From ece55ffe06c76eaccf16c5771f72c280f3d6ee23 Mon Sep 17 00:00:00 2001
From: Josh XT <102809327+Josh-XT@users.noreply.github.com>
Date: Mon, 22 Jan 2024 10:46:10 -0500
Subject: [PATCH 01/25] Create Dockerfile

---
 Dockerfile | 8 ++++++++
 1 file changed, 8 insertions(+)
 create mode 100644 Dockerfile

diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..1624570
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,8 @@
+FROM python:3.11-slim
+WORKDIR /app
+COPY . .
+# Argument for specifying the GPU type, defaulting to "other"
+ARG gpu_type=other
+RUN pip install --no-cache-dir -r requirements_${gpu_type}.txt
+EXPOSE 7851
+CMD ["python", "script.py"]

From 55799b2de8f3d225b12205480b152a933a8426ed Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 10:54:14 -0500
Subject: [PATCH 02/25] Add workflow

---
 .github/workflows/publish-docker.yml | 51 ++++++++++++++++++++++++++++
 Dockerfile                           |  3 +-
 2 files changed, 53 insertions(+), 1 deletion(-)
 create mode 100644 .github/workflows/publish-docker.yml

diff --git a/.github/workflows/publish-docker.yml b/.github/workflows/publish-docker.yml
new file mode 100644
index 0000000..6f5a605
--- /dev/null
+++ b/.github/workflows/publish-docker.yml
@@ -0,0 +1,51 @@
+name: Publish Docker image
+
+on:
+  push:
+    branches: [main]
+  release:
+    types: [published]
+  workflow_dispatch:
+
+jobs:
+  build_and_push:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        include:
+          - image_name: "python:3.11-slim"
+            gpu_type: "other"
+            platforms: "linux/amd64,linux/arm64/v8"
+            tag_name: "other"
+          - image_name: "nvidia/cuda:12.1.1-devel-ubuntu22.04"
+            gpu_type: "nvidia"
+            platforms: "linux/amd64"
+            tag_name: "cuda"
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: ./Dockerfile
+          platforms: ${{ matrix.platforms }}
+          push: true
+          tags: |
+            ghcr.io/josh-xt/alltalk_tts:${{ matrix.tag_name }}
+            ghcr.io/josh-xt/alltalk_tts:${{ matrix.tag_name }}-${{ github.sha }}
+          build-args: |
+            image_name=${{ matrix.image_name }}
+            gpu_type=${{ matrix.gpu_type }}
diff --git a/Dockerfile b/Dockerfile
index 1624570..5a3a349 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -1,4 +1,5 @@
-FROM python:3.11-slim
+ARG image_name=python:3.11-slim
+FROM ${image_name}
 WORKDIR /app
 COPY . .
 # Argument for specifying the GPU type, defaulting to "other"

From 61998b4d39385fdc703a17b397fb77c4960ec2bd Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 11:21:15 -0500
Subject: [PATCH 03/25] Set to nvidia

---
 .github/workflows/publish-docker.yml | 21 +++------------------
 Dockerfile                           |  9 ++++-----
 2 files changed, 7 insertions(+), 23 deletions(-)

diff --git a/.github/workflows/publish-docker.yml b/.github/workflows/publish-docker.yml
index 6f5a605..bdb66b0 100644
--- a/.github/workflows/publish-docker.yml
+++ b/.github/workflows/publish-docker.yml
@@ -10,18 +10,6 @@ on:
 jobs:
   build_and_push:
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        include:
-          - image_name: "python:3.11-slim"
-            gpu_type: "other"
-            platforms: "linux/amd64,linux/arm64/v8"
-            tag_name: "other"
-          - image_name: "nvidia/cuda:12.1.1-devel-ubuntu22.04"
-            gpu_type: "nvidia"
-            platforms: "linux/amd64"
-            tag_name: "cuda"
-
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -41,11 +29,8 @@ jobs:
         with:
           context: .
           file: ./Dockerfile
-          platforms: ${{ matrix.platforms }}
+          platforms: "linux/amd64"
           push: true
           tags: |
-            ghcr.io/josh-xt/alltalk_tts:${{ matrix.tag_name }}
-            ghcr.io/josh-xt/alltalk_tts:${{ matrix.tag_name }}-${{ github.sha }}
-          build-args: |
-            image_name=${{ matrix.image_name }}
-            gpu_type=${{ matrix.gpu_type }}
+            ghcr.io/josh-xt/alltalk_tts:latest
+            ghcr.io/josh-xt/alltalk_tts:main-${{ github.sha }}
diff --git a/Dockerfile b/Dockerfile
index 5a3a349..702953c 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -1,9 +1,8 @@
-ARG image_name=python:3.11-slim
-FROM ${image_name}
+FROM nvidia/cuda:12.1.1-devel-ubuntu22.04
 WORKDIR /app
 COPY . .
-# Argument for specifying the GPU type, defaulting to "other"
-ARG gpu_type=other
-RUN pip install --no-cache-dir -r requirements_${gpu_type}.txt
+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
 EXPOSE 7851
 CMD ["python", "script.py"]

From a199adfbd60fc1cac20806aa26d3b3cd95839c8e Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 11:24:54 -0500
Subject: [PATCH 04/25] Add deps

---
 Dockerfile | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/Dockerfile b/Dockerfile
index 702953c..b157498 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -1,6 +1,15 @@
 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 \
+    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
 WORKDIR /app
 COPY . .
+ENV CUDA_DOCKER_ARCH=all
+RUN pip install deepspeed
 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

From d008c7ab0a07c99b4a806a70ed32a1af8c0e5257 Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 11:27:35 -0500
Subject: [PATCH 05/25] Move install

---
 Dockerfile | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index b157498..5a79e77 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -9,9 +9,10 @@ RUN apt-get update && apt-get upgrade -y \
 WORKDIR /app
 COPY . .
 ENV CUDA_DOCKER_ARCH=all
-RUN pip install deepspeed
+
 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 -r requirements_other.txt && \
+    pip install --no-cache-dir deepspeed
 EXPOSE 7851
 CMD ["python", "script.py"]

From f089e3e85b8f7c437a09fcda6688f273011f3d50 Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 11:45:55 -0500
Subject: [PATCH 06/25] Add multi build

---
 .github/workflows/publish-docker.yml | 32 ++++++++++++++++++++++++----
 Dockerfile                           | 14 +++---------
 nvidia.Dockerfile                    | 18 ++++++++++++++++
 3 files changed, 49 insertions(+), 15 deletions(-)
 create mode 100644 nvidia.Dockerfile

diff --git a/.github/workflows/publish-docker.yml b/.github/workflows/publish-docker.yml
index bdb66b0..570e75e 100644
--- a/.github/workflows/publish-docker.yml
+++ b/.github/workflows/publish-docker.yml
@@ -10,6 +10,15 @@ on:
 jobs:
   build_and_push:
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        include:
+          - dockerfile: "./Dockerfile"
+            platforms: "linux/amd64,linux/arm64/v8"
+            tag_name: "cpu"
+          - dockerfile: "./nvidia.Dockerfile"
+            platforms: "linux/amd64"
+            tag_name: "cuda"
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -24,13 +33,28 @@ jobs:
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
 
