Update README.md

CJK Symbols and Punctuation range u3000 > u303F

.github/FUNDING.yml

@@ -0,0 +1 @@
+ko_fi: erew123

.github/workflows/publish-docker.yml

@@ -0,0 +1,67 @@
+name: Publish Docker image
+
+on:
+  push:
+    branches: [main]
+  release:
+    types: [published]
+  workflow_dispatch:
+
+jobs:
+  build_and_push:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        include:
+          - dockerfile: "Dockerfile"
+            platforms: "linux/amd64"
+            tag_name: "cpu"
+          - dockerfile: "nvidia.Dockerfile"
+            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: 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: ${{ env.ACTOR_LOWER }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Login to DockerHub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ vars.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: ./${{ matrix.dockerfile }}
+          platforms: ${{ matrix.platforms }}
+          push: true
+          tags: |
+            ghcr.io/${{ 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
+            ${{ vars.DOCKERHUB_USERNAME }}/${{ 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
+        with:
+          username: ${{ vars.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+          repository: ${{ vars.DOCKERHUB_USERNAME }}/${{ env.REPO_NAME }}

.gitignore

@@ -1,6 +1,7 @@
 voices/*.*
 models/*.*
 outputs/*.*
+finetune/*.*
 config.json
 confignew.json
 models.json

.vscode/settings.json

@@ -0,0 +1,9 @@
+{
+    "files.associations": {
+        "*.html": "jinja-html"
+    },
+    "emmet.includeLanguages": {
+        "jinja-html": "html",
+        "jinja2": "html"
+    },
+}

Dockerfile

@@ -0,0 +1,12 @@
+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 portaudio19-dev \
+    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
+RUN chmod +x launch.sh
+ENTRYPOINT ["sh", "-c", "./launch.sh"]

README.md

@@ -1,42 +1,97 @@
 # AllTalk TTS
 AllTalk is an updated version of the Coqui_tts extension for Text Generation web UI. Features include:
 
-- **Custom Start-up Settings:** Adjust your default start-up settings. [Screenshot](https://github.com/erew123/alltalk_tts#screenshots)
-- **Narrarator:** Use different voices for main character and narration. [Example Narration](https://vocaroo.com/18nrv7FR6wuA)
-- **Low VRAM mode:** Great for people with small GPU memory or if your VRAM is filled by your LLM. [Screenshot](https://github.com/erew123/alltalk_tts#screenshots)
-- **DeepSpeed:** A 3-4x performance boost generating TTS. [DeepSpeed Windows/Linux Instructions](https://github.com/erew123/alltalk_tts?tab=readme-ov-file#deepspeed-installation-options) [Screenshot](https://github.com/erew123/alltalk_tts/assets/35898566/548619c8-5f1b-47d0-a73d-54d2fee3f3db)
+- **Can be run as a** [standalone](https://github.com/erew123/alltalk_tts/#-quick-setup-text-generation-webui--standalone-installation) **or part of** [Text-generation-webui](https://github.com/erew123/alltalk_tts/#-quick-setup-text-generation-webui--standalone-installation) **using the a quick setup utility**
+- **Model Finetuning:** Train the model specifically on a voice of your choosing for better reproduction.
 - **Local/Custom models:** Use any of the XTTSv2 models (API Local and XTTSv2 Local).
-- **Optional wav file maintenance:** Configurable deletion of old output wav files. [Screenshot](https://github.com/erew123/alltalk_tts#screenshots)
-- **Finetuning** Train the model specifically on a voice of your choosing for better reproduction.
-- **Documentation:** Fully documented with a built in webpage. [Screenshot](https://github.com/erew123/alltalk_tts#screenshots)
-- **Console output** Clear command line output for any warnings or issues.
-- **API Suite and 3rd Party support via JSON calls** Can be used with 3rd party applications via JSON calls.
-- **Can be run as a standalone app** Not just inside of text-generation-webui.
+- **Bulk TTS Generator/Editor:** Generate hours of TTS into one big file or have something read back to you [demo](https://www.youtube.com/watch?v=hunvXn0mLzc).
+- **DeepSpeed:** A 2-3x performance boost generating TTS. [Screenshot](https://github.com/erew123/screenshots/raw/main/deepspeed.jpg)
+- **Low VRAM mode:** Great for people with small GPU memory or if your VRAM is filled by your LLM.
+- **Custom Start-up Settings:** Adjust your default start-up settings. [Screenshot](https://github.com/erew123/screenshots/raw/main/settingsanddocs.jpg)
+- **Narrarator:** Use different voices for main character and narration. [Example Narration](https://vocaroo.com/18nrv7FR6wuA)
+- **Optional wav file maintenance:** Configurable deletion of old output wav files. [Screenshot](https://github.com/erew123/screenshots/raw/main/settingsanddocs.jpg)
+- **Documentation:** Fully documented with a built in webpage. [Screenshot](https://github.com/erew123/screenshots/raw/main/settingsanddocs.jpg)
+- **Clear Console output:** Clear command line output for any warnings or issues.
+- **API Suite and 3rd Party support via JSON calls:** Can be used with 3rd party applications via JSON calls.
+- **SillyTavern integration:** Full integration with SillyTavern. [Screenshot](https://github.com/erew123/screenshots/raw/main/sillytavern.jpg)
 
