:t.call(e,r)}}catch(t){return{type:"throw",arg:t}}}e.wrap=f;var h="suspendedStart",p="suspendedYield",y="executing",d="completed",v={};function m(){}function g(){}function w(){}var x={};l(x,a,(function(){return this}));var E=Object.getPrototypeOf,b=E&&E(E(B([])));b&&b!==r&&n.call(b,a)&&(x=b);var T=w.prototype=m.prototype=Object.create(x);function _(t){["next","throw","return"].forEach((function(e){l(t,e,(function(t){return this._invoke(e,t)}))}))}function L(t,e){function r(o,i,a,c){var u=s(t[o],t,i);if("throw"!==u.type){var l=u.arg,f=l.value;return f&&"object"==_typeof(f)&&n.call(f,"__await")?e.resolve(f.__await).then((function(t){r("next",t,a,c)}),(function(t){r("throw",t,a,c)})):e.resolve(f).then((function(t){l.value=t,a(l)}),(function(t){return r("throw",t,a,c)}))}c(u.arg)}var i;o(this,"_invoke",{value:function(t,n){function o(){return new e((function(e,o){r(t,n,e,o)}))}return i=i?i.then(o,o):o()}})}function S(e,r,n){var o=h;return function(i,a){if(o===y)throw new Error("Generator is already running");if(o===d){if("throw"===i)throw a;return{value:t,done:!0}}for(n.method=i,n.arg=a;;){var c=n.delegate;if(c){var u=I(c,n);if(u){if(u===v)continue;return u}}if("next"===n.method)n.sent=n._sent=n.arg;else if("throw"===n.method){if(o===h)throw o=d,n.arg;n.dispatchException(n.arg)}else"return"===n.method&&n.abrupt("return",n.arg);o=y;var l=s(e,r,n);if("normal"===l.type){if(o=n.done?d:p,l.arg===v)continue;return{value:l.arg,done:n.done}}"throw"===l.type&&(o=d,n.method="throw",n.arg=l.arg)}}}function I(e,r){var n=r.method,o=e.iterator[n];if(o===t)return r.delegate=null,"throw"===n&&e.iterator.return&&(r.method="return",r.arg=t,I(e,r),"throw"===r.method)||"return"!==n&&(r.method="throw",r.arg=new TypeError("The iterator does not provide a '"+n+"' method")),v;var i=s(o,e.iterator,r.arg);if("throw"===i.type)return r.method="throw",r.arg=i.arg,r.delegate=null,v;var a=i.arg;return a?a.done?(r[e.resultName]=a.value,r.next=e.nextLoc,"return"!==r.method&&(r.method="next",r.arg=t),r.delegate=null,v):a:(r.method="throw",r.arg=new TypeError("iterator result is not an object"),r.delegate=null,v)}function O(t){var e={tryLoc:t[0]};1 in t&&(e.catchLoc=t[1]),2 in t&&(e.finallyLoc=t[2],e.afterLoc=t[3]),this.tryEntries.push(e)}function j(t){var e=t.completion||{};e.type="normal",delete e.arg,t.completion=e}function G(t){this.tryEntries=[{tryLoc:"root"}],t.forEach(O,this),this.reset(!0)}function B(e){if(e||""===e){var r=e[a];if(r)return r.call(e);if("function"==typeof e.next)return e;if(!isNaN(e.length)){var o=-1,i=function r(){for(;++o<e.length;)if(n.call(e,o))return r.value=e[o],r.done=!1,r;return r.value=t,r.done=!0,r};return i.next=i}}throw new TypeError(_typeof(e)+" is not iterable")}return g.prototype=w,o(T,"constructor",{value:w,configurable:!0}),o(w,"constructor",{value:g,configurable:!0}),g.displayName=l(w,u,"GeneratorFunction"),e.isGeneratorFunction=function(t){var e="function"==typeof t&&t.constructor;return!!e&&(e===g||"GeneratorFunction"===(e.displayName||e.name))},e.mark=function(t){return Object.setPrototypeOf?Object.setPrototypeOf(t,w):(t.__proto__=w,l(t,u,"GeneratorFunction")),t.prototype=Object.create(T),t},e.awrap=function(t){return{__await:t}},_(L.prototype),l(L.prototype,c,(function(){return this})),e.AsyncIterator=L,e.async=function(t,r,n,o,i){void 0===i&&(i=Promise);var a=new L(f(t,r,n,o),i);return e.isGeneratorFunction(r)?a:a.next().then((function(t){return t.done?t.value:a.next()}))},_(T),l(T,u,"Generator"),l(T,a,(function(){return this})),l(T,"toString",(function(){return"[object Generator]"})),e.keys=function(t){var e=Object(t),r=[];for(var n in e)r.push(n);return r.reverse(),function t(){for(;r.length;){var n=r.pop();if(n in e)return t.value=n,t.done=!1,t}return t.done=!0,t}},e.values=B,G.prototype={constructor:G,reset:function(e){if(this.prev=0,this.next=0,this.sent=this._sent=t,this.done=!1,this.delegate=null,this.method="next",this.arg=t,this.tryEntries.forEach(j),!e)for(var r in this)"t"===r.charAt(0)&&n.call(this,r)&&!isNaN(+r.slice(1))&&(this[r]=t)},stop:function(){this.done=!0;var t=this.tryELine truncated

system/word_addin/1995fcd6d39cade7d871.js.LICENSE.txt

@@ -1 +1 @@
-/*! regenerator-runtime -- Copyright (c) 2014-present, Facebook, Inc. -- license (MIT): https://github.com/facebook/regenerator/blob/main/LICENSE */
+/*! regenerator-runtime -- Copyright (c) 2014-present, Facebook, Inc. -- license (MIT): https://github.com/facebook/regenerator/blob/main/LICENSE */

system/word_addin/1fda685b81e1123773f6.css

@@ -1,80 +1,80 @@
-/* 
- * Copyright (c) Microsoft Corporation. All rights reserved. Licensed under the MIT license.
- * See LICENSE in the project root for license information.
- */
-
- html,
- body {
-     width: 100%;
-     height: 100%;
-     margin: 0;
-     padding: 0;
- }
- 
- ul {
-     margin: 0;
-     padding: 0;
- }
- 
- .ms-welcome__header {
-    padding: 20px;
-    padding-bottom: 30px;
-    padding-top: 100px;
-    display: -webkit-flex;
-    display: flex;
-    -webkit-flex-direction: column;
-    flex-direction: column;
-    align-items: center;
- }
-
- .ms-welcome__main {
-    display: -webkit-flex;
-    display: flex;
-    -webkit-flex-direction: column;
-    flex-direction: column;
-    -webkit-flex-wrap: nowrap;
-    flex-wrap: nowrap;
-    -webkit-align-items: center;
-    align-items: center;
-    -webkit-flex: 1 0 0;
-    flex: 1 0 0;
-    padding: 10px 20px;
- }
- 
- .ms-welcome__main > h2 {
-     width: 100%;
-     text-align: center;
- }
- 
- .ms-welcome__features {
-     list-style-type: none;
-     margin-top: 20px;
- }
- 
- .ms-welcome__features.ms-List .ms-ListItem {
-     padding-bottom: 20px;
-     display: -webkit-flex;
-     display: flex;
- }
- 
- .ms-welcome__features.ms-List .ms-ListItem > .ms-Icon {
-     margin-right: 10px;
- }
- 
- .ms-welcome__action.ms-Button--hero {
-     margin-top: 30px;
- }
- 
-.ms-Button.ms-Button--hero .ms-Button-label {
-  color: #0078d7;
-}
-
-.ms-Button.ms-Button--hero:hover .ms-Button-label,
-.ms-Button.ms-Button--hero:focus .ms-Button-label{
-  color: #005a9e;
-  cursor: pointer;
-}
-
-b {
-    font-weight: bold;
+/* 
+ * Copyright (c) Microsoft Corporation. All rights reserved. Licensed under the MIT license.
+ * See LICENSE in the project root for license information.
+ */
+
+ html,
+ body {
+     width: 100%;
+     height: 100%;
+     margin: 0;
+     padding: 0;
+ }
+ 
+ ul {
+     margin: 0;
+     padding: 0;
+ }
+ 
+ .ms-welcome__header {
+    padding: 20px;
+    padding-bottom: 30px;
+    padding-top: 100px;
+    display: -webkit-flex;
+    display: flex;
+    -webkit-flex-direction: column;
+    flex-direction: column;
+    align-items: center;
+ }
+
+ .ms-welcome__main {
+    display: -webkit-flex;
+    display: flex;
+    -webkit-flex-direction: column;
+    flex-direction: column;
+    -webkit-flex-wrap: nowrap;
+    flex-wrap: nowrap;
+    -webkit-align-items: center;
+    align-items: center;
+    -webkit-flex: 1 0 0;
+    flex: 1 0 0;
+    padding: 10px 20px;
+ }
+ 
+ .ms-welcome__main > h2 {
+     width: 100%;
+     text-align: center;
+ }
+ 
+ .ms-welcome__features {
+     list-style-type: none;
+     margin-top: 20px;
+ }
+ 
+ .ms-welcome__features.ms-List .ms-ListItem {
+     padding-bottom: 20px;
+     display: -webkit-flex;
+     display: flex;
+ }
+ 
+ .ms-welcome__features.ms-List .ms-ListItem > .ms-Icon {
+     margin-right: 10px;
+ }
+ 
+ .ms-welcome__action.ms-Button--hero {
+     margin-top: 30px;
+ }
+ 
+.ms-Button.ms-Button--hero .ms-Button-label {
+  color: #0078d7;
+}
+
+.ms-Button.ms-Button--hero:hover .ms-Button-label,
+.ms-Button.ms-Button--hero:focus .ms-Button-label{
+  color: #005a9e;
+  cursor: pointer;
+}
+
+b {
+    font-weight: bold;
 }