+      - name: Login to DockerHub
+        if: vars.DOCKERHUB_USERNAME != ''
+        uses: docker/login-action@v3
+        with:
+          username: ${{ vars.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
       - name: Build and push Docker image
         uses: docker/build-push-action@v5
         with:
           context: .
-          file: ./Dockerfile
-          platforms: "linux/amd64"
+          file: ${{ matrix.dockerfile }}
+          platforms: ${{ matrix.platforms }}
           push: true
           tags: |
-            ghcr.io/josh-xt/alltalk_tts:latest
-            ghcr.io/josh-xt/alltalk_tts:main-${{ github.sha }}
+            ghcr.io/${{ github.actor }}/alltalk_tts:${{ matrix.tag_name }}-${{ github.sha }}
+            ghcr.io/${{ github.actor }}/alltalk_tts:${{ matrix.tag_name }}
+
+      - name: Docker Hub Description
+        if: vars.DOCKERHUB_USERNAME != ''
+        uses: peter-evans/dockerhub-description@v3.4.2
+        with:
+          username: ${{ vars.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+          repository: ${{ vars.DOCKERHUB_USERNAME }}/alltalk_tts
diff --git a/Dockerfile b/Dockerfile
index 5a79e77..3c329a5 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -1,18 +1,10 @@
-FROM nvidia/cuda:12.1.1-devel-ubuntu22.04
+FROM python:3-slim-bullseye
 ENV HOST 0.0.0.0
 RUN apt-get update && apt-get upgrade -y \
     && apt-get install -y git build-essential \
-    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
+    python3 python3-pip gcc wget
 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
+RUN pip install --no-cache-dir -r requirements_other.txt
 EXPOSE 7851
 CMD ["python", "script.py"]
diff --git a/nvidia.Dockerfile b/nvidia.Dockerfile
new file mode 100644
index 0000000..5a79e77
--- /dev/null
+++ b/nvidia.Dockerfile
@@ -0,0 +1,18 @@
+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 \
+    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
+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
+CMD ["python", "script.py"]

From cd164ae2581d6ead1d66e4534dae34c0baa524f8 Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 11:49:10 -0500
Subject: [PATCH 07/25] Updates

---
 .github/workflows/publish-docker.yml | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/.github/workflows/publish-docker.yml b/.github/workflows/publish-docker.yml
index 570e75e..1f7dc52 100644
--- a/.github/workflows/publish-docker.yml
+++ b/.github/workflows/publish-docker.yml
@@ -13,10 +13,10 @@ jobs:
     strategy:
       matrix:
         include:
-          - dockerfile: "./Dockerfile"
+          - dockerfile: "Dockerfile"
             platforms: "linux/amd64,linux/arm64/v8"
             tag_name: "cpu"
-          - dockerfile: "./nvidia.Dockerfile"
+          - dockerfile: "nvidia.Dockerfile"
             platforms: "linux/amd64"
             tag_name: "cuda"
     steps:
@@ -26,11 +26,16 @@ jobs:
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
 
+      - name: Lowercase Actor and Extract Repo Name
+        run: |
+          echo "ACTOR_LOWER=$(echo ${{ github.actor }} | tr '[:upper:]' '[:lower:]')" >> $GITHUB_ENV
+          echo "REPO_NAME=$(echo ${{ github.repository }} | cut -d'/' -f 2)" >> $GITHUB_ENV
+
       - name: Login to GitHub Container Registry
         uses: docker/login-action@v3
         with:
           registry: ghcr.io
-          username: ${{ github.actor }}
+          username: ${{ env.ACTOR_LOWER }}
           password: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Login to DockerHub
@@ -44,12 +49,12 @@ jobs:
         uses: docker/build-push-action@v5
         with:
           context: .
-          file: ${{ matrix.dockerfile }}
+          file: ./${{ matrix.dockerfile }}
           platforms: ${{ matrix.platforms }}
           push: true
           tags: |
-            ghcr.io/${{ github.actor }}/alltalk_tts:${{ matrix.tag_name }}-${{ github.sha }}
-            ghcr.io/${{ github.actor }}/alltalk_tts:${{ matrix.tag_name }}
+            ghcr.io/${{ env.ACTOR_LOWER }}/${{ env.REPO_NAME }}:${{ matrix.tag_name }}-${{ github.sha }}
+            ghcr.io/${{ env.ACTOR_LOWER }}/${{ env.REPO_NAME }}:${{ matrix.tag_name }}
 
       - name: Docker Hub Description
         if: vars.DOCKERHUB_USERNAME != ''
@@ -57,4 +62,4 @@ jobs:
         with:
           username: ${{ vars.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
-          repository: ${{ vars.DOCKERHUB_USERNAME }}/alltalk_tts
+          repository: ${{ vars.DOCKERHUB_USERNAME }}/${{ env.REPO_NAME }}

From 6166d4f75122f20572ae1b3ede2f3f0a654ec505 Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 11:52:41 -0500
Subject: [PATCH 08/25] No arm support

---
 .github/workflows/publish-docker.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/publish-docker.yml b/.github/workflows/publish-docker.yml
index 1f7dc52..60cb6e9 100644
--- a/.github/workflows/publish-docker.yml
+++ b/.github/workflows/publish-docker.yml
@@ -14,7 +14,7 @@ jobs:
       matrix:
         include:
           - dockerfile: "Dockerfile"
-            platforms: "linux/amd64,linux/arm64/v8"
+            platforms: "linux/amd64"
             tag_name: "cpu"
           - dockerfile: "nvidia.Dockerfile"
             platforms: "linux/amd64"

From def2d51c5ffd66add1d1d432c60484430521e088 Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 11:54:29 -0500
Subject: [PATCH 09/25] Use ubuntu

---
 Dockerfile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Dockerfile b/Dockerfile
index 3c329a5..d7f3543 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -1,4 +1,4 @@
-FROM python:3-slim-bullseye
+FROM ubuntu:22.04
 ENV HOST 0.0.0.0
 RUN apt-get update && apt-get upgrade -y \
     && apt-get install -y git build-essential \

From c17959f142046d58e1341c518c146bea497e5f17 Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 12:12:22 -0500
Subject: [PATCH 10/25] Add dockerhub publish

---
 .github/workflows/publish-docker.yml | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/publish-docker.yml b/.github/workflows/publish-docker.yml
index 60cb6e9..95de743 100644
--- a/.github/workflows/publish-docker.yml
+++ b/.github/workflows/publish-docker.yml
@@ -39,7 +39,6 @@ jobs:
           password: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Login to DockerHub
-        if: vars.DOCKERHUB_USERNAME != ''
         uses: docker/login-action@v3
         with:
           username: ${{ vars.DOCKERHUB_USERNAME }}
@@ -55,9 +54,12 @@ jobs:
           tags: |
             ghcr.io/${{ env.ACTOR_LOWER }}/${{ env.REPO_NAME }}:${{ matrix.tag_name }}-${{ github.sha }}
             ghcr.io/${{ env.ACTOR_LOWER }}/${{ env.REPO_NAME }}:${{ matrix.tag_name }}
+            ghcr.io/${{ env.ACTOR_LOWER }}/${{ env.REPO_NAME }}:latest
+            ${{ steps.vars.outputs.DOCKERHUB_USERNAME }}/${{ env.REPO_NAME }}:${{ matrix.tag_name }}-${{ github.sha }}
+            ${{ steps.vars.outputs.DOCKERHUB_USERNAME }}/${{ env.REPO_NAME }}:${{ matrix.tag_name }}
+            ${{ steps.vars.outputs.DOCKERHUB_USERNAME }}/${{ env.REPO_NAME }}:latest
 