-## Index
+### Index
 
-- 🟩 [Installation](https://github.com/erew123/alltalk_tts?#-installation-on-text-generation-web-ui)
+- 🟩 [Installation](https://github.com/erew123/alltalk_tts/#-quick-setup-text-generation-webui--standalone-installation)
 - 🟪 [Updating & problems with updating](https://github.com/erew123/alltalk_tts?#-updating)
 - 🟫 [Screenshots](https://github.com/erew123/alltalk_tts#-screenshots)
 - 🟨 [Help with problems](https://github.com/erew123/alltalk_tts?#-help-with-problems)
 - ⚫ [Finetuning a model](https://github.com/erew123/alltalk_tts?#-finetuning-a-model)
 - 🔵🟢🟡 [DeepSpeed Installation (Windows & Linux)](https://github.com/erew123/alltalk_tts?#-deepspeed-installation-options)
+- ⬜ [AllTalk TTS Generator](https://github.com/erew123/alltalk_tts?#-alltalk-tts-generator)
 - 🟠 [API Suite and JSON-CURL](https://github.com/erew123/alltalk_tts?#-api-suite-and-json-curl)
 - 🔴 [Future to-do list & Upcoming updates](https://github.com/erew123/alltalk_tts?#-future-to-do-list)
 
-#### Updates
-The latest build (13 Dec 2023) has had the entire text filtering engine and narration engine rebuilt from scratch. It's highly complicated how its actually working, but the end result it a much clearer TTS output and much better control over the narrator option and how to handle text that isnt within quotes or asterisks. It does however mean you need to ensure your character card is set up correctly if using the narrator function. Details are below in the installation notes.
+### 🔄 Feature requests, Updates & Bug fixes
+Please check the below link to find a list of all recent updates and changes.
+####     🔄 **Updates list & bug fixes list** can be found [here](https://github.com/erew123/alltalk_tts/issues/25)
+####     🔄 **Current Feature request list** can be found [here](https://github.com/erew123/alltalk_tts/discussions/74)
 
-DeepSpeed **v11.2** can be installed within the **default text-generation-webui Python 3.11 environment**. Installs in custom Python environments are possible, but can be more complicated. Instructions [here](https://github.com/erew123/alltalk_tts##deepspeed-installation-options) (or scroll down).
+I welcome your input and ideas for new features, suggestions, and improvements. Feel free to share your thoughts and collaborate in the discussions area. If you find this project valuable and would like to show your appreciation, you can make a donation on my [Ko-fi](https://ko-fi.com/erew123) page. Your support goes a long way in ensuring that I can continue to deliver even better features and experiences.
+
+**ERROR** `ImportError: cannot import name 'SampleOutput' from 'transformers.generation.utils'` please see this issue [here](https://github.com/erew123/alltalk_tts/issues/82)
+
+### 🟩 Quick Setup (Text-generation-webui & Standalone Installation)
+For Windows 10/11 and Linux machines there is a quick setup script. Please note, Python on Windows requires you install the C++ development [tools](https://wiki.python.org/moin/WindowsCompilers) to compile packages, further details can be found in the help section.
+
+Click to expand the correct section below:
+<details>
+	<summary>QUICK SETUP - Text-Generation-webui</summary><br>
+
+ If you wish to see this as a video, please go [here](https://www.youtube.com/watch?v=icn2XS5rUH8)
+1) To download the AllTalk setup you can either:
+   - A) Go to the [Releases page](https://github.com/erew123/alltalk_tts/releases) and download the latest `alltalk_tts.zip` then extract it to the text-generation-webui extensions folder<br>e.g. `\text-generation-webui\extensions\alltalk_tts\`.<br><br>
+   - B) Go to a terminal/console, move into the `\text-generation-webui\extensions\` folder<br>and `git clone https://github.com/erew123/alltalk_tts`<br><br>
+3) In a terminal/command prompt, in the text-generation-webui folder you will start its Python environment with either `cmd_windows.bat` or `./cmd_linux.sh`
+4) Move into the AllTalk folder e.g. `cd extensions` then `cd alltalk_tts`
+5) Start the AllTalk setup script `atsetup.bat` or `./atsetup.sh`
+6) Follow the on-screen prompts and install the correct requirements files that you need. It's recommended to test AllTalk works before installing DeepSpeed.
+
+   Any time you need to make changes to AllTalk, or use Finetuning etc, always start the Text-generation-webui Python environment first.
+
+   Please read the `🟩 Other installation notes` (also additional voices are available there).
+
+   Finetuning & DeepSpeed have other installation requirements (depending on your OS) so please read any instructions in the setup utility and refer back here to this page for detailed instructions (as needed).<br><br>
+</details>
+<details>
+	<summary>QUICK SETUP - Standalone Installation</summary><br>
+
+ If you wish to see this as a video, please go [here](https://www.youtube.com/watch?v=AQYCccDRbaY)
+1) To download the AllTalk setup you can either:
+   - A) Go to the [Releases page](https://github.com/erew123/alltalk_tts/releases) and download the latest `alltalk_tts.zip` and extract it to the folder of your choice<br>e.g. `C:\myfiles\alltalk_tts\`.<br><br>
+   - B) Go to a terminal/console, move into the folder of your choice e.g `C:\myfiles\` folder<br>and `git clone https://github.com/erew123/alltalk_tts`<br><br>
+4) In a terminal/command prompt, move into the AllTalk folder e.g. `cd alltalk_tts`
+5) Start the AllTalk setup script `atsetup.bat` or `./atsetup.sh`
+6) Follow the on-screen prompts and install the correct requirements files that you need. It's recommended to test AllTalk works before installing DeepSpeed.
+
+   DeepSpeed on Windows machines will be installed as standard. Linux machines have other requirements which are detailed within the setup utility and on this page.
+
+   Please read the `🟩 Other installation notes` (also additional voices are available there).
+
+   You cannot have a dash in your folder path e.g. `c:\myfiles\alltalk_tts-main` so please ensure you remove any `-` from your folder path. This is a conda specific requirement and will cause AllTalk not to start at all.
+
+   Finetuning has other installation requirements so please read any instructions in the setup utility and refer back here to this page for detailed instructions.<br><br>
+</details>
+
+### 🟩 Manual Installation - As part of Text generation web UI
+On Mac's or if you wish to perform a manual installation. Click to expand the correct section below:
+<details>
+	<summary>MANUAL INSTALLATION - Text-Generation-webui</summary><br>
 