system/word_addin/commands.js

@@ -1,2 +1,2 @@
-!function(){var e={};e.g=function(){if("object"==typeof globalThis)return globalThis;try{return this||new Function("return this")()}catch(e){if("object"==typeof window)return window}}(),Office.onReady((function(){})),("undefined"!=typeof self?self:"undefined"!=typeof window?window:void 0!==e.g?e.g:void 0).action=function(e){var n={type:Office.MailboxEnums.ItemNotificationMessageType.InformationalMessage,message:"Performed action.",icon:"Icon.80x80",persistent:!0};Office.context.mailbox.item.notificationMessages.replaceAsync("action",n),e.completed()}}();
+!function(){var e={};e.g=function(){if("object"==typeof globalThis)return globalThis;try{return this||new Function("return this")()}catch(e){if("object"==typeof window)return window}}(),Office.onReady((function(){})),("undefined"!=typeof self?self:"undefined"!=typeof window?window:void 0!==e.g?e.g:void 0).action=function(e){var n={type:Office.MailboxEnums.ItemNotificationMessageType.InformationalMessage,message:"Performed action.",icon:"Icon.80x80",persistent:!0};Office.context.mailbox.item.notificationMessages.replaceAsync("action",n),e.completed()}}();
 //# sourceMappingURL=commands.js.map

system/word_addin/manifest.xml

@@ -1,79 +1,79 @@
-<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
-<OfficeApp xmlns="http://schemas.microsoft.com/office/appforoffice/1.1" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:bt="http://schemas.microsoft.com/office/officeappbasictypes/1.0" xmlns:ov="http://schemas.microsoft.com/office/taskpaneappversionoverrides" xsi:type="TaskPaneApp">
-  <Id>68b6ad53-4f72-42a8-a971-a9643c2f409a</Id>
-  <Version>1.0.0.0</Version>
-  <ProviderName>AllTalk</ProviderName>
-  <DefaultLocale>en-US</DefaultLocale>
-  <DisplayName DefaultValue="AllTalk TTS"/>
-  <Description DefaultValue="Enhance your document creation with AllTalk TTS's advanced text-to-voice functionality. Requires connection to AllTalk server."/>
-  <IconUrl DefaultValue="http://127.0.0.1:7851/api/word_addin/assets/icon-32.png"/>
-  <HighResolutionIconUrl DefaultValue="http://127.0.0.1:7851/api/word_addin/assets/icon-64.png"/>
-  <SupportUrl DefaultValue="https://github.com/erew123/alltalk_tts/issues"/>
-  <AppDomains>
-    <AppDomain>https://www.contoso.com</AppDomain>
-  </AppDomains>
-  <Hosts>
-    <Host Name="Document"/>
-  </Hosts>
-  <DefaultSettings>
-    <SourceLocation DefaultValue="http://127.0.0.1:7851/api/word_addin/taskpane.html"/>
-  </DefaultSettings>
-  <Permissions>ReadWriteDocument</Permissions>
-  <VersionOverrides xmlns="http://schemas.microsoft.com/office/taskpaneappversionoverrides" xsi:type="VersionOverridesV1_0">
-    <Hosts>
-      <Host xsi:type="Document">
-        <DesktopFormFactor>
-          <!-- You can add GetStarted information here if needed -->
-          <FunctionFile resid="Commands.Url"/>
-          <ExtensionPoint xsi:type="PrimaryCommandSurface">
-            <OfficeTab id="TabHome">
-              <Group id="AllTalkGroup">
-                <Label resid="AllTalkGroup.Label"/>
-                <Icon>
-                  <bt:Image size="16" resid="Icon.16x16"/>
-                  <bt:Image size="32" resid="Icon.32x32"/>
-                  <bt:Image size="80" resid="Icon.80x80"/>
-                </Icon>
-                <Control xsi:type="Button" id="AllTalkTaskpaneButton">
-                  <Label resid="AllTalkTaskpaneButton.Label"/>
-                  <Supertip>
-                    <Title resid="AllTalkTaskpaneButton.Label"/>
-                    <Description resid="AllTalkTaskpaneButton.Tooltip"/>
-                  </Supertip>
-                  <Icon>
-                    <bt:Image size="16" resid="Icon.16x16"/>
-                    <bt:Image size="32" resid="Icon.32x32"/>
-                    <bt:Image size="80" resid="Icon.80x80"/>
-                  </Icon>
-                  <Action xsi:type="ShowTaskpane">
-                    <TaskpaneId>ButtonId1</TaskpaneId>
-                    <SourceLocation resid="Taskpane.Url"/>
-                  </Action>
-                </Control>
-              </Group>
-            </OfficeTab>
-          </ExtensionPoint>
-        </DesktopFormFactor>
-      </Host>
-    </Hosts>
-    <Resources>
-      <bt:Images>
-        <bt:Image id="Icon.16x16" DefaultValue="http://127.0.0.1:7851/api/word_addin/assets/icon-16.png"/>
-        <bt:Image id="Icon.32x32" DefaultValue="http://127.0.0.1:7851/api/word_addin/assets/icon-32.png"/>
-        <bt:Image id="Icon.80x80" DefaultValue="http://127.0.0.1:7851/api/word_addin/assets/icon-80.png"/>
-      </bt:Images>
-      <bt:Urls>
-        <!-- Ensure that these URLs are pointing to valid locations -->
-        <bt:Url id="Commands.Url" DefaultValue="http://127.0.0.1:7851/api/word_addin/commands.html"/>
-        <bt:Url id="Taskpane.Url" DefaultValue="http://127.0.0.1:7851/api/word_addin/taskpane.html"/>
-      </bt:Urls>
-      <bt:ShortStrings>
-        <bt:String id="AllTalkGroup.Label" DefaultValue="AllTalk Controls"/>
-        <bt:String id="AllTalkTaskpaneButton.Label" DefaultValue="Open AllTalk"/>
-      </bt:ShortStrings>
-      <bt:LongStrings>
-        <bt:String id="AllTalkTaskpaneButton.Tooltip" DefaultValue="Open the AllTalk task pane to start using the add-in."/>
-      </bt:LongStrings>
-    </Resources>
-  </VersionOverrides>
-</OfficeApp>
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<OfficeApp xmlns="http://schemas.microsoft.com/office/appforoffice/1.1" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:bt="http://schemas.microsoft.com/office/officeappbasictypes/1.0" xmlns:ov="http://schemas.microsoft.com/office/taskpaneappversionoverrides" xsi:type="TaskPaneApp">
+  <Id>68b6ad53-4f72-42a8-a971-a9643c2f409a</Id>
+  <Version>1.0.0.0</Version>
+  <ProviderName>AllTalk</ProviderName>
+  <DefaultLocale>en-US</DefaultLocale>
+  <DisplayName DefaultValue="AllTalk TTS"/>
+  <Description DefaultValue="Enhance your document creation with AllTalk TTS's advanced text-to-voice functionality. Requires connection to AllTalk server."/>
+  <IconUrl DefaultValue="http://127.0.0.1:7851/api/word_addin/assets/icon-32.png"/>
+  <HighResolutionIconUrl DefaultValue="http://127.0.0.1:7851/api/word_addin/assets/icon-64.png"/>
+  <SupportUrl DefaultValue="https://github.com/erew123/alltalk_tts/issues"/>
+  <AppDomains>
+    <AppDomain>https://www.contoso.com</AppDomain>
+  </AppDomains>
+  <Hosts>
+    <Host Name="Document"/>
+  </Hosts>
+  <DefaultSettings>
+    <SourceLocation DefaultValue="http://127.0.0.1:7851/api/word_addin/taskpane.html"/>
+  </DefaultSettings>
+  <Permissions>ReadWriteDocument</Permissions>
+  <VersionOverrides xmlns="http://schemas.microsoft.com/office/taskpaneappversionoverrides" xsi:type="VersionOverridesV1_0">
+    <Hosts>
+      <Host xsi:type="Document">
+        <DesktopFormFactor>
+          <!-- You can add GetStarted information here if needed -->
+          <FunctionFile resid="Commands.Url"/>
+          <ExtensionPoint xsi:type="PrimaryCommandSurface">
+            <OfficeTab id="TabHome">
+              <Group id="AllTalkGroup">
+                <Label resid="AllTalkGroup.Label"/>
+                <Icon>
+                  <bt:Image size="16" resid="Icon.16x16"/>
+                  <bt:Image size="32" resid="Icon.32x32"/>
+                  <bt:Image size="80" resid="Icon.80x80"/>
+                </Icon>
+                <Control xsi:type="Button" id="AllTalkTaskpaneButton">
+                  <Label resid="AllTalkTaskpaneButton.Label"/>
+                  <Supertip>
+                    <Title resid="AllTalkTaskpaneButton.Label"/>
+                    <Description resid="AllTalkTaskpaneButton.Tooltip"/>
+                  </Supertip>
+                  <Icon>
+                    <bt:Image size="16" resid="Icon.16x16"/>
+                    <bt:Image size="32" resid="Icon.32x32"/>
+                    <bt:Image size="80" resid="Icon.80x80"/>
+                  </Icon>
+                  <Action xsi:type="ShowTaskpane">
+                    <TaskpaneId>ButtonId1</TaskpaneId>
+                    <SourceLocation resid="Taskpane.Url"/>
+                  </Action>
+                </Control>
+              </Group>
+            </OfficeTab>
+          </ExtensionPoint>
+        </DesktopFormFactor>
+      </Host>
+    </Hosts>
+    <Resources>
+      <bt:Images>
+        <bt:Image id="Icon.16x16" DefaultValue="http://127.0.0.1:7851/api/word_addin/assets/icon-16.png"/>
+        <bt:Image id="Icon.32x32" DefaultValue="http://127.0.0.1:7851/api/word_addin/assets/icon-32.png"/>
+        <bt:Image id="Icon.80x80" DefaultValue="http://127.0.0.1:7851/api/word_addin/assets/icon-80.png"/>
+      </bt:Images>
+      <bt:Urls>
+        <!-- Ensure that these URLs are pointing to valid locations -->
+        <bt:Url id="Commands.Url" DefaultValue="http://127.0.0.1:7851/api/word_addin/commands.html"/>
+        <bt:Url id="Taskpane.Url" DefaultValue="http://127.0.0.1:7851/api/word_addin/taskpane.html"/>
+      </bt:Urls>
+      <bt:ShortStrings>
+        <bt:String id="AllTalkGroup.Label" DefaultValue="AllTalk Controls"/>
+        <bt:String id="AllTalkTaskpaneButton.Label" DefaultValue="Open AllTalk"/>
+      </bt:ShortStrings>
+      <bt:LongStrings>
+        <bt:String id="AllTalkTaskpaneButton.Tooltip" DefaultValue="Open the AllTalk task pane to start using the add-in."/>
+      </bt:LongStrings>
+    </Resources>
+  </VersionOverrides>
+</OfficeApp>