       - name: Docker Hub Description
-        if: vars.DOCKERHUB_USERNAME != ''
         uses: peter-evans/dockerhub-description@v3.4.2
         with:
           username: ${{ vars.DOCKERHUB_USERNAME }}

From c3bb58d2af0fbd72da806d71480361c25ac7bdb3 Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 12:15:10 -0500
Subject: [PATCH 11/25] Update dockerhub

---
 .github/workflows/publish-docker.yml | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/.github/workflows/publish-docker.yml b/.github/workflows/publish-docker.yml
index 95de743..302b78c 100644
--- a/.github/workflows/publish-docker.yml
+++ b/.github/workflows/publish-docker.yml
@@ -55,9 +55,9 @@ jobs:
             ghcr.io/${{ env.ACTOR_LOWER }}/${{ env.REPO_NAME }}:${{ matrix.tag_name }}-${{ github.sha }}
             ghcr.io/${{ env.ACTOR_LOWER }}/${{ env.REPO_NAME }}:${{ matrix.tag_name }}
             ghcr.io/${{ env.ACTOR_LOWER }}/${{ env.REPO_NAME }}:latest
-            ${{ steps.vars.outputs.DOCKERHUB_USERNAME }}/${{ env.REPO_NAME }}:${{ matrix.tag_name }}-${{ github.sha }}
-            ${{ steps.vars.outputs.DOCKERHUB_USERNAME }}/${{ env.REPO_NAME }}:${{ matrix.tag_name }}
-            ${{ steps.vars.outputs.DOCKERHUB_USERNAME }}/${{ env.REPO_NAME }}:latest
+            ${{ vars.DOCKERHUB_USERNAME }}/${{ env.REPO_NAME }}:${{ matrix.tag_name }}-${{ github.sha }}
+            ${{ vars.DOCKERHUB_USERNAME }}/${{ env.REPO_NAME }}:${{ matrix.tag_name }}
+            ${{ vars.DOCKERHUB_USERNAME }}/${{ env.REPO_NAME }}:latest
 
       - name: Docker Hub Description
         uses: peter-evans/dockerhub-description@v3.4.2

From d15931bdda41c803c73da9eebb43b344c5c0a082 Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 15:54:46 -0500
Subject: [PATCH 12/25] 3

---
 Dockerfile        | 2 +-
 nvidia.Dockerfile | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index d7f3543..a8ef875 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -7,4 +7,4 @@ WORKDIR /app
 COPY . .
 RUN pip install --no-cache-dir -r requirements_other.txt
 EXPOSE 7851
-CMD ["python", "script.py"]
+CMD ["python3", "script.py"]
diff --git a/nvidia.Dockerfile b/nvidia.Dockerfile
index 5a79e77..cd9c594 100644
--- a/nvidia.Dockerfile
+++ b/nvidia.Dockerfile
@@ -15,4 +15,4 @@ RUN pip install --no-cache-dir -r requirements_nvidia.txt && \
     pip install --no-cache-dir -r requirements_other.txt && \
     pip install --no-cache-dir deepspeed
 EXPOSE 7851
-CMD ["python", "script.py"]
+CMD ["python3", "script.py"]

From fcec9d8f5ba1f8f1fdbd9572ef2a66d9387de041 Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 16:32:30 -0500
Subject: [PATCH 13/25] Fix python alias

---
 Dockerfile        | 5 +++--
 nvidia.Dockerfile | 5 +++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index a8ef875..1ddd804 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -2,9 +2,10 @@ FROM ubuntu:22.04
 ENV HOST 0.0.0.0
 RUN apt-get update && apt-get upgrade -y \
     && apt-get install -y git build-essential \
-    python3 python3-pip gcc wget
+    python3 python3-pip gcc wget \
+    && ln -s /usr/bin/python3 /usr/bin/python
 WORKDIR /app
 COPY . .
 RUN pip install --no-cache-dir -r requirements_other.txt
 EXPOSE 7851
-CMD ["python3", "script.py"]
+CMD ["python", "script.py"]
diff --git a/nvidia.Dockerfile b/nvidia.Dockerfile
index cd9c594..617f070 100644
--- a/nvidia.Dockerfile
+++ b/nvidia.Dockerfile
@@ -5,7 +5,8 @@ RUN apt-get update && apt-get upgrade -y \
     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
+    && 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
@@ -15,4 +16,4 @@ RUN pip install --no-cache-dir -r requirements_nvidia.txt && \
     pip install --no-cache-dir -r requirements_other.txt && \
     pip install --no-cache-dir deepspeed
 EXPOSE 7851
-CMD ["python3", "script.py"]
+CMD ["python", "script.py"]

From bd74de53dac979efb27624fb26bc03a8745e0afa Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 16:53:08 -0500
Subject: [PATCH 14/25] Add portaudio19-dev

---
 Dockerfile        | 2 +-
 nvidia.Dockerfile | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index 1ddd804..8e5a376 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -1,7 +1,7 @@
 FROM ubuntu:22.04
 ENV HOST 0.0.0.0
 RUN apt-get update && apt-get upgrade -y \
-    && apt-get install -y git build-essential \
+    && apt-get install -y git build-essential portaudio19-dev \
     python3 python3-pip gcc wget \
     && ln -s /usr/bin/python3 /usr/bin/python
 WORKDIR /app
diff --git a/nvidia.Dockerfile b/nvidia.Dockerfile
index 617f070..686bb09 100644
--- a/nvidia.Dockerfile
+++ b/nvidia.Dockerfile
@@ -1,7 +1,7 @@
 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 \
+    && 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 \

From d750959f52db7c4cd08e580921d14f4598a277a5 Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 17:04:28 -0500
Subject: [PATCH 15/25] Add docker-compose

---
 docker-compose-cuda.yml | 17 +++++++++++++++++
 docker-compose.yml      | 10 ++++++++++
 2 files changed, 27 insertions(+)
 create mode 100644 docker-compose-cuda.yml
 create mode 100644 docker-compose.yml

diff --git a/docker-compose-cuda.yml b/docker-compose-cuda.yml
new file mode 100644
index 0000000..3b99827
--- /dev/null
+++ b/docker-compose-cuda.yml
@@ -0,0 +1,17 @@
+version: '3.8'
+services:
+  alltalk-tts:
+    image: joshxt/alltalk_tts:cuda
+    restart: unless-stopped
+    ports:
+      - "7851:7851"
+    volumes:
+      - ./outputs:/app/outputs/
+      - ./finetune/put-voice-samples-in-here:/app/finetune/put-voice-samples-in-here
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [ gpu ]
\ No newline at end of file
diff --git a/docker-compose.yml b/docker-compose.yml
new file mode 100644
index 0000000..d54c3ee
--- /dev/null
+++ b/docker-compose.yml
@@ -0,0 +1,10 @@
+version: '3.8'
+services:
+  alltalk-tts:
+    image: joshxt/alltalk_tts:cpu
+    restart: unless-stopped
+    ports:
+      - "7851:7851"
+    volumes:
+      - ./outputs:/app/outputs/
+      - ./finetune/put-voice-samples-in-here:/app/finetune/put-voice-samples-in-here

From cdce7511dc01e1111470bec756a9b6c09f2b106e Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 17:31:41 -0500
Subject: [PATCH 16/25] Use deepspeed