-## 🟩 Installation on Text generation web UI
 This has been tested on the current Dec 2023 release of Text generation webUI. If you have not updated it for a while, you may wish to update Text generation webUI, [instructions here](https://github.com/oobabooga/text-generation-webui?tab=readme-ov-file#how-to-install)
 
+- If you want to watch a video of how to do the below [link here](https://youtu.be/9BPKuwaav5w)<br>
+
 1) In a command prompt/terminal window you need to move into your Text generation webUI folder:<br><br>
 `cd text-generation-webui`
 
-2) Start the Text generation webUI Python environment for your OS:<br><br>
-`cmd_windows.bat`, `./cmd_linux.sh`, `cmd_macos.sh` or `cmd_wsl.bat`
+2) Start the Text generation webUI Python environment for your OS with whichever **one** of the below is correct for your OS:<br><br>
+`cmd_windows.bat`, `./cmd_linux.sh`, `cmd_macos.sh` or `cmd_wsl.bat`<br><br> Loading Text-generation-webui's Python Environment is $\textcolor{red}{\textsf{VERY IMPORTANT}}$. If you are uncertain what a loaded Python environment looks like, image [here](https://github.com/erew123/alltalk_tts/issues/25#issuecomment-1869344442) and video [here](https://www.youtube.com/watch?v=9BPKuwaav5w)
 
 3) Move into your extensions folder:<br><br>
 `cd extensions`
@@ -47,47 +102,120 @@ This has been tested on the current Dec 2023 release of Text generation webUI. I
 5) Move into the **alltalk_tts** folder:<br><br>
 `cd alltalk_tts`
 
-6) Install the requirements that are correct for your machine:<br><br>
+6) Install one of the two requirements files. Whichever one of the two is correct for your machine type:<br><br>
 **Nvidia graphics card machines** - `pip install -r requirements_nvidia.txt`<br><br>
 **Other machines (mac, amd etc)** - `pip install -r requirements_other.txt`
 
 7) **(Optional DeepSpeed)** If you have an Nvidia Graphics card on a system running Linux or Windows and wish to use **DeepSpeed** please follow these instructions [here](https://github.com/erew123/alltalk_tts?#-deepspeed-installation-options). **However**, I would highly reccommend before you install DeepSpeed, you start text-generation-webui up, confirm AllTalk starts correctly and everything is working, as DeepSpeed can add another layer of complications troubleshooting any potential start-up issues. If necessary you can `pip uninstall deepspeed`.
 