system/word_addin/polyfill.js

@@ -1,2 +1,2 @@
-!function(){var t={35666:function(t){var r=function(t){"use strict";var r,e=Object.prototype,n=e.hasOwnProperty,i=Object.defineProperty||function(t,r,e){t[r]=e.value},o="function"==typeof Symbol?Symbol:{},u=o.iterator||"@@iterator",a=o.asyncIterator||"@@asyncIterator",c=o.toStringTag||"@@toStringTag";function s(t,r,e){return Object.defineProperty(t,r,{value:e,enumerable:!0,configurable:!0,writable:!0}),t[r]}try{s({},"")}catch(t){s=function(t,r,e){return t[r]=e}}function f(t,r,e,n){var o=r&&r.prototype instanceof y?r:y,u=Object.create(o.prototype),a=new j(n||[]);return i(u,"_invoke",{value:R(t,e,a)}),u}function l(t,r,e){try{return{type:"normal",arg:t.call(r,e)}}catch(t){return{type:"throw",arg:t}}}t.wrap=f;var h="suspendedStart",p="suspendedYield",v="executing",g="completed",d={};function y(){}function m(){}function b(){}var x={};s(x,u,(function(){return this}));var w=Object.getPrototypeOf,E=w&&w(w(P([])));E&&E!==e&&n.call(E,u)&&(x=E);var S=b.prototype=y.prototype=Object.create(x);function A(t){["next","throw","return"].forEach((function(r){s(t,r,(function(t){return this._invoke(r,t)}))}))}function O(t,r){function e(i,o,u,a){var c=l(t[i],t,o);if("throw"!==c.type){var s=c.arg,f=s.value;return f&&"object"==typeof f&&n.call(f,"__await")?r.resolve(f.__await).then((function(t){e("next",t,u,a)}),(function(t){e("throw",t,u,a)})):r.resolve(f).then((function(t){s.value=t,u(s)}),(function(t){return e("throw",t,u,a)}))}a(c.arg)}var o;i(this,"_invoke",{value:function(t,n){function i(){return new r((function(r,i){e(t,n,r,i)}))}return o=o?o.then(i,i):i()}})}function R(t,r,e){var n=h;return function(i,o){if(n===v)throw new Error("Generator is already running");if(n===g){if("throw"===i)throw o;return k()}for(e.method=i,e.arg=o;;){var u=e.delegate;if(u){var a=T(u,e);if(a){if(a===d)continue;return a}}if("next"===e.method)e.sent=e._sent=e.arg;else if("throw"===e.method){if(n===h)throw n=g,e.arg;e.dispatchException(e.arg)}else"return"===e.method&&e.abrupt("return",e.arg);n=v;var c=l(t,r,e);if("normal"===c.type){if(n=e.done?g:p,c.arg===d)continue;return{value:c.arg,done:e.done}}"throw"===c.type&&(n=g,e.method="throw",e.arg=c.arg)}}}function T(t,e){var n=e.method,i=t.iterator[n];if(i===r)return e.delegate=null,"throw"===n&&t.iterator.return&&(e.method="return",e.arg=r,T(t,e),"throw"===e.method)||"return"!==n&&(e.method="throw",e.arg=new TypeError("The iterator does not provide a '"+n+"' method")),d;var o=l(i,t.iterator,e.arg);if("throw"===o.type)return e.method="throw",e.arg=o.arg,e.delegate=null,d;var u=o.arg;return u?u.done?(e[t.resultName]=u.value,e.next=t.nextLoc,"return"!==e.method&&(e.method="next",e.arg=r),e.delegate=null,d):u:(e.method="throw",e.arg=new TypeError("iterator result is not an object"),e.delegate=null,d)}function I(t){var r={tryLoc:t[0]};1 in t&&(r.catchLoc=t[1]),2 in t&&(r.finallyLoc=t[2],r.afterLoc=t[3]),this.tryEntries.push(r)}function M(t){var r=t.completion||{};r.type="normal",delete r.arg,t.completion=r}function j(t){this.tryEntries=[{tryLoc:"root"}],t.forEach(I,this),this.reset(!0)}function P(t){if(t){var e=t[u];if(e)return e.call(t);if("function"==typeof t.next)return t;if(!isNaN(t.length)){var i=-1,o=function e(){for(;++i<t.length;)if(n.call(t,i))return e.value=t[i],e.done=!1,e;return e.value=r,e.done=!0,e};return o.next=o}}return{next:k}}function k(){return{value:r,done:!0}}return m.prototype=b,i(S,"constructor",{value:b,configurable:!0}),i(b,"constructor",{value:m,configurable:!0}),m.displayName=s(b,c,"GeneratorFunction"),t.isGeneratorFunction=function(t){var r="function"==typeof t&&t.constructor;return!!r&&(r===m||"GeneratorFunction"===(r.displayName||r.name))},t.mark=function(t){return Object.setPrototypeOf?Object.setPrototypeOf(t,b):(t.__proto__=b,s(t,c,"GeneratorFunction")),t.prototype=Object.create(S),t},t.awrap=function(t){return{__await:t}},A(O.prototype),s(O.prototype,a,(function(){return this})),t.AsyncIterator=O,t.async=function(r,e,n,i,o){void 0===o&&(o=Promise);var u=new O(f(r,e,n,i),o);return t.isGeneratorFunction(e)?u:u.next().then((function(t){return t.done?t.value:u.next()}))},A(S),s(S,c,"Generator"),s(S,u,(function(){return this})),s(S,"toString",(function(){return"[object Generator]"})),t.keys=function(t){var r=Object(t),e=[];for(var n in r)e.push(n);return e.reverse(),function t(){for(;e.length;){var n=e.pop();if(n in r)return t.value=n,t.done=!1,t}return t.done=!0,t}},t.values=P,j.prototype={constructor:j,reset:function(t){if(this.prev=0,this.next=0,this.sent=this._sent=r,this.done=!1,this.delegate=null,this.method="next",this.arg=r,this.tryEntries.forEach(M),!t)for(var e in this)"t"===e.charAt(0)&&n.call(this,e)&&!isNaN(+e.slice(1))&&(this[e]=r)},stop:function(){this.done=!0;var t=this.tryEntries[0].completion;if("throw"===t.type)throw t.arg;return this.rval},dispatchException:function(t){if(this.done)throw t;var e=this;function i(n,i){return a.type="throw",a.arg=t,e.next=n,i&&(e.method="next",e.arg=r),!!i}for(var o=this.tryEntries.length-1;o>=0;--o){var u=this.tryEntries[o],aLine truncated
+!function(){var t={35666:function(t){var r=function(t){"use strict";var r,e=Object.prototype,n=e.hasOwnProperty,i=Object.defineProperty||function(t,r,e){t[r]=e.value},o="function"==typeof Symbol?Symbol:{},u=o.iterator||"@@iterator",a=o.asyncIterator||"@@asyncIterator",c=o.toStringTag||"@@toStringTag";function s(t,r,e){return Object.defineProperty(t,r,{value:e,enumerable:!0,configurable:!0,writable:!0}),t[r]}try{s({},"")}catch(t){s=function(t,r,e){return t[r]=e}}function f(t,r,e,n){var o=r&&r.prototype instanceof y?r:y,u=Object.create(o.prototype),a=new j(n||[]);return i(u,"_invoke",{value:R(t,e,a)}),u}function l(t,r,e){try{return{type:"normal",arg:t.call(r,e)}}catch(t){return{type:"throw",arg:t}}}t.wrap=f;var h="suspendedStart",p="suspendedYield",v="executing",g="completed",d={};function y(){}function m(){}function b(){}var x={};s(x,u,(function(){return this}));var w=Object.getPrototypeOf,E=w&&w(w(P([])));E&&E!==e&&n.call(E,u)&&(x=E);var S=b.prototype=y.prototype=Object.create(x);function A(t){["next","throw","return"].forEach((function(r){s(t,r,(function(t){return this._invoke(r,t)}))}))}function O(t,r){function e(i,o,u,a){var c=l(t[i],t,o);if("throw"!==c.type){var s=c.arg,f=s.value;return f&&"object"==typeof f&&n.call(f,"__await")?r.resolve(f.__await).then((function(t){e("next",t,u,a)}),(function(t){e("throw",t,u,a)})):r.resolve(f).then((function(t){s.value=t,u(s)}),(function(t){return e("throw",t,u,a)}))}a(c.arg)}var o;i(this,"_invoke",{value:function(t,n){function i(){return new r((function(r,i){e(t,n,r,i)}))}return o=o?o.then(i,i):i()}})}function R(t,r,e){var n=h;return function(i,o){if(n===v)throw new Error("Generator is already running");if(n===g){if("throw"===i)throw o;return k()}for(e.method=i,e.arg=o;;){var u=e.delegate;if(u){var a=T(u,e);if(a){if(a===d)continue;return a}}if("next"===e.method)e.sent=e._sent=e.arg;else if("throw"===e.method){if(n===h)throw n=g,e.arg;e.dispatchException(e.arg)}else"return"===e.method&&e.abrupt("return",e.arg);n=v;var c=l(t,r,e);if("normal"===c.type){if(n=e.done?g:p,c.arg===d)continue;return{value:c.arg,done:e.done}}"throw"===c.type&&(n=g,e.method="throw",e.arg=c.arg)}}}function T(t,e){var n=e.method,i=t.iterator[n];if(i===r)return e.delegate=null,"throw"===n&&t.iterator.return&&(e.method="return",e.arg=r,T(t,e),"throw"===e.method)||"return"!==n&&(e.method="throw",e.arg=new TypeError("The iterator does not provide a '"+n+"' method")),d;var o=l(i,t.iterator,e.arg);if("throw"===o.type)return e.method="throw",e.arg=o.arg,e.delegate=null,d;var u=o.arg;return u?u.done?(e[t.resultName]=u.value,e.next=t.nextLoc,"return"!==e.method&&(e.method="next",e.arg=r),e.delegate=null,d):u:(e.method="throw",e.arg=new TypeError("iterator result is not an object"),e.delegate=null,d)}function I(t){var r={tryLoc:t[0]};1 in t&&(r.catchLoc=t[1]),2 in t&&(r.finallyLoc=t[2],r.afterLoc=t[3]),this.tryEntries.push(r)}function M(t){var r=t.completion||{};r.type="normal",delete r.arg,t.completion=r}function j(t){this.tryEntries=[{tryLoc:"root"}],t.forEach(I,this),this.reset(!0)}function P(t){if(t){var e=t[u];if(e)return e.call(t);if("function"==typeof t.next)return t;if(!isNaN(t.length)){var i=-1,o=function e(){for(;++i<t.length;)if(n.call(t,i))return e.value=t[i],e.done=!1,e;return e.value=r,e.done=!0,e};return o.next=o}}return{next:k}}function k(){return{value:r,done:!0}}return m.prototype=b,i(S,"constructor",{value:b,configurable:!0}),i(b,"constructor",{value:m,configurable:!0}),m.displayName=s(b,c,"GeneratorFunction"),t.isGeneratorFunction=function(t){var r="function"==typeof t&&t.constructor;return!!r&&(r===m||"GeneratorFunction"===(r.displayName||r.name))},t.mark=function(t){return Object.setPrototypeOf?Object.setPrototypeOf(t,b):(t.__proto__=b,s(t,c,"GeneratorFunction")),t.prototype=Object.create(S),t},t.awrap=function(t){return{__await:t}},A(O.prototype),s(O.prototype,a,(function(){return this})),t.AsyncIterator=O,t.async=function(r,e,n,i,o){void 0===o&&(o=Promise);var u=new O(f(r,e,n,i),o);return t.isGeneratorFunction(e)?u:u.next().then((function(t){return t.done?t.value:u.next()}))},A(S),s(S,c,"Generator"),s(S,u,(function(){return this})),s(S,"toString",(function(){return"[object Generator]"})),t.keys=function(t){var r=Object(t),e=[];for(var n in r)e.push(n);return e.reverse(),function t(){for(;e.length;){var n=e.pop();if(n in r)return t.value=n,t.done=!1,t}return t.done=!0,t}},t.values=P,j.prototype={constructor:j,reset:function(t){if(this.prev=0,this.next=0,this.sent=this._sent=r,this.done=!1,this.delegate=null,this.method="next",this.arg=r,this.tryEntries.forEach(M),!t)for(var e in this)"t"===e.charAt(0)&&n.call(this,e)&&!isNaN(+e.slice(1))&&(this[e]=r)},stop:function(){this.done=!0;var t=this.tryEntries[0].completion;if("throw"===t.type)throw t.arg;return this.rval},dispatchException:function(t){if(this.done)throw t;var e=this;function i(n,i){return a.type="throw",a.arg=t,e.next=n,i&&(e.method="next",e.arg=r),!!i}for(var o=this.tryEntries.length-1;o>=0;--o){var u=this.tryEntries[o],aLine truncated
 //# sourceMappingURL=polyfill.js.map