---
 confignew.json | 26 +++++++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/confignew.json b/confignew.json
index 8d9d0c5..039a973 100644
--- a/confignew.json
+++ b/confignew.json
@@ -1 +1,25 @@
-{"activate": true, "autoplay": true, "branding": "AllTalk ", "narrator_enabled": false, "deepspeed_activate": false, "delete_output_wavs": "Disabled", "ip_address": "127.0.0.1", "language": "English", "low_vram": false, "local_temperature": "0.7", "local_repetition_penalty": "10.0", "tts_model_loaded": true, "tts_model_name": "tts_models/multilingual/multi-dataset/xtts_v2", "narrator_voice": "female_01.wav", "output_folder_wav": "extensions/alltalk_tts/outputs/", "output_folder_wav_standalone": "outputs/", "port_number": "7851", "remove_trailing_dots": false, "show_text": true, "tts_method_api_local": false, "tts_method_api_tts": false, "tts_method_xtts_local": true, "voice": "female_01.wav"}
\ No newline at end of file
+{
+    "activate": true,
+    "autoplay": true,
+    "branding": "AllTalk ",
+    "narrator_enabled": false,
+    "deepspeed_activate": true,
+    "delete_output_wavs": "Disabled",
+    "ip_address": "127.0.0.1",
+    "language": "English",
+    "low_vram": false,
+    "local_temperature": "0.7",
+    "local_repetition_penalty": "10.0",
+    "tts_model_loaded": true,
+    "tts_model_name": "tts_models/multilingual/multi-dataset/xtts_v2",
+    "narrator_voice": "female_01.wav",
+    "output_folder_wav": "extensions/alltalk_tts/outputs/",
+    "output_folder_wav_standalone": "outputs/",
+    "port_number": "7851",
+    "remove_trailing_dots": false,
+    "show_text": true,
+    "tts_method_api_local": false,
+    "tts_method_api_tts": false,
+    "tts_method_xtts_local": true,
+    "voice": "female_01.wav"
+}
\ No newline at end of file

From 81a9f4c847686de64073b8e82fd0b41042219199 Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 17:33:02 -0500
Subject: [PATCH 17/25] Persist config

---
 docker-compose-cuda.yml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/docker-compose-cuda.yml b/docker-compose-cuda.yml
index 3b99827..49edd03 100644
--- a/docker-compose-cuda.yml
+++ b/docker-compose-cuda.yml
@@ -8,6 +8,7 @@ services:
     volumes:
       - ./outputs:/app/outputs/
       - ./finetune/put-voice-samples-in-here:/app/finetune/put-voice-samples-in-here
+      - ./confignew.json:/app/confignew.json
     deploy:
       resources:
         reservations:

From 51c91c3d708b4ba31cad762ef43352d0a3982154 Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 17:35:21 -0500
Subject: [PATCH 18/25] Fix config

---
 confignew.json          |  2 +-
 docker-compose-cuda.yml |  2 +-
 docker-compose.yml      |  1 +
 dockerconfig.json       | 25 +++++++++++++++++++++++++
 4 files changed, 28 insertions(+), 2 deletions(-)
 create mode 100644 dockerconfig.json

diff --git a/confignew.json b/confignew.json
index 039a973..2b8f584 100644
--- a/confignew.json
+++ b/confignew.json
@@ -3,7 +3,7 @@
     "autoplay": true,
     "branding": "AllTalk ",
     "narrator_enabled": false,
-    "deepspeed_activate": true,
+    "deepspeed_activate": false,
     "delete_output_wavs": "Disabled",
     "ip_address": "127.0.0.1",
     "language": "English",
diff --git a/docker-compose-cuda.yml b/docker-compose-cuda.yml
index 49edd03..2ee2b53 100644
--- a/docker-compose-cuda.yml
+++ b/docker-compose-cuda.yml
@@ -8,7 +8,7 @@ services:
     volumes:
       - ./outputs:/app/outputs/
       - ./finetune/put-voice-samples-in-here:/app/finetune/put-voice-samples-in-here
-      - ./confignew.json:/app/confignew.json
+      - ./dockerconfig.json:/app/confignew.json
     deploy:
       resources:
         reservations:
diff --git a/docker-compose.yml b/docker-compose.yml
index d54c3ee..39d3609 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -8,3 +8,4 @@ services:
     volumes:
       - ./outputs:/app/outputs/
       - ./finetune/put-voice-samples-in-here:/app/finetune/put-voice-samples-in-here
+      - ./dockerconfig.json:/app/confignew.json
\ No newline at end of file
diff --git a/dockerconfig.json b/dockerconfig.json
new file mode 100644
index 0000000..039a973
--- /dev/null
+++ b/dockerconfig.json
@@ -0,0 +1,25 @@
+{
+    "activate": true,
+    "autoplay": true,
+    "branding": "AllTalk ",
+    "narrator_enabled": false,
+    "deepspeed_activate": true,
+    "delete_output_wavs": "Disabled",
+    "ip_address": "127.0.0.1",
+    "language": "English",
+    "low_vram": false,
+    "local_temperature": "0.7",
+    "local_repetition_penalty": "10.0",
+    "tts_model_loaded": true,
+    "tts_model_name": "tts_models/multilingual/multi-dataset/xtts_v2",
+    "narrator_voice": "female_01.wav",
+    "output_folder_wav": "extensions/alltalk_tts/outputs/",
+    "output_folder_wav_standalone": "outputs/",
+    "port_number": "7851",
+    "remove_trailing_dots": false,
+    "show_text": true,
+    "tts_method_api_local": false,
+    "tts_method_api_tts": false,
+    "tts_method_xtts_local": true,
+    "voice": "female_01.wav"
+}
\ No newline at end of file

From 360f70cb0acd16ebeb754d8afe66aa369957b16f Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 18:10:20 -0500
Subject: [PATCH 19/25] Disable deepspeed

---
 dockerconfig.json | 2 +-
 nvidia.Dockerfile | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/dockerconfig.json b/dockerconfig.json
index 039a973..2b8f584 100644
--- a/dockerconfig.json
+++ b/dockerconfig.json
@@ -3,7 +3,7 @@
     "autoplay": true,
     "branding": "AllTalk ",
     "narrator_enabled": false,
-    "deepspeed_activate": true,
+    "deepspeed_activate": false,
     "delete_output_wavs": "Disabled",
     "ip_address": "127.0.0.1",
     "language": "English",
diff --git a/nvidia.Dockerfile b/nvidia.Dockerfile
index 686bb09..fdc2f39 100644
--- a/nvidia.Dockerfile
+++ b/nvidia.Dockerfile
@@ -13,7 +13,6 @@ 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
+    pip install --no-cache-dir -r requirements_other.txt
 EXPOSE 7851
 CMD ["python", "script.py"]

From 12bf008b3fb7d2ba0e7af15c41fb4412eac81a08 Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 19:15:54 -0500
Subject: [PATCH 20/25] Run back end without subprocess