-8) You can now start move back to the main Text generation webUI folder `cd ..` (a few times), start Text generation webUI (`start_windows.bat`,`./start_linux.sh`, `start_macos.sh` or `start_wsl.bat`)  and load the AllTalk extension in the Text generation webUI **session** tab.
-   
-9) Please read the note below about start-up times and also the note about ensuring your character cards are set up [correctly](https://github.com/erew123/alltalk_tts#the-one-thing-i-cant-easily-work-around)
+8) You can now start move back to the main Text generation webUI folder `cd ..` (a few times), start Text generation webUI with whichever **one** of the startup scripts is correct for your OS (`start_windows.bat`,`./start_linux.sh`, `start_macos.sh` or `start_wsl.bat`)  and load the AllTalk extension in the Text generation webUI **session** tab.<br><br> Starting Text-generation-webui with its correct start-up script is $\textcolor{red}{\textsf{VERY IMPORTANT}}$.
+
+   Any time you need to make changes to AllTalk, or use Finetuning etc, always start the Text-generation-webui Python environment first.
+
+   Please read the `🟩 Other installation notes` (also additional voices are available there).
+
+   Finetuning & DeepSpeed have other installation requirements (depending on your OS) so please read any instructions in the setup utility and refer back here to this page for detailed instructions (as needed).<br><br>
+
+</details>
+
+### 🟩 Manual Installation - As a Standalone Application
+On Mac's or if you wish to perform a manual installation. Click to expand the correct section below:
+<details>
+	<summary>MANUAL INSTALLATION - I want to run AllTalk as a standalone when installed with Text-generation-webui</summary><br>
+	
+If you already have AllTalk as a extension of Text-generation-webui, and wish to run it as standalone, load Text-generation-webui's Python environment `cmd_windows.bat`, `./cmd_linux.sh`, `cmd_macos.sh` or `cmd_wsl.bat`, move into the AllTalk folder `cd extensions` > `cd alltalk_tts` and start AllTalk with `python script.py`. There is nothing beyond this you would need to do.
+</details>
+<details>
+	<summary>MANUAL INSTALLATION - I wish to do a custom install of AllTalk</summary><br>
+	
+AllTalk will run as a standalone app, as long as you install its requirements files into whatever Python environment you are using. You can follow the steps to install the AllTalk's requirements into whatever Python environment you wish. Because I dont know what Python environment you are wanting to use, I can only give you a loose set of installation instructions. 
+
+Please note, at time of writing, the TTS engine requires Python **3.9.x** to **3.11.x** [TTS Engine details here](https://pypi.org/project/TTS/). AllTalk and its requirements are tested on Python **3.11.x**.
+
+#### 🟩 A very quick understanding of Python Environments.
+Different Python applications have different requirements, some of those requirement’s conflict with other Python applications requirements. To work around this problem, you can create different Python environments that remain separated from one another. A simple way of looking at Python environments, is just like how your house has different rooms for specific purposes (Kitchen, Bathroom, Bedroom etc). You can create a Python environment that is built/customised specifically for your current applications needs/purposes and will **not** interfere with any other Python applications environments/installations. <br><br>If you are adept at managing Python environments, have an existing Python environment and know that you won’t cause any conflicts by installing AllTalk's requirements within that Python environment, then load up your Python environment and install the requirements. For everyone else, here is a basic guide on installing AllTalk in its own custom Python environment (there will be small variations between OS's, but the principle is the same).
+
+**Note:** A standard VENV can cause module path issues, hence Conda is the correct method to create a Python environment for AllTalk. 
+
+#### 🟩 Building a custom Python Environment with Miniconda
+1) Open a terminal/command prompt, and confirm that both `python --version` and `pip` both work. Neither of them should give an error message. If they do you may need to install Python (and maybe Pip).<br><br>[Python Website](https://www.python.org/downloads/)<br>[Pip Website](https://pip.pypa.io/en/stable/installation/)<br><br>Once you have those working you can now continue on.<br><br>
+
+2) Assuming you don't already have Miniconda installed, we will need to download and install Minoconda as this is what we will use to build our custom Python environment.<br><br>[Miniconda Website](https://docs.conda.io/projects/miniconda/en/latest/)<br><br>Download the Miniconda version that is correct for your OS and then install it. Miniconda will create some items in your Start Menu or Application Launcher called something like `Anaconda Prompt`<br><br> You will start the `Anaconda Prompt` and your prompt in your terminal/command prompt will say something like: <br><br>`(base) C:\users\myaccount\>`<br><br> The important bit is that it has the `(base)`, the location after that doesn't matter. `(base)` signifies we are in the base conda Python environment and can now create custom Python environments with Conda.<br><br>
+  
+3) In your Anaconda Prompt command prompt/terminal, move into the folder where you want to download AllTalk to and then git clone this repository. For simplicity I am going to assume that location is `c:\myfiles\`. So you will:<br><br>`cd myfiles`<br><br>`git clone https://github.com/erew123/alltalk_tts`<br><br>
+
+4) Now we will create our custom Conda Python 3.11.5 environment and give it the name alltalkenv by typing the following at the prompt:<br><br>`conda create --name alltalkenv python=3.11.5`<br><br>You will be prompted if you want to continue and you say yes.<br><br>Once that process has completed, we now need to change from the `(base)` Conda Python environment, to our newly created `(alltalkenv)` environment. So type the following:<br><br>`conda activate alltalkenv`<br><br>Your prompt should now change from `(base) C:\myfiles\>` to `(alltalkenv) C:\myfiles\>`<br><br>
+
+5) **If you are NOT using an Nvidia card and CUDA, skip to step 6**. To force PyTorch to install with CUDA, perform the following:<br><br>`pip cache purge` (Clear the current Pip cache)<br><br>`pip uninstall torch torchaudio` (Uninstall Torch and Torchaudio from the `alltalkenv` environment)<br><br>
+You can now either install the CUDA 11.8 or 12.1 version of Torch and Torchaudio with **one** of the following<br><br>**CUDA 11.8** > `pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118`<br><br>**CUDA 12.1** > `pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121`<br><br>
+
+6) Move into the alltalk_tts folder and install one of the two requirements files. Whichever one of the two is correct for your machine type:<br><br>`cd alltalk_tts`<br><br>
+**Nvidia graphics card machines** - `pip install -r requirements_nvidia.txt`<br><br>
+**Other machines (mac, amd etc)** - `pip install -r requirements_other.txt`<br><br>
+
+7) Start AllTalk with `python script.py`<br><br>
+
+🟩 Anytime you wish to use AllTalk, update its requirements, install some other requirements such as DeepSpeed, you will need to start its Conda Python Environment in the terminal/prompt, which you will do with `conda activate alltalkenv` as long as the Conda executable is accessible at the command prompt/terminal you are in.<br><br>It is fully possible to create a batch file or script file that you can use as a launcher from your Start Menu/Application Launcher that will start the environment and AllTalk for you. 
+
+Deepspeed and other such things can be installed. Please read the relevant instructions for those items, however, make the relevant changes to load your correct Python environment when installing any requirements files and starting AllTalk.<br><br>
+
+   Any time you need to make changes to AllTalk, or use Finetuning etc, always start your Python environment first.
+
+   Please read the `🟩 Other installation notes` (also additional voices are available there).
+
+   Finetuning & DeepSpeed have other installation requirements (depending on your OS) so please read any instructions in the setup utility and refer back here to this page for detailed instructions (as needed).<br><br>
+
+</details>
 