system/word_addin/taskpane.js

@@ -1,3 +1,3 @@
-/*! For license information please see taskpane.js.LICENSE.txt */
-!function(){var t={27091:function(t){"use strict";t.exports=function(t,e){return e||(e={}),t?(t=String(t.__esModule?t.default:t),e.hash&&(t+=e.hash),e.maybeNeedQuotes&&/[\t\n\f\r "'=<>`]/.test(t)?'"'.concat(t,'"'):t):t}},44944:function(t,e,r){"use strict";t.exports=r.p+"assets/logo-filled.png"},36076:function(t,e,r){"use strict";t.exports=r.p+"1995fcd6d39cade7d871.js"},60806:function(t,e,r){"use strict";t.exports=r.p+"1fda685b81e1123773f6.css"}},e={};function r(n){var o=e[n];if(void 0!==o)return o.exports;var i=e[n]={exports:{}};return t[n](i,i.exports,r),i.exports}r.m=t,r.n=function(t){var e=t&&t.__esModule?function(){return t.default}:function(){return t};return r.d(e,{a:e}),e},r.d=function(t,e){for(var n in e)r.o(e,n)&&!r.o(t,n)&&Object.defineProperty(t,n,{enumerable:!0,get:e[n]})},r.g=function(){if("object"==typeof globalThis)return globalThis;try{return this||new Function("return this")()}catch(t){if("object"==typeof window)return window}}(),r.o=function(t,e){return Object.prototype.hasOwnProperty.call(t,e)},function(){var t;r.g.importScripts&&(t=r.g.location+"");var e=r.g.document;if(!t&&e&&(e.currentScript&&(t=e.currentScript.src),!t)){var n=e.getElementsByTagName("script");if(n.length)for(var o=n.length-1;o>-1&&!t;)t=n[o--].src}if(!t)throw new Error("Automatic publicPath is not supported in this browser");t=t.replace(/#.*$/,"").replace(/\?.*$/,"").replace(/\/[^\/]+$/,"/"),r.p=t}(),r.b=document.baseURI||self.location.href,function(){function t(e){return t="function"==typeof Symbol&&"symbol"==typeof Symbol.iterator?function(t){return typeof t}:function(t){return t&&"function"==typeof Symbol&&t.constructor===Symbol&&t!==Symbol.prototype?"symbol":typeof t},t(e)}function e(){"use strict";e=function(){return n};var r,n={},o=Object.prototype,i=o.hasOwnProperty,c=Object.defineProperty||function(t,e,r){t[e]=r.value},a="function"==typeof Symbol?Symbol:{},u=a.iterator||"@@iterator",f=a.asyncIterator||"@@asyncIterator",s=a.toStringTag||"@@toStringTag";function l(t,e,r){return Object.defineProperty(t,e,{value:r,enumerable:!0,configurable:!0,writable:!0}),t[e]}try{l({},"")}catch(r){l=function(t,e,r){return t[e]=r}}function h(t,e,r,n){var o=e&&e.prototype instanceof w?e:w,i=Object.create(o.prototype),a=new k(n||[]);return c(i,"_invoke",{value:I(t,r,a)}),i}function p(t,e,r){try{return{type:"normal",arg:t.call(e,r)}}catch(t){return{type:"throw",arg:t}}}n.wrap=h;var y="suspendedStart",v="suspendedYield",d="executing",m="completed",g={};function w(){}function b(){}function x(){}var E={};l(E,u,(function(){return this}));var L=Object.getPrototypeOf,_=L&&L(L(T([])));_&&_!==o&&i.call(_,u)&&(E=_);var j=x.prototype=w.prototype=Object.create(E);function O(t){["next","throw","return"].forEach((function(e){l(t,e,(function(t){return this._invoke(e,t)}))}))}function S(e,r){function n(o,c,a,u){var f=p(e[o],e,c);if("throw"!==f.type){var s=f.arg,l=s.value;return l&&"object"==t(l)&&i.call(l,"__await")?r.resolve(l.__await).then((function(t){n("next",t,a,u)}),(function(t){n("throw",t,a,u)})):r.resolve(l).then((function(t){s.value=t,a(s)}),(function(t){return n("throw",t,a,u)}))}u(f.arg)}var o;c(this,"_invoke",{value:function(t,e){function i(){return new r((function(r,o){n(t,e,r,o)}))}return o=o?o.then(i,i):i()}})}function I(t,e,n){var o=y;return function(i,c){if(o===d)throw new Error("Generator is already running");if(o===m){if("throw"===i)throw c;return{value:r,done:!0}}for(n.method=i,n.arg=c;;){var a=n.delegate;if(a){var u=P(a,n);if(u){if(u===g)continue;return u}}if("next"===n.method)n.sent=n._sent=n.arg;else if("throw"===n.method){if(o===y)throw o=m,n.arg;n.dispatchException(n.arg)}else"return"===n.method&&n.abrupt("return",n.arg);o=d;var f=p(t,e,n);if("normal"===f.type){if(o=n.done?m:v,f.arg===g)continue;return{value:f.arg,done:n.done}}"throw"===f.type&&(o=m,n.method="throw",n.arg=f.arg)}}}function P(t,e){var n=e.method,o=t.iterator[n];if(o===r)return e.delegate=null,"throw"===n&&t.iterator.return&&(e.method="return",e.arg=r,P(t,e),"throw"===e.method)||"return"!==n&&(e.method="throw",e.arg=new TypeError("The iterator does not provide a '"+n+"' method")),g;var i=p(o,t.iterator,e.arg);if("throw"===i.type)return e.method="throw",e.arg=i.arg,e.delegate=null,g;var c=i.arg;return c?c.done?(e[t.resultName]=c.value,e.next=t.nextLoc,"return"!==e.method&&(e.method="next",e.arg=r),e.delegate=null,g):c:(e.method="throw",e.arg=new TypeError("iterator result is not an object"),e.delegate=null,g)}function B(t){var e={tryLoc:t[0]};1 in t&&(e.catchLoc=t[1]),2 in t&&(e.finallyLoc=t[2],e.afterLoc=t[3]),this.tryEntries.push(e)}function N(t){var e=t.completion||{};e.type="normal",delete e.arg,t.completion=e}function k(t){this.tryEntries=[{tryLoc:"root"}],t.forEach(B,this),this.reset(!0)}function T(e){if(e||""===e){var n=e[u];if(n)return n.call(e);if("function"==typeof e.next)return e;if(!isNaN(e.length)){var o=-1,c=function t(){for(;++o<e.length;)if(i.call(e,o))return t.value=e[o],t.done=!1,t;return t.value=r,t.done=!0,t};return c.next=c}}throw new TLine truncated
+/*! For license information please see taskpane.js.LICENSE.txt */
+!function(){var t={27091:function(t){"use strict";t.exports=function(t,e){return e||(e={}),t?(t=String(t.__esModule?t.default:t),e.hash&&(t+=e.hash),e.maybeNeedQuotes&&/[\t\n\f\r "'=<>`]/.test(t)?'"'.concat(t,'"'):t):t}},44944:function(t,e,r){"use strict";t.exports=r.p+"assets/logo-filled.png"},36076:function(t,e,r){"use strict";t.exports=r.p+"1995fcd6d39cade7d871.js"},60806:function(t,e,r){"use strict";t.exports=r.p+"1fda685b81e1123773f6.css"}},e={};function r(n){var o=e[n];if(void 0!==o)return o.exports;var i=e[n]={exports:{}};return t[n](i,i.exports,r),i.exports}r.m=t,r.n=function(t){var e=t&&t.__esModule?function(){return t.default}:function(){return t};return r.d(e,{a:e}),e},r.d=function(t,e){for(var n in e)r.o(e,n)&&!r.o(t,n)&&Object.defineProperty(t,n,{enumerable:!0,get:e[n]})},r.g=function(){if("object"==typeof globalThis)return globalThis;try{return this||new Function("return this")()}catch(t){if("object"==typeof window)return window}}(),r.o=function(t,e){return Object.prototype.hasOwnProperty.call(t,e)},function(){var t;r.g.importScripts&&(t=r.g.location+"");var e=r.g.document;if(!t&&e&&(e.currentScript&&(t=e.currentScript.src),!t)){var n=e.getElementsByTagName("script");if(n.length)for(var o=n.length-1;o>-1&&!t;)t=n[o--].src}if(!t)throw new Error("Automatic publicPath is not supported in this browser");t=t.replace(/#.*$/,"").replace(/\?.*$/,"").replace(/\/[^\/]+$/,"/"),r.p=t}(),r.b=document.baseURI||self.location.href,function(){function t(e){return t="function"==typeof Symbol&&"symbol"==typeof Symbol.iterator?function(t){return typeof t}:function(t){return t&&"function"==typeof Symbol&&t.constructor===Symbol&&t!==Symbol.prototype?"symbol":typeof t},t(e)}function e(){"use strict";e=function(){return n};var r,n={},o=Object.prototype,i=o.hasOwnProperty,c=Object.defineProperty||function(t,e,r){t[e]=r.value},a="function"==typeof Symbol?Symbol:{},u=a.iterator||"@@iterator",f=a.asyncIterator||"@@asyncIterator",s=a.toStringTag||"@@toStringTag";function l(t,e,r){return Object.defineProperty(t,e,{value:r,enumerable:!0,configurable:!0,writable:!0}),t[e]}try{l({},"")}catch(r){l=function(t,e,r){return t[e]=r}}function h(t,e,r,n){var o=e&&e.prototype instanceof w?e:w,i=Object.create(o.prototype),a=new k(n||[]);return c(i,"_invoke",{value:I(t,r,a)}),i}function p(t,e,r){try{return{type:"normal",arg:t.call(e,r)}}catch(t){return{type:"throw",arg:t}}}n.wrap=h;var y="suspendedStart",v="suspendedYield",d="executing",m="completed",g={};function w(){}function b(){}function x(){}var E={};l(E,u,(function(){return this}));var L=Object.getPrototypeOf,_=L&&L(L(T([])));_&&_!==o&&i.call(_,u)&&(E=_);var j=x.prototype=w.prototype=Object.create(E);function O(t){["next","throw","return"].forEach((function(e){l(t,e,(function(t){return this._invoke(e,t)}))}))}function S(e,r){function n(o,c,a,u){var f=p(e[o],e,c);if("throw"!==f.type){var s=f.arg,l=s.value;return l&&"object"==t(l)&&i.call(l,"__await")?r.resolve(l.__await).then((function(t){n("next",t,a,u)}),(function(t){n("throw",t,a,u)})):r.resolve(l).then((function(t){s.value=t,a(s)}),(function(t){return n("throw",t,a,u)}))}u(f.arg)}var o;c(this,"_invoke",{value:function(t,e){function i(){return new r((function(r,o){n(t,e,r,o)}))}return o=o?o.then(i,i):i()}})}function I(t,e,n){var o=y;return function(i,c){if(o===d)throw new Error("Generator is already running");if(o===m){if("throw"===i)throw c;return{value:r,done:!0}}for(n.method=i,n.arg=c;;){var a=n.delegate;if(a){var u=P(a,n);if(u){if(u===g)continue;return u}}if("next"===n.method)n.sent=n._sent=n.arg;else if("throw"===n.method){if(o===y)throw o=m,n.arg;n.dispatchException(n.arg)}else"return"===n.method&&n.abrupt("return",n.arg);o=d;var f=p(t,e,n);if("normal"===f.type){if(o=n.done?m:v,f.arg===g)continue;return{value:f.arg,done:n.done}}"throw"===f.type&&(o=m,n.method="throw",n.arg=f.arg)}}}function P(t,e){var n=e.method,o=t.iterator[n];if(o===r)return e.delegate=null,"throw"===n&&t.iterator.return&&(e.method="return",e.arg=r,P(t,e),"throw"===e.method)||"return"!==n&&(e.method="throw",e.arg=new TypeError("The iterator does not provide a '"+n+"' method")),g;var i=p(o,t.iterator,e.arg);if("throw"===i.type)return e.method="throw",e.arg=i.arg,e.delegate=null,g;var c=i.arg;return c?c.done?(e[t.resultName]=c.value,e.next=t.nextLoc,"return"!==e.method&&(e.method="next",e.arg=r),e.delegate=null,g):c:(e.method="throw",e.arg=new TypeError("iterator result is not an object"),e.delegate=null,g)}function B(t){var e={tryLoc:t[0]};1 in t&&(e.catchLoc=t[1]),2 in t&&(e.finallyLoc=t[2],e.afterLoc=t[3]),this.tryEntries.push(e)}function N(t){var e=t.completion||{};e.type="normal",delete e.arg,t.completion=e}function k(t){this.tryEntries=[{tryLoc:"root"}],t.forEach(B,this),this.reset(!0)}function T(e){if(e||""===e){var n=e[u];if(n)return n.call(e);if("function"==typeof e.next)return e;if(!isNaN(e.length)){var o=-1,c=function t(){for(;++o<e.length;)if(i.call(e,o))return t.value=e[o],t.done=!1,t;return t.value=r,t.done=!0,t};return c.next=c}}throw new TLine truncated
 //# sourceMappingURL=taskpane.js.map

system/word_addin/taskpane.js.LICENSE.txt

@@ -1 +1 @@
-/*! regenerator-runtime -- Copyright (c) 2014-present, Facebook, Inc. -- license (MIT): https://github.com/facebook/regenerator/blob/main/LICENSE */
+/*! regenerator-runtime -- Copyright (c) 2014-present, Facebook, Inc. -- license (MIT): https://github.com/facebook/regenerator/blob/main/LICENSE */