---
 Dockerfile              |   2 +-
 docker-compose-cuda.yml |   1 +
 docker-compose.yml      |   1 +
 dockerconfig.json       |   2 +-
 launch.sh               |   4 +
 nvidia.Dockerfile       |   2 +-
 script.py               | 385 ++++++++++++++++++++++++++++------------
 7 files changed, 277 insertions(+), 120 deletions(-)
 create mode 100644 launch.sh

diff --git a/Dockerfile b/Dockerfile
index 8e5a376..0e0cef9 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -8,4 +8,4 @@ WORKDIR /app
 COPY . .
 RUN pip install --no-cache-dir -r requirements_other.txt
 EXPOSE 7851
-CMD ["python", "script.py"]
+ENTRYPOINT ["sh", "-c", "./launch.sh"]
\ No newline at end of file
diff --git a/docker-compose-cuda.yml b/docker-compose-cuda.yml
index 2ee2b53..309609e 100644
--- a/docker-compose-cuda.yml
+++ b/docker-compose-cuda.yml
@@ -7,6 +7,7 @@ services:
       - "7851:7851"
     volumes:
       - ./outputs:/app/outputs/
+      - ./models:/app/models/
       - ./finetune/put-voice-samples-in-here:/app/finetune/put-voice-samples-in-here
       - ./dockerconfig.json:/app/confignew.json
     deploy:
diff --git a/docker-compose.yml b/docker-compose.yml
index 39d3609..2ab938b 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -7,5 +7,6 @@ services:
       - "7851:7851"
     volumes:
       - ./outputs:/app/outputs/
+      - ./models:/app/models/
       - ./finetune/put-voice-samples-in-here:/app/finetune/put-voice-samples-in-here
       - ./dockerconfig.json:/app/confignew.json
\ No newline at end of file
diff --git a/dockerconfig.json b/dockerconfig.json
index 2b8f584..039a973 100644
--- a/dockerconfig.json
+++ b/dockerconfig.json
@@ -3,7 +3,7 @@
     "autoplay": true,
     "branding": "AllTalk ",
     "narrator_enabled": false,
-    "deepspeed_activate": false,
+    "deepspeed_activate": true,
     "delete_output_wavs": "Disabled",
     "ip_address": "127.0.0.1",
     "language": "English",
diff --git a/launch.sh b/launch.sh
new file mode 100644
index 0000000..23dc4d6
--- /dev/null
+++ b/launch.sh
@@ -0,0 +1,4 @@
+#!/bin/sh
+uvicorn tts_server:app --host 0.0.0.0 --port 7581 --workers 1 --proxy-headers &
+sleep 5
+python script.py
\ No newline at end of file
diff --git a/nvidia.Dockerfile b/nvidia.Dockerfile
index fdc2f39..d7ac052 100644
--- a/nvidia.Dockerfile
+++ b/nvidia.Dockerfile
@@ -15,4 +15,4 @@ 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
 EXPOSE 7851
-CMD ["python", "script.py"]
+ENTRYPOINT ["sh", "-c", "./launch.sh"]
\ No newline at end of file
diff --git a/script.py b/script.py
index 74f23f5..a02d79c 100644
--- a/script.py
+++ b/script.py
@@ -30,12 +30,14 @@ 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)
@@ -56,6 +58,7 @@ except ModuleNotFoundError:
 # IMPORT - Attempt Importing DeepSpeed (required for displaying Deepspeed checkbox in gradio)
 try:
     import deepspeed
+
     deepspeed_installed = True
 except ImportError:
     deepspeed_installed = False
@@ -68,6 +71,7 @@ try:
     from modules.logging_colors import logger
     from modules.ui import create_refresh_button
     from modules.utils import gradio
+
     # 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"]
@@ -88,10 +92,12 @@ process_lock = threading.Lock()
 # Base setting for a possible FineTuned model existing and the loader being available
 tts_method_xtts_ft = False
 
+
 # Gather the voice files
 def get_available_voices():
     return sorted([voice.name for voice in Path(f"{this_dir}/voices").glob("*.wav")])
 
+
 #########################
 #### LICENSE DISPLAY ####
 #########################
@@ -149,6 +155,7 @@ def check_required_files():
     subprocess.run(["python", str(download_script_path)])
     print(f"[{params['branding']}Startup] All required files are present.")
 
+
 # STARTUP Call Check routine
 check_required_files()
 
@@ -163,7 +170,9 @@ finetuned_model = trained_model_directory.exists()
 # If true, this will add a extra option in the Gradio interface for loading Xttsv2 FT
 if finetuned_model:
     required_files = ["model.pth", "config.json", "vocab.json"]
-    finetuned_model = all((trained_model_directory / file).exists() for file in required_files)
+    finetuned_model = all(
+        (trained_model_directory / file).exists() for file in required_files
+    )
 if finetuned_model:
     print(f"[{params['branding']}Startup] Finetuned model \033[93mDetected\033[0m")
 
@@ -181,6 +190,7 @@ 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 ####
 ######################
@@ -239,65 +249,79 @@ def signal_handler(sig, frame):
 # Attach the signal handler to the SIGINT signal (Ctrl+C)
 signal.signal(signal.SIGINT, signal_handler)
 
-# Start the subprocess
-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]")
-    print(
-        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."
-    )
-    # Cleanly kill off this script, but allow text-generation-webui to keep running, albeit without this alltalk_tts
-    sys.exit(1)
-
-timeout = startup_wait_time  # Gather timeout setting from startup_wait_time
-
-# Introduce a delay before starting the check loop
-time.sleep(26)  # Wait 26 secs before checking if the tts_server.py has started up.
-start_time = time.time()
-while time.time() - start_time < timeout:
-    try:
-        response = requests.get(f"{base_url}/ready")
-        if response.status_code == 200:
-            break
-    except requests.RequestException as e:
-        # Print the exception for debugging purposes
+try:
+    response = requests.get(f"{base_url}/ready")
+    if response.status_code == 200:
+        pass
+except:
+    # Start the subprocess
+    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]")
         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."
+            f"[{params['branding']}Startup] \033[94m {params['branding']}Settings & Documentation:\033[00m",
+            f"\033[92mhttp://{params['ip_address']}:{params['port_number']}\033[00m",
         )
-    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.")
-    # Cleanly kill off this script, but allow text-generation-webui to keep running, albeit without this alltalk_tts
-    sys.exit(1)
+        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."
+        )
+        # Cleanly kill off this script, but allow text-generation-webui to keep running, albeit without this alltalk_tts
+        sys.exit(1)
+
+    timeout = startup_wait_time  # Gather timeout setting from startup_wait_time
+
+    # Introduce a delay before starting the check loop
+    time.sleep(26)  # Wait 26 secs before checking if the tts_server.py has started up.
+    start_time = time.time()
+    while time.time() - start_time < timeout:
+        try:
+            response = requests.get(f"{base_url}/ready")
+            if response.status_code == 200:
+                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."
+            )
+        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."
+        )
+        # Cleanly kill off this script, but allow text-generation-webui to keep running, albeit without this alltalk_tts
+        sys.exit(1)
 
 
 #####################################
@@ -352,6 +376,7 @@ def send_reload_request(tts_method):
         )
         return {"status": "error", "message": str(e)}
 
+
 ##################
 #### LOW VRAM ####
 ##################
@@ -392,7 +417,7 @@ def send_deepspeed_request(deepspeed_param):
             audio_path = this_dir / "templates" / "deepspeedenabled.wav"
         else:
             audio_path = this_dir / "templates" / "deepspeeddisabled.wav"
-        
+
         url = f"{base_url}/api/deepspeed?new_deepspeed_value={deepspeed_param}"
         headers = {"Content-Type": "application/json"}
         response = requests.post(url, headers=headers)
@@ -466,9 +491,13 @@ 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:
@@ -506,7 +535,12 @@ def voice_preview(string):
     # Lock before making the generate request
     with process_lock:
         generate_response = send_generate_request(
-            string, params["voice"], language_code, temperature, repetition_penalty, output_file_str
+            string,
+            params["voice"],
+            language_code,
+            temperature,
+            repetition_penalty,
+            output_file_str,
         )
     # Check if lock is already acquired
     if process_lock.locked():
@@ -528,7 +562,7 @@ def process_text(text):
     text = html.unescape(text)
 