-10) Some extra voices downloadable [here](https://drive.google.com/file/d/1bYdZdr3L69kmzUN3vSiqZmLRD7-A3M47/view?usp=drive_link)
 
 #### 🟩 Other installation notes
-On first startup, AllTalk will download the Coqui XTTSv2 2.0.2 model to its **models** folder (1.8GB space required). Check the command prompt/terminal window if you want to know what its doing. After it says "Model Loaded" the Text generation webUI is usually available on its IP address a few seconds later, for you to connect to in your browser.
+On first startup, AllTalk will download the Coqui XTTSv2 2.0.2 model to its **models** folder (1.8GB space required). Check the command prompt/terminal window if you want to know what its doing. After it says "Model Loaded" the Text generation webUI is usually available on its IP address a few seconds later, for you to connect to in your browser. If you are running a headless system and need to change the IP, please see the Help with problems section down below.
 
 Once the extension is loaded, please find all documentation and settings on the link provided in the interface (as shown in the screenshot below).
 
 **Where to find voices** https://aiartes.com/voiceai or https://commons.wikimedia.org/ or interviews on youtube etc. Instructions on how to cut down and prepare a voice sample are within the built in documentation.
 
-#### 🟩 The one thing I cant easily work around
-Narrator function specific - With a RP chat with your AI, **on your character card** `parameters menu` > `character tab` > `greeting` make sure that anything in there that is the **narrator is in asterisks** and anything **spoken is in double quotes**, then hit the `save` (💾) button. Greeting paragraphs/sentences are handled differently from how the AI sends text and so its difficut to account for them both.
+Please read the note below about start-up times and also the note about ensuring your character cards are set up [correctly](https://github.com/erew123/alltalk_tts#-a-note-on-character-cards--greeting-messages)
 
-I could force a delimeter in at this stage, but I know it would/may affect things further down the line in the chat and I need a good think about that before just making a change. This issue **only** affects the greeting card/start of conversation and the "example" card that comes with text-generation-webui suffers this issue (if you want to try it for yourself). So you would put double quotes around like this (from the example card):
+Some extra voices for AllTalk are downloadable [here](https://drive.google.com/file/d/1bYdZdr3L69kmzUN3vSiqZmLRD7-A3M47/view?usp=drive_link) and [here](https://drive.google.com/file/d/1CPnx1rpkuKvVj5fGr9OiUJHZ_e8DfTzP/view)
 
-`"`*Hey! I'm so excited to finally meet you. I've heard so many great things about you and I'm eager to pick your brain about computers. I'm sure you have a wealth of knowledge that I can learn from.*`"`
+#### 🟩 A note on Character Cards & Greeting Messages
+Messages intended for the Narrator should be enclosed in asterisks `*` and those for the character inside quotation marks `"`. However, AI systems often deviate from these rules, resulting in text that is neither in quotes nor asterisks. Sometimes, text may appear with only a single asterisk, and AI models may vary their formatting mid-conversation. For example, they might use asterisks initially and then switch to unmarked text. A properly formatted line should look like this:
 
-## 🟪 Updating
+`"`Hey! I'm so excited to finally meet you. I've heard so many great things about you and I'm eager to pick your brain about computers.`"` `*`She walked across the room and picked up her cup of coffee`*`
+
+Most narrator/character systems switch voices upon encountering an asterisk or quotation marks, which is somewhat effective. AllTalk has undergone several revisions in its sentence splitting and identification methods. While some irregularities and AI deviations in message formatting are inevitable, any line beginning or ending with an asterisk should now be recognized as Narrator dialogue. Lines enclosed in double quotes are identified as Character dialogue. For any other text, you can choose how AllTalk handles it: whether it should be interpreted as Character or Narrator dialogue (most AI systems tend to lean more towards one format when generating text not enclosed in quotes or asterisks).
+
+With improvements to the splitter/processor, I'm confident it's functioning well. You can monitor what AllTalk identifies as Narrator lines on the command line and adjust its behavior if needed (Text Not Inside - Function).
+
+### 🟪 Updating
+<details>
+	<summary>UPDATING - I am using Text-Generation-webui</summary><br>
 This is pretty much a repeat of the installation process. 
 