templates/tts_chunk_player/crunker.esm.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"crunker.esm.js","mappings":"AACA,IAAIA,EAAsB,CCA1BA,EAAwB,CAACC,EAASC,KACjC,IAAI,IAAIC,KAAOD,EACXF,EAAoBI,EAAEF,EAAYC,KAASH,EAAoBI,EAAEH,EAASE,IAC5EE,OAAOC,eAAeL,EAASE,EAAK,CAAEI,YAAY,EAAMC,IAAKN,EAAWC,IAE1E,ECNDH,EAAwB,CAACS,EAAKC,IAAUL,OAAOM,UAAUC,eAAeC,KAAKJ,EAAKC,I,8jDCoBlF,IAGqBI,EAAO,WAU1B,aAAqE,6DAAJ,CAAC,EAApDC,EAAU,EAAVA,WAAU,UACtBC,KAAKC,SAAWD,KAAKE,eAAeH,GAEpCA,IAAAA,EAAeC,KAAKC,SAASF,YAE7BC,KAAKG,YAAcJ,CACrB,C,UA6YC,O,EA3YD,E,EAAA,6BAKA,WAAkE,IAA3CA,EAAqB,UAAH,6CAAG,MAE1C,OADAK,OAAOC,aAAeD,OAAOC,cAAiBD,OAAeE,oBAAuBF,OAAeG,gBAC5F,IAAIF,aAAa,CAAEN,WAAAA,GAC5B,GAEA,mBAIA,WACE,OAAOC,KAAKC,QACd,GAEA,wBAGAO,iBAA4E,kCAAxDC,EAAS,yBAATA,EAAS,gBAC3B,aAAaC,QAAQC,IACnBF,EAAUG,KAAIJ,eAAOK,GACnB,IAAIC,EAkBJ,OAfEA,EADED,aAAoBE,MAAQF,aAAoBG,WACnCH,EAASI,oBAETC,MAAML,GAAUM,MAAK,SAACC,GASnC,OARIA,EAASC,QAAQC,IAAI,kBAAoBF,EAASC,QAAQ7B,IAAI,gBAAiB+B,SAAS,WAC1FC,QAAQC,KAAK,oEAAD,OAERL,EAASC,QAAQ7B,IAAI,gBAAiBkC,MAAM,KAAK,GAAE,sDACPb,EAAQ,OAInDO,EAASH,aAClB,UAGW,EAAKhB,SAAS0B,gBAAgBb,EAC7C,IAEJ,GAEA,wBAOA,SAAWc,GACT,IAAMC,EAAS7B,KAAKC,SAAS6B,aAC3B9B,KAAK+B,qBAAqBH,GAC1B5B,KAAKG,YAAcH,KAAKgC,aAAaJ,GACrC5B,KAAKG,aAgBP,OAbAyB,EAAQK,SAAQ,SAACnB,GACf,IAAK,IAAIoB,EAAgB,EAAGA,EAAgBpB,EAAOqB,iBAAkBD,IAAiB,CAIpF,IAHA,IAAME,EAAaP,EAAOQ,eAAeH,GACnCI,EAAaxB,EAAOuB,eAAeH,GAEhCK,EAAIzB,EAAOuB,eAAeH,GAAeM,OAAS,EAAGD,GAAK,EAAGA,IACpEH,EAAWG,IAAMD,EAAWC,GAG9BV,EAAOQ,eAAeH,GAAeO,IAAIL,EAC3C,CACF,IAEOP,CACT,GAEA,yBAOA,SAAYD,GACV,IAAMC,EAAS7B,KAAKC,SAAS6B,aAC3B9B,KAAK+B,qBAAqBH,GAC1B5B,KAAK0C,aAAad,GAClB5B,KAAKG,aAEHwC,EAAS,EAUb,OARAf,EAAQK,SAAQ,SAACnB,GACf,IAAK,IAAIoB,EAAgB,EAAGA,EAAgBpB,EAAOqB,iBAAkBD,IACnEL,EAAOQ,eAAeH,GAAeO,IAAI3B,EAAOuB,eAAeH,GAAgBS,GAGjFA,GAAU7B,EAAO0B,MACnB,IAEOX,CACT,GAEA,sBAUA,SAASf,GAA6E,IAAxD8B,EAAmB,UAAH,6CAAG,EAAGC,EAAkB,UAAH,6CAAG,EACpE,GAAgB,IAAZA,EAAe,OAAO/B,EAE1B,GAAI8B,EAAW,EAAG,MAAM,IAAIE,MAAM,8DAClC,GAAID,EAAU,EAAG,MAAM,IAAIC,MAAM,6DAQjC,IANA,IAAMC,EAAgB/C,KAAKC,SAAS6B,aAClChB,EAAOqB,iBACPa,KAAKC,KAAKnC,EAAO0B,OAASK,EAAU/B,EAAOf,YAC3Ce,EAAOf,YAGAmC,EAAgB,EAAGA,EAAgBpB,EAAOqB,iBAAkBD,IAAiB,CACpF,IAAMgB,EAAcpC,EAAOuB,eAAeH,GAC1Ca,EACGV,eAAeH,GACfO,IAAIS,EAAYC,SAAS,EAAGH,KAAKC,KAAKL,EAAW9B,EAAOf,YAAc,GAAI,GAE7EgD,EACGV,eAAeH,GACfO,IACCS,EAAYC,SAASH,KAAKC,KAAKL,EAAW9B,EAAOf,YAAc,EAAGgD,EAAcP,OAAS,GACzFQ,KAAKC,MAAML,EAAWC,GAAW/B,EAAOf,YAE9C,CAEA,OAAOgD,CACT,GAEA,wBASA,SAAWjC,EAAqBsC,EAAeC,GAAmE,IAAtDC,EAAiB,UAAH,6CAAG,EAAGC,EAAkB,UAAH,6CAAG,EAChG,GAAIH,GAASC,EAAK,MAAM,IAAIP,MAAM,6EAMlC,IAJA,IAAMN,EAASQ,KAAKQ,OAAOH,EAAMD,GAASpD,KAAKG,aACzCwC,EAASK,KAAKQ,MAAMJ,EAAQpD,KAAKG,aACjCsD,EAAYzD,KAAKC,SAAS6B,aAAahB,EAAOqB,iBAAkBK,EAAQxC,KAAKG,aAE1EuD,EAAU,EAAGA,EAAU5C,EAAOqB,iBAAkBuB,IAIvD,IAHA,IAAMC,EAAY7C,EAAOuB,eAAeqB,GAClCtB,EAAaqB,EAAUpB,eAAeqB,GAEnCnB,EAAI,EAAGA,EAAIC,EAAQD,IAC1BH,EAAWG,GAAKoB,EAAUhB,EAASJ,GAG/BA,EAAIe,EAAStD,KAAKG,cACpBiC,EAAWG,IAAMA,GAAKe,EAAStD,KAAKG,cAIlCoC,EAAIC,EAASe,EAAUvD,KAAKG,cAC9BiC,EAAWG,KAAOC,EAASD,IAAMgB,EAAUvD,KAAKG,cAKtD,OAAOsD,CACT,GAEA,kBAGA,SAAK3C,GACH,IAAM8C,EAAS5D,KAAKC,SAAS4D,qBAM7B,OAJAD,EAAO9C,OAASA,EAChB8C,EAAOE,QAAQ9D,KAAKC,SAAS8D,aAC7BH,EAAOR,QAEAQ,CACT,GAEA,oBAUA,SAAO9C,GAAuE,IAAlDkD,EAAe,UAAH,6CAAG,YACnCC,EAAWjE,KAAKkE,YAAYpD,GAC5BqD,EAAWnE,KAAKoE,cAAcH,EAAUnD,EAAOqB,iBAAkBrB,EAAOf,YACxEsE,EAAY,IAAIrD,KAAK,CAACmD,GAAW,CAAEH