     # Replace ellipsis with a single dot
-    text = re.sub(r'\.{3,}', '.', text)
+    text = re.sub(r"\.{3,}", ".", text)
 
     # Pattern to identify combined narrator and character speech
     combined_pattern = r'(\*[^*"]+\*|"[^"*]+")'
@@ -543,22 +577,22 @@ def process_text(text):
     for match in re.finditer(combined_pattern, text):
         # Add the text before the match, if any, as ambiguous
         if start < match.start():
-            ambiguous_text = text[start:match.start()].strip()
+            ambiguous_text = text[start : match.start()].strip()
             if ambiguous_text:
-                ordered_parts.append(('ambiguous', ambiguous_text))
+                ordered_parts.append(("ambiguous", ambiguous_text))
 
         # Add the matched part as either narrator or character
         matched_text = match.group(0)
-        if matched_text.startswith('*') and matched_text.endswith('*'):
-            ordered_parts.append(('narrator', matched_text.strip('*').strip()))
+        if matched_text.startswith("*") and matched_text.endswith("*"):
+            ordered_parts.append(("narrator", matched_text.strip("*").strip()))
         elif matched_text.startswith('"') and matched_text.endswith('"'):
-            ordered_parts.append(('character', matched_text.strip('"').strip()))
+            ordered_parts.append(("character", matched_text.strip('"').strip()))
         else:
             # In case of mixed or improperly formatted parts
-            if '*' in matched_text:
-                ordered_parts.append(('narrator', matched_text.strip('*').strip('"')))
+            if "*" in matched_text:
+                ordered_parts.append(("narrator", matched_text.strip("*").strip('"')))
             else:
-                ordered_parts.append(('character', matched_text.strip('"').strip('*')))
+                ordered_parts.append(("character", matched_text.strip('"').strip("*")))
 
         # Update the start of the next segment
         start = match.end()
@@ -567,10 +601,11 @@ def process_text(text):
     if start < len(text):
         ambiguous_text = text[start:].strip()
         if ambiguous_text:
-            ordered_parts.append(('ambiguous', ambiguous_text))
+            ordered_parts.append(("ambiguous", ambiguous_text))
 
     return ordered_parts
 
+
 #################################
 #### TTS STANDARD GENERATION ####
 #################################
@@ -579,7 +614,7 @@ def output_modifier(string, state):
     if not params["activate"]:
         return string
     original_string = string
-    #print("ORIGINAL STRING IS:", original_string)
+    # print("ORIGINAL STRING IS:", original_string)
     cleaned_string = before_audio_generation(string, params)
     if cleaned_string is None:
         return
@@ -601,29 +636,50 @@ def output_modifier(string, state):
                         continue
 
                     # Determine the voice to use based on the part type
-                    if part_type == 'narrator':
+                    if part_type == "narrator":
                         voice_to_use = params["narrator_voice"]
-                        print(f"[{params['branding']}TTSGen] \033[92mNarrator\033[0m")  # Green
-                    elif part_type == 'character':
+                        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 = params["voice"] if non_quoted_text_is else params["narrator_voice"]
-                        voice_description = "\033[36mCharacter (Text-not-inside)\033[0m" if non_quoted_text_is else "\033[92mNarrator (Text-not-inside)\033[0m"
+                        voice_to_use = (
+                            params["voice"]
+                            if non_quoted_text_is
+                            else params["narrator_voice"]
+                        )
+                        voice_description = (
+                            "\033[36mCharacter (Text-not-inside)\033[0m"
+                            if non_quoted_text_is
+                            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"([!?.])\1+", r"\1", 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-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\$]',
+                        "",
+                        cleaned_part,
+                    )
                     # Remove all newline characters (single or multiple)
-                    cleaned_part = re.sub(r'\n+', ' ', cleaned_part)
+                    cleaned_part = re.sub(r"\n+", " ", cleaned_part)
 
                     # Generate TTS and output to a file
                     output_filename = get_output_filename(state)
                     generate_response = send_generate_request(
-                        cleaned_part, voice_to_use, language_code, temperature, repetition_penalty, output_filename
+                        cleaned_part,
+                        voice_to_use,
+                        language_code,
+                        temperature,
+                        repetition_penalty,
+                        output_filename,
                     )
                     audio_path = generate_response.get("data", {}).get("audio_path")
                     audio_files_all_paragraphs.append(audio_path)
@@ -636,20 +692,33 @@ def output_modifier(string, state):
                 # Decode HTML entities first
                 cleaned_part = html.unescape(original_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"([!?.])\1+", r"\1", 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-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\$]',
+                    "",
+                    cleaned_part,
+                )
                 # Remove all newline characters (single or multiple)
-                cleaned_part = re.sub(r'\n+', ' ', cleaned_part)
+                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.
                 if "character_menu" in state:
-                    output_file = Path(f'{params["output_folder_wav"]}/{state["character_menu"]}_{int(time.time())}.wav')
+                    output_file = Path(
+                        f'{params["output_folder_wav"]}/{state["character_menu"]}_{int(time.time())}.wav'
+                    )
                 else:
-                    output_file = Path(f'{params["output_folder_wav"]}/TTSOUT_{int(time.time())}.wav')
+                    output_file = Path(
+                        f'{params["output_folder_wav"]}/TTSOUT_{int(time.time())}.wav'
+                    )
                 output_file_str = output_file.as_posix()
                 output_file = get_output_filename(state)
                 generate_response = send_generate_request(
-                    cleaned_part, params["voice"], language_code, temperature, repetition_penalty, output_file_str
+                    cleaned_part,
+                    params["voice"],
+                    language_code,
+                    temperature,
+                    repetition_penalty,
+                    output_file_str,
                 )
                 audio_path = generate_response.get("data", {}).get("audio_path")
                 final_output_file = audio_path
@@ -690,15 +759,21 @@ def output_modifier(string, state):
 
 def get_output_filename(state):
     if "character_menu" in state:
-        return Path(f'{params["output_folder_wav"]}/{state["character_menu"]}_{str(uuid.uuid4())[:8]}.wav').as_posix()
+        return Path(
+            f'{params["output_folder_wav"]}/{state["character_menu"]}_{str(uuid.uuid4())[:8]}.wav'
+        ).as_posix()
     else:
-        return Path(f'{params["output_folder_wav"]}/TTSOUT_{str(uuid.uuid4())[:8]}.wav').as_posix()
+        return Path(
+            f'{params["output_folder_wav"]}/TTSOUT_{str(uuid.uuid4())[:8]}.wav'
+        ).as_posix()
 
 
 ###############################################
 #### SEND GENERATION REQUEST TO TTS ENGINE ####
 ###############################################
-def send_generate_request(text, voice, language, temperature, repetition_penalty, output_file):
+def send_generate_request(
+    text, voice, language, temperature, repetition_penalty, output_file
+):
     url = f"{base_url}/api/generate"
     payload = {
         "text": text,
@@ -730,12 +805,14 @@ def state_modifier(state):
     state["stream"] = False
     return state
 