 1) In a command prompt/terminal window you need to move into your Text generation webUI folder:<br><br>
-`cd text-generation-webui`
+`cd text-generation-webui` and start the Python environment for your OS with whichever **one** of the below is correct for your OS:<br><br>
+`cmd_windows.bat`, `./cmd_linux.sh`, `cmd_macos.sh` or `cmd_wsl.bat`<br>
 
-2) Move into your extensions and alltalk_tts folder:<br><br>
-`cd extensions` then `cd alltalk_tts`
+2) Move into your extensions and alltalk_tts folder e.g. `cd extensions` then `cd alltalk_tts`
 
-3) At the command prompt/terminal, type:<br><br>
-`git pull`
+3) At the command prompt/terminal, type `git pull`
 
 4) Install the correct requirements for your machine:<br><br>
 **Nvidia graphics card machines** - `pip install -r requirements_nvidia.txt`<br><br>
-**Other machines (mac, amd etc)** - `pip install -r requirements_other.txt`
+**Other machines (mac, amd etc)** - `pip install -r requirements_other.txt`<br><br>
+</details>
+<details>
+	<summary>UPDATING - I am running as a Standalone Application</summary><br>
+	
+1) In a command prompt/terminal window you need to move into your `alltalk_tts` folder and run `start_environment.bat` or `/start_environment.sh` to load the Python environment.
+
+2) At the command prompt/terminal, type `git pull` and wait for it to complete the download.
+
+3) Install the correct requirements for your machine:<br><br>
+**Nvidia graphics card machines** - `pip install -r requirements_nvidia.txt`<br><br>
+**Other machines (mac, amd etc)** - `pip install -r requirements_other.txt`<br><br>
+</details>
 
 #### 🟪 Updating "git pull" error
 
@@ -99,6 +227,7 @@ I did leave a mistake in the `/extensions/alltalk_tts/.gitignore` file at one po
 voices/*.*
 models/*.*
 outputs/*.*
+finetune/*.*
 config.json
 confignew.json
 models.json
@@ -138,15 +267,17 @@ You can now start text-generation-webui or AllTalk (standalone) and it should st
 Assuming its all working fine and you are happy, you can delete the old alltalk_tts.old folder.
 </details>
 
-## 🟫 Screenshots
-|![image](https://github.com/erew123/alltalk_tts/assets/35898566/4ca9b4c7-60ce-4ac6-82e5-fd1989b84644) | ![image](https://github.com/erew123/alltalk_tts/assets/35898566/548619c8-5f1b-47d0-a73d-54d2fee3f3db) |
-|:---:|:---:|
-|![image](https://github.com/erew123/alltalk_tts/assets/35898566/b0e13dba-c6b1-4ab7-845d-244ac1158330) |  ![image](https://github.com/erew123/alltalk_tts/assets/35898566/e35e987c-543a-486b-b4fb-ee6ebe6f59c6) |
-|![image](https://github.com/erew123/alltalk_tts/assets/35898566/68edc968-bdd2-4f98-9d56-b9ca40decf26) | ![image](https://github.com/erew123/alltalk_tts/assets/35898566/eb5e617b-2345-418d-8267-a9d30f705a10) |
+### 🟫 Screenshots
+|![image](https://github.com/erew123/screenshots/raw/main/textgensettings.jpg) | ![image](https://github.com/erew123/screenshots/raw/main/setuputilitys.jpg) | ![image](https://github.com/erew123/screenshots/raw/main/deepspeed.jpg) |![image](https://github.com/erew123/screenshots/raw/main/textgen.jpg) |
+|:---:|:---:|:---:|:---:|
+|![image](https://github.com/erew123/screenshots/raw/main/settingsanddocs.jpg) | ![image](https://github.com/erew123/screenshots/raw/main/finetune1.jpg) | ![image](https://github.com/erew123/screenshots/raw/main/finetune2.jpg) |![image](https://github.com/erew123/screenshots/raw/main/sillytavern.jpg)|
 
-## 🟨 Help with problems
+### 🟨 Help with problems
+
+#### &nbsp;&nbsp;&nbsp;&nbsp; 🔄 **Minor updates/bug fixes list** can be found [here](https://github.com/erew123/alltalk_tts/issues/25)
 
 #### 🟨 How to make a diagnostics report file
+If you are on a Windows machine or a Linux machine, you should be able to use the `atsetup.bat` or `./atsetup.sh` utility to create a diagnositcs file. If you are unable to use the `atsetup` utility, please follow the instructions below.
 <details>
 	<summary>Click to expand</summary>
 	
@@ -174,7 +305,7 @@ Assuming its all working fine and you are happy, you can delete the old alltalk_
 **A)** Its trying to load the voice model into your graphics card VRAM (assuming you have a Nvidia Graphics card, otherwise its your system RAM)<br>
 **B)** Its trying to start up the mini-webserver and send the "ready" signal back to the main process.
 
-Before giving other possibilities a go, some people with **old machines** are finding their startup times are **very** slow 2-3 minutes. Ive extended the allowed time within the script from 1 minute to 2 minutes. **If you have an older machine** and wish to try extending this further, you can do so by editing `script.py` and changing line 251 `timeout = 120` changing the timeout to a larger value e.g `timeout = 240` (4 minutes).
+Before giving other possibilities a go, some people with **old machines** are finding their startup times are **very** slow 2-3 minutes. Ive extended the allowed time within the script from 1 minute to 2 minutes. **If you have an older machine** and wish to try extending this further, you can do so by editing `script.py` and changing `startup_wait_time = 120` (120 seconds, aka 2 minutes) at the top of the script.py file, to a larger value e.g `startup_wait_time = 240` (240 seconds aka 4 minutes).
 