,KAAAA,IAEzC,MAAO,CACLM,KAAMD,EACNE,IAAKvE,KAAKwE,WAAWH,GACrBI,QAASzE,KAAK0E,oBAAoBL,GAEtC,GAEA,sBAMA,SAASC,GAA6D,IAAjDK,EAAmB,UAAH,6CAAG,UAChCC,EAAIC,SAASC,cAAc,KAOjC,OALAF,EAAEG,MAAMC,QAAU,OAClBJ,EAAEK,KAAOjF,KAAKwE,WAAWF,GACzBM,EAAEM,SAAW,GAAH,OAAMP,EAAQ,YAAIL,EAAKN,KAAKtC,MAAM,KAAK,IACjDkD,EAAEO,QAEKP,CACT,GAEA,0BAOA,SAAgBQ,GACd,OAAOpF,KAAKqF,oBAAiBC,EAAYF,GAC3C,GAEA,mBAGA,WAEE,OADApF,KAAKC,SAASsF,QACPvF,IACT,GAEA,0BAKA,SAAqB4B,GACnB,OAAOoB,KAAKwC,IAAG,MAARxC,KAAI,EAAQpB,EAAQhB,KAAI,SAACE,GAAM,OAAKA,EAAO2E,QAAQ,KAC5D,GAEA,kCAKA,SAA6B7D,GAC3B,OAAOoB,KAAKwC,IAAG,MAARxC,KAAI,EAAQpB,EAAQhB,KAAI,SAACE,GAAM,OAAKA,EAAOqB,gBAAgB,KACpE,GAEA,0BAKA,SAAqBP,GACnB,OAAOA,EAAQhB,KAAI,SAACE,GAAM,OAAKA,EAAO0B,MAAM,IAAEkD,QAAO,SAACd,EAAGe,GAAC,OAAKf,EAAIe,CAAC,GAAE,EACxE,GAEA,0BAKA,WACE,MAAO,iBAAkBvF,QAAU,uBAAwBA,QAAU,oBAAqBA,MAC5F,GAEA,2BAOA,SAAsBU,EAAsB8E,EAAuB7F,GACjE,IAEM8F,EADiBC,EACJF,EAIbG,EALiBD,EAKDhF,EAAO0B,OACvBwD,EAFkB,GAEiBD,EAEnC9E,EAAc,IAAIgF,YALD,EAK8BD,GAC/CE,EAAO,IAAIC,SAASlF,GAgB1B,OAdAjB,KAAKoG,aAAaF,EAAM,EAAG,QAC3BA,EAAKG,UAAU,EAAGL,GAAgB,GAClChG,KAAKoG,aAAaF,EAAM,EAAG,QAC3BlG,KAAKoG,aAAaF,EAAM,GAAI,QAC5BA,EAAKG,UAAU,GAAI,IAAI,GACvBH,EAAKI,UAAU,GAAI,GAAG,GACtBJ,EAAKI,UAAU,GAAIV,GAAe,GAClCM,EAAKG,UAAU,GAAItG,GAAY,GAC/BmG,EAAKG,UAAU,GAAItG,EAAa8F,GAAY,GAC5CK,EAAKI,UAAU,GAAIT,GAAY,GAC/BK,EAAKI,UAAU,GAtBE,IAsBY,GAC7BtG,KAAKoG,aAAaF,EAAM,GAAI,QAC5BA,EAAKG,UAAU,GAAIN,GAAe,GAE3B/F,KAAKuG,iBAAiBL,EAAMpF,EAAQ0F,GAC7C,GAEA,8BAKA,SAAyBrC,EAAoBrD,EAAsB6B,GACjE,IAAK,IAAIJ,EAAI,EAAGA,EAAIzB,EAAO0B,OAAQD,IAAKI,GAAU,EAAG,CACnD,IAAM8D,EAAMzD,KAAKwC,KAAK,EAAGxC,KAAK0D,IAAI,EAAG5F,EAAOyB,KAC5C4B,EAASwC,SAAShE,EAAQ8D,EAAM,EAAU,MAANA,EAAqB,MAANA,GAAc,EACnE,CAEA,OAAOtC,CACT,GAEA,0BAKA,SAAqBA,EAAoBxB,EAAgBiE,GACvD,IAAK,IAAIrE,EAAI,EAAGA,EAALine truncated

tts_server.py

@@ -8,7 +8,8 @@ from TTS.tts.configs.xtts_config import XttsConfig
 from TTS.tts.models.xtts import Xtts
 import io
 import wave
-
+import logging
+logging.disable(logging.WARNING)
 ##########################
 #### Webserver Imports####
 ##########################
@@ -19,6 +20,7 @@ from fastapi import (
     Response,
     Depends,
     HTTPException,
+    Query,
 )
 from fastapi.responses import JSONResponse, HTMLResponse, RedirectResponse, FileResponse, StreamingResponse
 from fastapi.middleware.cors import CORSMiddleware
@@ -34,7 +36,7 @@ this_dir = Path(__file__).parent.resolve()
 # STARTUP VARIABLE - Set "device" to cuda if exists, otherwise cpu
 device = "cuda" if torch.cuda.is_available() else "cpu"
 # STARTUP VARIABLE - Import languges file for Gradio to be able to display them in the interface
-with open(this_dir / "languages.json", encoding="utf8") as f:
+with open(this_dir / "system" / "config" / "languages.json", encoding="utf8") as f:
     languages = json.load(f)
 # Base setting for a possible FineTuned model existing and the loader being available
 tts_method_xtts_ft = False
@@ -119,12 +121,6 @@ try:
     deepspeed_available = True
 except ImportError:
     pass
-if deepspeed_available:
-    print(f"[{params['branding']}Startup] DeepSpeed \033[93mDetected\033[0m")
-    print(f"[{params['branding']}Startup] Activate DeepSpeed in {params['branding']}settings")
-else:
-    print(f"[{params['branding']}Startup] DeepSpeed \033[93mNot Detected\033[0m. See https://github.com/microsoft/DeepSpeed")
-
 