+
 def update_narrator_enabled(value):
     if value == "Enabled":
         params["narrator_enabled"] = True
     elif value == "Disabled":
         params["narrator_enabled"] = False
 
+
 def update_non_quoted_text_is(value):
     global non_quoted_text_is
     if value == "Narrator":
@@ -743,6 +820,7 @@ def update_non_quoted_text_is(value):
     elif value == "Char":
         non_quoted_text_is = True
 
+
 def input_modifier(string, state):
     if not params["activate"]:
         return string
@@ -755,21 +833,29 @@ def ui():
     with gr.Accordion(params["branding"] + " TTS (XTTSv2)"):
         # Activate alltalk_tts, Enable autoplay, Show text
         with gr.Row():
-            activate = gr.Checkbox(value=params['activate'], label='Enable TTS')
-            autoplay = gr.Checkbox(value=params['autoplay'], label='Autoplay TTS')
-            show_text = gr.Checkbox(value=params['show_text'], label='Show Text')
+            activate = gr.Checkbox(value=params["activate"], label="Enable TTS")
+            autoplay = gr.Checkbox(value=params["autoplay"], label="Autoplay TTS")
+            show_text = gr.Checkbox(value=params["show_text"], label="Show Text")
 
         # Low vram enable, Deepspeed enable, Remove trailing dots
         with gr.Row():
-            low_vram = gr.Checkbox(value=params['low_vram'], label='Enable Low VRAM Mode')
+            low_vram = gr.Checkbox(
+                value=params["low_vram"], label="Enable Low VRAM Mode"
+            )
             low_vram_play = gr.HTML(visible=False)
-            deepspeed_checkbox = gr.Checkbox(value=params['deepspeed_activate'], label='Enable DeepSpeed', visible=deepspeed_installed)
+            deepspeed_checkbox = gr.Checkbox(
+                value=params["deepspeed_activate"],
+                label="Enable DeepSpeed",
+                visible=deepspeed_installed,
+            )
             deepspeed_checkbox_play = gr.HTML(visible=False)
-            remove_trailing_dots = gr.Checkbox(value=params['remove_trailing_dots'], label='Remove trailing "."')
+            remove_trailing_dots = gr.Checkbox(
+                value=params["remove_trailing_dots"], label='Remove trailing "."'
+            )
 
         # TTS method, Character voice selection
         with gr.Row():
-            model_loader_choices=["API TTS", "API Local", "XTTSv2 Local"]
+            model_loader_choices = ["API TTS", "API Local", "XTTSv2 Local"]
             if finetuned_model:
                 model_loader_choices.append("XTTSv2 FT")
             tts_radio_buttons = gr.Radio(
@@ -780,33 +866,86 @@ def ui():
             tts_radio_buttons_play = gr.HTML(visible=False)
             with gr.Row():
                 available_voices = get_available_voices()
-                default_voice = params["voice"] # Check if the default voice is in the list of available voices
+                default_voice = params[
+                    "voice"
+                ]  # Check if the default voice is in the list of available voices
 
                 if default_voice not in available_voices:
-                    default_voice = available_voices[ 0 ] # Choose the first available voice as the default
+                    default_voice = available_voices[
+                        0
+                    ]  # Choose the first available voice as the default
                 # Add allow_custom_value=True to the Dropdown
-                voice = gr.Dropdown(available_voices, label="Character Voice", value=default_voice, allow_custom_value=True, )
-                create_refresh_button(voice, lambda: None, lambda: {"choices": get_available_voices(), "value": params["voice"],}, "refresh-button",)
+                voice = gr.Dropdown(
+                    available_voices,
+                    label="Character Voice",
+                    value=default_voice,
+                    allow_custom_value=True,
+                )
+                create_refresh_button(
+                    voice,
+                    lambda: None,
+                    lambda: {
+                        "choices": get_available_voices(),
+                        "value": params["voice"],
+                    },
+                    "refresh-button",
+                )
 
         # Language, Narrator voice
         with gr.Row():
-            language = gr.Dropdown(languages.keys(), label="Language", value=params["language"])
+            language = gr.Dropdown(
+                languages.keys(), label="Language", value=params["language"]
+            )
             with gr.Row():
-                narrator_voice_gr = gr.Dropdown(get_available_voices(), label="Narrator Voice", allow_custom_value=True, value=params["narrator_voice"])
-                create_refresh_button(narrator_voice_gr, lambda: None, lambda: {"choices": get_available_voices(), "value": params["narrator_voice"],}, "refresh-button")
+                narrator_voice_gr = gr.Dropdown(
+                    get_available_voices(),
+                    label="Narrator Voice",
+                    allow_custom_value=True,
+                    value=params["narrator_voice"],
+                )
+                create_refresh_button(
+                    narrator_voice_gr,
+                    lambda: None,
+                    lambda: {
+                        "choices": get_available_voices(),
+                        "value": params["narrator_voice"],
+                    },
+                    "refresh-button",
+                )
 
         # Temperature, Repetition Penalty
         with gr.Row():
-            local_temperature_gr = gr.Slider(minimum=0.05, maximum=1, step=0.05, label="Temperature", value=params["local_temperature"])
-            local_repetition_penalty_gr = gr.Slider(minimum=0.5, maximum=20, step=0.5, label="Repetition Penalty", value=params["local_repetition_penalty"])
+            local_temperature_gr = gr.Slider(
+                minimum=0.05,
+                maximum=1,
+                step=0.05,
+                label="Temperature",
+                value=params["local_temperature"],
+            )
+            local_repetition_penalty_gr = gr.Slider(
+                minimum=0.5,
+                maximum=20,
+                step=0.5,
+                label="Repetition Penalty",
+                value=params["local_repetition_penalty"],
+            )
 
         # Narrator enable, Non quoted text, Explanation text
         with gr.Row():
             with gr.Row():
-                narrator_enabled_gr = gr.Radio(choices={"Enabled": "true", "Disabled": "false"}, label="Narrator", value="Enabled" if params.get("narrator_enabled") else "Disabled")
-                non_quoted_text_is_gr = gr.Radio(choices={"Character": "true", "Narrator": "false"}, label='Unmarked text NOT inside of * or " is', value="Character" if non_quoted_text_is else "Narrator")
+                narrator_enabled_gr = gr.Radio(
+                    choices={"Enabled": "true", "Disabled": "false"},
+                    label="Narrator",
+                    value="Enabled" if params.get("narrator_enabled") else "Disabled",
+                )
+                non_quoted_text_is_gr = gr.Radio(
+                    choices={"Character": "true", "Narrator": "false"},
+                    label='Unmarked text NOT inside of * or " is',
+                    value="Character" if non_quoted_text_is else "Narrator",
+                )
                 explanation_text = gr.HTML(
-                f"<p>⚙️ <a href='http://{params['ip_address']}:{params['port_number']}'>Settings and Documentation Page</a><a href='http://{params['ip_address']}:{params['port_number']}'></a>⚙️<br>- Low VRAM Mode and Deepspeed take 15 seconds to be enabled or disabled.<br>- The DeepSpeed checkbox is only visible if DeepSpeed is present.</p>")
+                    f"<p>⚙️ <a href='http://{params['ip_address']}:{params['port_number']}'>Settings and Documentation Page</a><a href='http://{params['ip_address']}:{params['port_number']}'></a>⚙️<br>- Low VRAM Mode and Deepspeed take 15 seconds to be enabled or disabled.<br>- The DeepSpeed checkbox is only visible if DeepSpeed is present.</p>"
+                )
 