 **Note:** If you need to create a support ticket, please create a `diagnostics.log` report file to submit with a support request. Details on doing this are above.
 
@@ -203,6 +334,34 @@ Other possibilities for this issue are:
 11) You have built yourself a custom Python environment and something is funky with it. This is very hard to diagnose as its not a standard environment. You may want to updating text-generation-webui and re installing its requirements file (whichever one you use that comes down with text-generation-webui).
 </details>
 
+#### 🟨 Windows & Python requirements for compiling packages
+
+`ERROR: Microsoft Visual C++ 14.0 or greater is required` or `ERROR: Could not build wheels for TTS.` or `ModuleNotFoundError: No module named 'TTS`
+
+<details>
+	<summary>Click to expand</summary><br>
+
+ Python requires that you install C++ development tools on Windows. This is detailed on the [Python site here](https://wiki.python.org/moin/WindowsCompilers). You would need to install `MSVCv142 - VS 2019 C++ x64/x86 build tools` and `Windows 10/11 SDK` from the C++ Build tools section. 
+ 
+ You can get hold of the **Community** edition [here](https://visualstudio.microsoft.com/downloads/) the during installation, selecting `C++ Build tools` and then `MSVCv142 - VS 2019 C++ x64/x86 build tools` and `Windows 10/11 SDK`. 
+
+![image](https://github.com/erew123/screenshots/raw/main/pythonrequirementswindows.jpg)
+ 
+</details>
+
+#### 🟨 I think AllTalks requirements file has installed something another extension doesn't like
+<details>
+	<summary>Click to expand</summary><br>
+	
+Ive paid very close attention to **not** impact what Text-generation-webui is requesting on a factory install. This is one of the requirements of submitting an extension to Text-generation-webui. If you want to look at a comparison of a factory fresh text-generation-webui installed packages (with cuda 12.1, though AllTalk's requirements were set on cuda 11.8) you can find that comparison [here](https://github.com/erew123/alltalk_tts/issues/23). This comparison shows that AllTalk is requesting the same package version numbers as Text-generation-webui or even lower version numbers (meaning AllTalk will not update them to a later version). What other extensions do, I cant really account for that.
+
+I will note that the TTS engine downgrades Pandas data validator to 1.5.3 though its unlikely to cause any issues. You can upgrade it back to text-generation-webui default (december 2023) with `pip install pandas==2.1.4` when inside of the python environment. I have noticed no ill effects from it being a lower or higher version, as far as AllTalk goes. This is also the same behaviour as the Coqui_tts extension that comes with Text-generation-webui.
+
+Other people are reporting issues with extensions not starting with errors about Pydantic e.g. ```pydantic.errors.PydanticImportError: BaseSettings` has been moved to the pydantic-settings package. See https://docs.pydantic.dev/2.5/migration/#basesettings-has-moved-to-pydantic-settings for more details.```
+
+Im not sure if the Pydantic version has been recently updated by the Text-generation-webui installer, but this is nothing to do with AllTalk. The other extension you are having an issue with, need to be updated to work with Pydantic 2.5.x. AllTalk was updated in mid december to work with 2.5.x. I am not specifically condoning doing this, as it may have other knock on effects, but within the text-gen Python environment, you can use `pip install pydantic==2.5.0` or `pip install pydantic==1.10.13` to change the version of Pydantic installed.
+</details>
+
 #### 🟨 I activated DeepSpeed in the settings page, but I didnt install DeepSpeed yet and now I have issues starting up
 <details>
 	<summary>Click to expand</summary><br>
@@ -212,6 +371,15 @@ You can either follow the [Problems Updating](https://github.com/erew123/alltalk
 If you want to use DeepSpeed, you need an Nvidia Graphics card and to install DeepSpeed on your system. Instructions are [here](https://github.com/erew123/alltalk_tts#-deepspeed-installation-options)
 </details>
 
+#### 🟨 I am running a Headless system and need to change the IP Address manually as I cannot reach the config page.
+<details>
+	<summary>Click to expand</summary><br>
+	
+To do this you can edit the `confignew.json` file within the `alltalk_tts` folder. You would look for `"ip_address": "127.0.0.1",` and change the `127.0.0.1` to your chosen IP address,then save the file and start AllTalk.<br><br>
+
+When doing this, be careful not to impact the formatting of the JSON file. Worst case, you can re-download a fresh copy of `confignew.json` from this website and that will put you back to a factory setting.
+</details>
+
 #### 🟨 I am having problems updating/some other issue where it wont start up/Im sure this is a bug
 <details>
 	<summary>Click to expand</summary><br>
@@ -221,6 +389,14 @@ Please see [Problems Updating](https://github.com/erew123/alltalk_tts#-problems-
 Also, is your text-generation-webui up to date? [instructions here](https://github.com/oobabooga/text-generation-webui?tab=readme-ov-file#how-to-install)
 </details>
 
+#### 🟨 Standalone Install - start_{youros}.xx opens and closes instantly and AllTalk doesnt start
+<details>
+	<summary>Click to expand</summary><br>
+
+This is more than likely caused by having a `-` in your folder path e.g. `c:\myfiles\alltalk_tts-main`. In this circumstance you would be best renaming the folder to remove the `-` from its name e.g. `c:\myfiles\alltalk_tts`, delete the `alltalk_environment` folder and `start_alltalk.bat` or `start_alltalk.sh` and then re-run `atsetup` to re-create the environment and startup files. 
+
+</details>
+
 #### 🟨 I am having problems getting AllTalk to start after changing settings or making a custom setup/model setup.
 