 @asynccontextmanager
 async def startup_shutdown(no_actual_value_it_demanded_something_be_here):
@@ -186,9 +182,8 @@ async def setup():
     # Calculate start time minus end time
     generate_elapsed_time = generate_end_time - generate_start_time
     # Print out the result of the load time
-    print(
-        f"[{params['branding']}Model] \033[94mModel Loaded in \033[93m{generate_elapsed_time:.2f} seconds.\033[0m"
-    )
+    print(f"[{params['branding']}Model] \033[94mModel Loaded in \033[93m{generate_elapsed_time:.2f} seconds.\033[0m")
+    print(f"[{params['branding']}Model] Ready")
     # Set "tts_model_loaded" to true
     params["tts_model_loaded"] = True
     # Set the output path for wav files
@@ -222,6 +217,8 @@ async def api_manual_load_model():
             model_path=modeldownload_base_path / modeldownload_model_path,
             config_path=modeldownload_base_path / modeldownload_model_path / "config.json",
         ).to(device)
+        print(f"[{params['branding']}Model] \033[94mCoqui Public Model License\033[0m")
+        print(f"[{params['branding']}Model] \033[94mhttps://coqui.ai/cpml.txt\033[0m")
     return model
 
 
@@ -251,6 +248,8 @@ async def xtts_manual_load_model():
         use_deepspeed=params["deepspeed_activate"],
     )
     model.to(device)
+    print(f"[{params['branding']}Model] \033[94mCoqui Public Model License\033[0m")
+    print(f"[{params['branding']}Model] \033[94mhttps://coqui.ai/cpml.txt\033[0m")
     return model
 
 # MODEL LOADER For "XTTSv2 FT"
@@ -269,6 +268,8 @@ async def xtts_ft_manual_load_model():
         use_deepspeed=params["deepspeed_activate"],
     )
     model.to(device)
+    print(f"[{params['branding']}Model] \033[94mCoqui Public Model License\033[0m")
+    print(f"[{params['branding']}Model] \033[94mhttps://coqui.ai/cpml.txt\033[0m")
     return model
 
 # MODEL UNLOADER
@@ -475,6 +476,11 @@ async def deepspeed(request: Request, new_deepspeed_value: bool):
 ########################
 #### TTS GENERATION ####
 ########################
+debug_generate_audio = False
+tts_stop_generation = False # Called to stop generation of the current text at whatever stage its at. currently only set for streaming.
+tts_generation_lock = False # Tracks locking of the generaetion process.
+tts_narrator_generatingtts = False # Tracks if the current tts processes are narrator based, to avoid moving model on each chunk of text generated.
+# Not in use tts_queue_behaviour = False # True is to queue the current generation request. False is to cancel the current generation and start a new one.
 
 # TTS VOICE GENERATION METHODS (called from voice_preview and output_modifer)
 async def generate_audio(text, voice, language, temperature, repetition_penalty, output_file, streaming=False):
@@ -485,9 +491,11 @@ async def generate_audio(text, voice, language, temperature, repetition_penalty,
         return response
     async for _ in response:
         pass
-    
+
+
 async def generate_audio_internal(text, voice, language, temperature, repetition_penalty, output_file, streaming):
-    global model
+    global model, tts_stop_generation, tts_generation_lock
+    tts_generation_lock = True
     if params["low_vram"] and device == "cpu":
         await switch_device()
     generate_start_time = time.time()  # Record the start time of generating TTS
@@ -538,6 +546,12 @@ async def generate_audio_internal(text, voice, language, temperature, repetition
             yield wav_buf.read()
 
             for i, chunk in enumerate(output):
+                if tts_stop_generation:
+                    print(f"[{params['branding']}TTSGen] Stopping audio generation.")
+                    file_chunks.clear()  # Clear the file_chunks list
+                    tts_stop_generation = False
+                    tts_generation_lock = False
+                    break
                 file_chunks.append(chunk)
                 if isinstance(chunk, list):
                     chunk = torch.cat(chunk, dim=0)
@@ -546,6 +560,7 @@ async def generate_audio_internal(text, voice, language, temperature, repetition
                 chunk = np.clip(chunk, -1, 1)
                 chunk = (chunk * 32767).astype(np.int16)
                 yield chunk.tobytes()
+                print(f"[{params['branding']}Debug] Stream audio generation: Yielded audio chunk {i}.") if debug_generate_audio else None   
         else:
             # Non-streaming-specific operation
             torchaudio.save(output_file, torch.tensor(output["wav"]).unsqueeze(0), 24000)
@@ -564,9 +579,9 @@ async def generate_audio_internal(text, voice, language, temperature, repetition
             file_path=output_file,
             speaker_wav=[f"{this_dir}/voices/{voice}"],
             language=language,
-            temperature=temperature,
-            length_penalty=model.config.length_penalty,
-            repetition_penalty=repetition_penalty,
+            temperature=float(temperature),
+            length_penalty=float(model.config.length_penalty),
+            repetition_penalty=float(repetition_penalty),
             top_k=model.config.top_k,
             top_p=model.config.top_p,
         )
@@ -588,12 +603,11 @@ async def generate_audio_internal(text, voice, language, temperature, repetition
     # Print Generation time and settings
     generate_end_time = time.time()  # Record the end time to generate TTS
     generate_elapsed_time = generate_end_time - generate_start_time
-    print(
-        f"[{params['branding']}TTSGen] \033[93m{generate_elapsed_time:.2f} seconds. \033[94mLowVRAM: \033[33m{params['low_vram']} \033[94mDeepSpeed: \033[33m{params['deepspeed_activate']}\033[0m"
-    )
+    print(f"[{params['branding']}TTSGen] \033[93m{generate_elapsed_time:.2f} seconds. \033[94mLowVRAM: \033[33m{params['low_vram']} \033[94mDeepSpeed: \033[33m{params['deepspeed_activate']}\033[0m")
     # Move model back to cpu system ram if needed.
-    if params["low_vram"] and device == "cuda":
+    if params["low_vram"] and device == "cuda" and tts_narrator_generatingtts == False:
         await switch_device()
+    tts_generation_lock = False
     return
 
 
@@ -638,7 +652,7 @@ def list_files(directory):
 #############################
 
 # Create an instance of Jinja2Templates for rendering HTML templates
-templates = Jinja2Templates(directory=this_dir / "templates")
+templates = Jinja2Templates(directory=this_dir / "system")
 
 # Create a dependency to get the current JSON data
 def get_json_data():
@@ -653,7 +667,7 @@ async def get_settings(request: Request):
     wav_files = list_files(this_dir / "voices")
     # Render the template with the current JSON data and list of WAV files
     return templates.TemplateResponse(
-        "generate_form.html",
+        "/at_admin/at_settings.html",
         {
             "request": request,
             "data": get_json_data(),
@@ -663,7 +677,7 @@ async def get_settings(request: Request):
     )
 
 # Define an endpoint to serve static files
-app.mount("/static", StaticFiles(directory=str(this_dir / "templates")), name="static")
+app.mount("/static", StaticFiles(directory=str(this_dir / "system")), name="static")
 
 @app.post("/update-settings")
 async def update_settings(
@@ -853,6 +867,13 @@ async def tts_generate_streaming(request: Request, text: str = Form(...), voice:
         print(f"An error occurred: {e}")
         return JSONResponse(content={"error": "An error occurred"}, status_code=500)
 
+@app.put("/api/stop-generation")
+async def stop_generation_endpoint():
+    global tts_stop_generation, tts_generation_lock
+    if tts_generation_lock and not tts_stop_generation:
+        tts_stop_generation = True
+    return {"message": "Generation stopped"}
+
 ##############################
 #### Standard Generation ####
 ##############################
@@ -870,7 +891,7 @@ except OSError:
         print(f"[{params['branding']}Startup] \033[91mInfo\033[0m On Linux, you can use the following command to install PortAudio:")
         print(f"[{params['branding']}Startup] \033[91mInfo\033[0m sudo apt-get install portaudio19-dev")
 