         # Preview speech
         with gr.Row():
@@ -817,7 +956,7 @@ def ui():
             )
             preview_play = gr.Button("Preview")
             preview_audio = gr.HTML(visible=False)
-        
+
         with gr.Row():
             convert = gr.Button("Permanently replace audios with the message texts")
             convert_cancel = gr.Button("Cancel", visible=False)
@@ -878,8 +1017,12 @@ def ui():
     autoplay.change(lambda x: params.update({"autoplay": x}), autoplay, None)
     low_vram.change(lambda x: params.update({"low_vram": x}), low_vram, None)
     low_vram.change(lambda x: send_lowvram_request(x), low_vram, low_vram_play, None)
-    tts_radio_buttons.change(send_reload_request, tts_radio_buttons, tts_radio_buttons_play, None)
-    deepspeed_checkbox.change(send_deepspeed_request, deepspeed_checkbox, deepspeed_checkbox_play, None)
+    tts_radio_buttons.change(
+        send_reload_request, tts_radio_buttons, tts_radio_buttons_play, None
+    )
+    deepspeed_checkbox.change(
+        send_deepspeed_request, deepspeed_checkbox, deepspeed_checkbox_play, None
+    )
     remove_trailing_dots.change(
         lambda x: params.update({"remove_trailing_dots": x}), remove_trailing_dots, None
     )
@@ -887,13 +1030,21 @@ def ui():
     language.change(lambda x: params.update({"language": x}), language, None)
 
     # TSS Settings
-    local_temperature_gr.change(lambda x: params.update({"local_temperature": x}), local_temperature_gr, None)
-    local_repetition_penalty_gr.change(lambda x: params.update({"local_repetition_penalty": x}), local_repetition_penalty_gr, None)
+    local_temperature_gr.change(
+        lambda x: params.update({"local_temperature": x}), local_temperature_gr, None
+    )
+    local_repetition_penalty_gr.change(
+        lambda x: params.update({"local_repetition_penalty": x}),
+        local_repetition_penalty_gr,
+        None,
+    )
 
     # Narrator selection actions
     narrator_enabled_gr.change(update_narrator_enabled, narrator_enabled_gr, None)
     non_quoted_text_is_gr.change(update_non_quoted_text_is, non_quoted_text_is_gr, None)
-    narrator_voice_gr.change(lambda x: params.update({"narrator_voice": x}), narrator_voice_gr, None)
+    narrator_voice_gr.change(
+        lambda x: params.update({"narrator_voice": x}), narrator_voice_gr, None
+    )
 
     # Play preview
     preview_text.submit(voice_preview, preview_text, preview_audio)

From ec1d0e8c5d3b092520a119f9b02a22238eefce95 Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 19:26:23 -0500
Subject: [PATCH 21/25] Check if running in docker

---
 script.py | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/script.py b/script.py
index a02d79c..5cee0f6 100644
--- a/script.py
+++ b/script.py
@@ -248,12 +248,12 @@ def signal_handler(sig, frame):
 
 # Attach the signal handler to the SIGINT signal (Ctrl+C)
 signal.signal(signal.SIGINT, signal_handler)
-
-try:
-    response = requests.get(f"{base_url}/ready")
-    if response.status_code == 200:
-        pass
-except:
+# Check if we're running in docker
+if os.path.isfile("/.dockerenv"):
+    print(
+        f"[{params['branding']}Startup] \033[94mRunning in Docker. Please wait.\033[0m"
+    )
+else:
     # Start the subprocess
     process = subprocess.Popen(["python", script_path])
     # Check if the subprocess has started successfully

From c29de18ad44d679501440916a315976549c1f833 Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 19:41:18 -0500
Subject: [PATCH 22/25] add chmod

---
 Dockerfile        | 1 +
 nvidia.Dockerfile | 1 +
 2 files changed, 2 insertions(+)

diff --git a/Dockerfile b/Dockerfile
index 0e0cef9..a4da795 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -8,4 +8,5 @@ WORKDIR /app
 COPY . .
 RUN pip install --no-cache-dir -r requirements_other.txt
 EXPOSE 7851
+RUN chmod +x launch.sh
 ENTRYPOINT ["sh", "-c", "./launch.sh"]
\ No newline at end of file
diff --git a/nvidia.Dockerfile b/nvidia.Dockerfile
index d7ac052..a273bc5 100644
--- a/nvidia.Dockerfile
+++ b/nvidia.Dockerfile
@@ -15,4 +15,5 @@ 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
 EXPOSE 7851
+RUN chmod +x launch.sh
 ENTRYPOINT ["sh", "-c", "./launch.sh"]
\ No newline at end of file

From 0ed3cb75b54146eb7006c8da25dc3b6b4efe1ffc Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 20:44:18 -0500
Subject: [PATCH 23/25] Add modeldownload

---
 launch.sh         | 1 +
 nvidia.Dockerfile | 3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/launch.sh b/launch.sh
index 23dc4d6..0de2cec 100644
--- a/launch.sh
+++ b/launch.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+python modeldownload.py
 uvicorn tts_server:app --host 0.0.0.0 --port 7581 --workers 1 --proxy-headers &
 sleep 5
 python script.py
\ No newline at end of file
diff --git a/nvidia.Dockerfile b/nvidia.Dockerfile
index a273bc5..475674a 100644
--- a/nvidia.Dockerfile
+++ b/nvidia.Dockerfile
@@ -13,7 +13,8 @@ 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 -r requirements_other.txt && \
+    pip install --no-cache-dir deepspeed
 EXPOSE 7851
 RUN chmod +x launch.sh
 ENTRYPOINT ["sh", "-c", "./launch.sh"]
\ No newline at end of file

From b3f53e93cc884315d0a147020c29048ef7cadc18 Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 20:46:53 -0500
Subject: [PATCH 24/25] fix typo

---
 launch.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/launch.sh b/launch.sh
index 0de2cec..97708c3 100644
--- a/launch.sh
+++ b/launch.sh
@@ -1,5 +1,5 @@
 #!/bin/sh
 python modeldownload.py
-uvicorn tts_server:app --host 0.0.0.0 --port 7581 --workers 1 --proxy-headers &
+uvicorn tts_server:app --host 0.0.0.0 --port 7851 --workers 1 --proxy-headers &
 sleep 5
 python script.py
\ No newline at end of file

From 71ba584e7ce333152dc605dad0e4f47d0e8837a5 Mon Sep 17 00:00:00 2001
From: Josh XT <josh@devxt.com>
Date: Mon, 22 Jan 2024 21:15:29 -0500
Subject: [PATCH 25/25] Add voices

---
 docker-compose-cuda.yml | 1 +
 docker-compose.yml      | 1 +
 2 files changed, 2 insertions(+)

diff --git a/docker-compose-cuda.yml b/docker-compose-cuda.yml
index 309609e..909a8f7 100644
--- a/docker-compose-cuda.yml
+++ b/docker-compose-cuda.yml
@@ -8,6 +8,7 @@ services:
     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
     deploy:
diff --git a/docker-compose.yml b/docker-compose.yml
index 2ab938b..fefcaaf 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -8,5 +8,6 @@ services:
     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
\ No newline at end of file