-from typing import Union, Dict
+from typing import Union, Dict, List
 from pydantic import BaseModel, ValidationError, Field
 
 def play_audio(file_path, volume):
@@ -889,7 +910,7 @@ class JSONInput(BaseModel):
     narrator_enabled: bool = Field(..., description="narrator_enabled needs to be true or false.")
     narrator_voice_gen: str = Field(..., pattern="^.*\.wav$", description="narrator_voice_gen needs to be the name of a wav file e.g. mysample.wav.")
     text_not_inside: str = Field(..., pattern="^(character|narrator)$", description="text_not_inside needs to be 'character' or 'narrator'.")
-    language: str = Field(..., pattern="^(ar|zh-cn|cs|nl|en|fr|de|hu|it|ja|ko|pl|pt|ru|es|tr)$", description="language needs to be one of the following ar|zh-cn|cs|nl|en|fr|de|hu|it|ja|ko|pl|pt|ru|es|tr.")
+    language: str = Field(..., pattern="^(ar|zh-cn|cs|nl|en|fr|de|hu|hi|it|ja|ko|pl|pt|ru|es|tr)$", description="language needs to be one of the following ar|zh-cn|cs|nl|en|fr|de|hu|hi|it|ja|ko|pl|pt|ru|es|tr.")
     output_file_name: str = Field(..., pattern="^[a-zA-Z0-9_]+$", description="output_file_name needs to be the name without any special characters or file extension e.g. 'filename'")
     output_file_timestamp: bool = Field(..., description="output_file_timestamp needs to be true or false.")
     autoplay: bool = Field(..., description="autoplay needs to be a true or false value.")
@@ -1028,12 +1049,17 @@ async def tts_generate(
             "autoplay_volume": autoplay_volume,
             "streaming": streaming,
         }
+        global tts_narrator_generatingtts
         JSONresult = TTSGenerator.validate_json_input(json_input_data)
         if JSONresult is None:
             pass
         else:
+            print(f"[{params['branding']}API] \033[91mError with API request:\033[0m", JSONresult)
             return JSONResponse(content={"error": JSONresult}, status_code=400)
         if narrator_enabled:
+            if params["low_vram"] and device == "cpu":
+                await switch_device()
+            tts_narrator_generatingtts = True
             processed_parts = process_text(text_input)
             audio_files_all_paragraphs = []
             for part_type, part in processed_parts:
@@ -1053,9 +1079,11 @@ async def tts_generate(
                     voice_description = "\033[36mCharacter (Text-not-inside)\033[0m" if text_not_inside == "character" else "\033[92mNarrator (Text-not-inside)\033[0m"
                     print(f"[{params['branding']}TTSGen] {voice_description}")
                 # Replace multiple exclamation marks, question marks, or other punctuation with a single instance
-                cleaned_part = re.sub(r'([!?.])\1+', r'\1', part)
+                cleaned_part = re.sub(r'([!?.\u3002\uFF1F\uFF01\uFF0C])\1+', r'\1', part)
+                # Replace "Chinese ellipsis" with a single dot
+                cleaned_part = re.sub(r"\u2026{1,2}", ". ", cleaned_part)
                 # Further clean to remove any other unwanted characters
-                cleaned_part = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171]\$', '', cleaned_part)
+                cleaned_part = re.sub(r'[^a-zA-Z0-9\s.,;:!?\-\'"$\u0400-\u04FF\u00C0-\u00FF\u0150\u0151\u0170\u0171\u0900-\u097F\u2018\u2019\u201C\u201D\u3001\u3002\u3040-\u309F\u30A0-\u30FF\u4E00-\u9FFF\u3400-\u4DBF\uF900-\uFAFF\u0600-\u06FF\u0750-\u077F\uFB50-\uFDFF\uFE70-\uFEFF\uAC00-\uD7A3\u1100-\u11FF\u3130-\u318F\uFF01\uFF0c\uFF1A\uFF1B\uFF1F]', '', cleaned_part)
                 # Remove all newline characters (single or multiple)
                 cleaned_part = re.sub(r'\n+', ' ', cleaned_part)
                 output_file = this_dir / "outputs" / f"{output_file_name}_{uuid.uuid4()}_{int(time.time())}.wav"
@@ -1065,6 +1093,10 @@ async def tts_generate(
                 audio_files_all_paragraphs.append(audio_path)
             # Combine audio files across paragraphs
             output_file_path, output_file_url, output_cache_url = combine(output_file_timestamp, output_file_name, audio_files_all_paragraphs)
+            tts_narrator_generatingtts = False
+            # Move model back to cpu system ram if needed.
+            if params["low_vram"] and device == "cuda":
+                await switch_device()
         else:
             if output_file_timestamp:
                 timestamp = int(time.time())
@@ -1084,15 +1116,19 @@ async def tts_generate(
                 output_cache_url = f'http://{params["ip_address"]}:{params["port_number"]}/audiocache/{output_file_name}.wav'
             if text_filtering == "html":
                 cleaned_string = html.unescape(standard_filtering(text_input))
-                cleaned_string = re.sub(r'([!?.])\1+', r'\1', text_input)
+                cleaned_string = re.sub(r'([!?.\u3002\uFF1F\uFF01\uFF0C])\1+', r'\1', text_input)
+                # Replace "Chinese ellipsis" with a single dot
+                cleaned_string = re.sub(r"\u2026{1,2}", ". ", cleaned_string)
                 # Further clean to remove any other unwanted characters
-                cleaned_string = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171]\$', '', cleaned_string)
+                cleaned_string = re.sub(r'[^a-zA-Z0-9\s.,;:!?\-\'"$\u0400-\u04FF\u00C0-\u00FF\u0150\u0151\u0170\u0171\u0900-\u097F\u2018\u2019\u201C\u201D\u3001\u3002\u3040-\u309F\u30A0-\u30FF\u4E00-\u9FFF\u3400-\u4DBF\uF900-\uFAFF\u0600-\u06FF\u0750-\u077F\uFB50-\uFDFF\uFE70-\uFEFF\uAC00-\uD7A3\u1100-\u11FF\u3130-\u318F\uFF01\uFF0c\uFF1A\uFF1B\uFF1F]', '', cleaned_string)
                 # Remove all newline characters (single or multiple)
                 cleaned_string = re.sub(r'\n+', ' ', cleaned_string)
             elif text_filtering == "standard":
-                cleaned_string = re.sub(r'([!?.])\1+', r'\1', text_input)
+                cleaned_string = re.sub(r'([!?.\u3002\uFF1F\uFF01\uFF0C])\1+', r'\1', text_input)
+                # Replace "Chinese ellipsis" with a single dot
+                cleaned_string = re.sub(r"\u2026{1,2}", ". ", cleaned_string)
                 # Further clean to remove any other unwanted characters
-                cleaned_string = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171]\$', '', cleaned_string)
+                cleaned_string = re.sub(r'[^a-zA-Z0-9\s.,;:!?\-\'"$\u0400-\u04FF\u00C0-\u00FF\u0150\u0151\u0170\u0171\u0900-\u097F\u2018\u2019\u201C\u201D\u3001\u3002\u3040-\u309F\u30A0-\u30FF\u4E00-\u9FFF\u3400-\u4DBF\uF900-\uFAFF\u0600-\u06FF\u0750-\u077F\uFB50-\uFDFF\uFE70-\uFEFF\uAC00-\uD7A3\u1100-\u11FF\u3130-\u318F\uFF01\uFF0c\uFF1A\uFF1B\uFF1F]', '', cleaned_string)
                 # Remove all newline characters (single or multiple)
                 cleaned_string = re.sub(r'\n+', ' ', cleaned_string)
             else:
@@ -1145,7 +1181,69 @@ def get_current_settings():
 #### Word Add-in Sharing ####
 #############################
 # Mount the static files from the 'word_addin' directory
-app.mount("/api/word_addin", StaticFiles(directory=os.path.join(this_dir / 'templates' / 'word_addin')), name="word_addin")
+app.mount("/api/word_addin", StaticFiles(directory=os.path.join(this_dir / 'system' / 'word_addin')), name="word_addin")
+
+#############################################
+#### TTS Generator Comparision Endpoints ####
+#############################################
+import subprocess
+import aiofiles
+
+class TTSItem(BaseModel):
+    id: int
+    fileUrl: str
+    text: str
+    characterVoice: str
+    language: str
+
+class TTSData(BaseModel):
+    ttsList: List[TTSItem]
+
+@app.post("/api/save-tts-data")
+async def save_tts_data(tts_data: List[TTSItem]):
+    # Convert the list of Pydantic models to a list of dictionaries
+    tts_data_list = [item.dict() for item in tts_data]
+    # Serialize the list of dictionaries to a JSON string
+    tts_data_json = json.dumps(tts_data_list, indent=4)
+    async with aiofiles.open(this_dir / "outputs" / "ttsList.json", 'w') as f:
+        await f.write(tts_data_json)
+    return {"message": "Data saved successfully"}
+
+import sys
+
+@app.get("/api/trigger-analysis")
+async def trigger_analysis(threshold: int = Query(default=98)):
+    venv_path = sys.prefix
+    env = os.environ.copy()
+    env["PATH"] = os.path.join(venv_path, "bin") + ":" + env["PATH"]
+    ttslist_path = this_dir / "outputs" / "ttsList.json"
+    wavfile_path = this_dir / "outputs"
+    subprocess.run(["python", "tts_diff.py", f"--threshold={threshold}", f"--ttslistpath={ttslist_path}", f"--wavfilespath={wavfile_path}"], cwd=this_dir / "system" / "tts_diff", env=env)
+    # Read the analysis summary
+    try:
+        with open(this_dir / "outputs" / "analysis_summary.json", "r") as summary_file:
+            summary_data = json.load(summary_file)
+    except FileNotFoundError:
+        summary_data = {"error": "Analysis summary file not found."}
+    return {"message": "Analysis Completed", "summary": summary_data}
+
+#################################################
+#### TTS Generator SRT Subtitiles generation ####
+#################################################
+@app.get("/api/srt-generation")
+async def srt_generation():
+    venv_path = sys.prefix
+    env = os.environ.copy()
+    env["PATH"] = os.path.join(venv_path, "bin") + ":" + env["PATH"]
+    ttslist_path = this_dir / "outputs" / "ttsList.json"
+    wavfile_path = this_dir / "outputs"
+    subprocess.run(["python", "tts_srt.py", f"--ttslistpath={ttslist_path}", f"--wavfilespath={wavfile_path}"], cwd=this_dir / "system" / "tts_srt", env=env)
+    
+    srt_file_path = this_dir / "outputs" / "subtitles.srt"
+    if not srt_file_path.exists():
+        raise HTTPException(status_code=404, detail="Subtitle file not found.")
+    
+    return FileResponse(path=srt_file_path, filename="subtitles.srt", media_type='application/octet-stream')
 
 ###################################################
 #### Webserver Startup & Initial model Loading ####

voices/Clint_Eastwood CC3.txt

@@ -9,4 +9,6 @@ Author	BBC
 This file is licensed under the Creative Commons Attribution 3.0 Unported license.
 https://creativecommons.org/licenses/by/3.0/deed.en
 
-Downsampled to 22050hz, mono and cut shorter
+Downsampled to 22050hz, mono and cut shorter.
+
+This license applies to both the original file ( «Clint_Eastwood CC3.wav» ) and it's derivative, the enhanced file ( «Clint_Eastwood (enhanced)CC3.wav» ).