 <details>
@@ -237,13 +413,33 @@ I would suggest following [Problems Updating](https://github.com/erew123/alltalk
 As far as I am aware, these are to do with the chrome browser the gradio text-generation-webui in some way. I raised an issue about this on the text-generation-webui [here](https://github.com/oobabooga/text-generation-webui/issues/4788) where you can see that AllTalk is not loaded and the messages persist. Either way, this is more a warning than an actual issue, so shouldnt affect any functionality of either AllTalk or text-generation-webui, they are more just an annoyance.
 </details>
 
-## ⚫ Finetuning a model
+#### 🟨 I have multiple GPU's and I have problems running Finetuning
+
+<details>
+	<summary>Click to expand</summary><br>
+	
+Finetuning pulls in various other scripts and some of those scripts can have issues with multiple Nvidia GPU's being present. Until the people that created those other scripts fix up their code, there is a workaround to temporarily tell your system to only use the 1x of your Nvidia GPU's. To do this:
+
+- **Windows** - You will start the script with `set CUDA_VISIBLE_DEVICES=0 && python finetune.py`<br>
+After you have completed training, you can reset back with `set CUDA_VISIBLE_DEVICES=`<br>
+   
+- **Linux** - You will start the script with `CUDA_VISIBLE_DEVICES=0 python finetune.py`<br>
+After you have completed training, you can reset back with `unset CUDA_VISIBLE_DEVICES`<br>
+
+Rebooting your system will also unset this. The setting is only applied temporarily.
+
+Depending on which of your Nvidia GPU's is the more powerful one, you can change the `0` to `1` or whichever of your GPU's is the most powerful.
+
+</details>
+
+### ⚫ Finetuning a model
 If you have a voice that the model doesnt quite reproduce correctly, or indeed you just want to improve the reproduced voice, then finetuning is a way to train your "XTTSv2 local" model **(stored in `/alltalk_tts/models/xxxxx/`)** on a specific voice. For this you will need:
 
-- An Nvidia graphics card
+- An Nvidia graphics card. (Please see this [note](https://github.com/erew123/alltalk_tts#-i-have-multiple-gpus-and-i-have-problems-running-finetuning) if you have multiple Nvidia GPU's).
 - To install a few portions of the Nvidia CUDA 11.8 Toolkit (this will not impact text-generation-webui's cuda setup.
 - 18GB of disk space free (most of this is used temporarily)
 - At least 2 minutes of good quality speech from your chosen speaker in mp3, wav or flacc format, in one or more files (have tested as far as 20 minutes worth of audio).
+- As a side note, many people seem to think that the Whisper v2 model (used on Step 1) is giving better results at generating training datasets, so you may prefer to try that, as opposed to the Whisper 3 model.
 
 #### ⚫ How will this work/How complicated is it?
 Everything has been done to make this as simple as possible. At its simplest, you can literally just download a large chunk of audio from an interview, and tell the finetuning to strip through it, find spoken parts and build your dataset. You can literally click 4 buttons, then copy a few files and you are done. At it's more complicated end you will clean up the audio a little beforehand, but its still only 4x buttons and copying a few files.
@@ -251,20 +447,36 @@ Everything has been done to make this as simple as possible. At its simplest, yo
 #### ⚫ The audio you will use
 I would suggest that if its in an interview format, you cut out the interviewer speaking in audacity or your chosen audio editing package. You dont have to worry about being perfect with your cuts, the finetuning Step 1 will go and find spoken audio and cut it out for you. Is there is music over the spoken parts, for best quality you would cut out those parts, though its not 100% necessary. As always, try to avoid bad quality audio with noises in it (humming sounds, hiss etc). You can try something like [Audioenhancer](https://audioenhancer.ai/) to try clean up noisier audio. There is no need to down-sample any of the audio, all of that is handled for you. Just give the finetuning some good quality audio to work with. 
 
+#### ⚫ A note about anonymous training Telemetry information & disabling it
+Portions of Coqui's TTS trainer scripts gather anonymous training information which you can disable. Their statement on this is listed [here](https://github.com/coqui-ai/Trainer?tab=readme-ov-file#anonymized-telemetry). Although I have tried to pass `TRAINER_TELEMETRY=0` through AllTalk, it appears you will have to set this manually if you wish to finetune on a non-internet enabled computer or disable the anonymous data being sent. You can do this by:
+
+- On Windows by typing `set TRAINER_TELEMETRY=0`
+- On Linux & Mac by typing `export TRAINER_TELEMETRY=0`
+
+Before you start `finetune.py`. You will now be able to finetune offline and no anonymous training data will be sent. 
+
 #### ⚫ Important requirements CUDA 11.8
-As mentioned you must have a small portion of the Nvidia CUDA Toolkit **11.8** installed. Not higher or lower versions. Specifically **11.8**. You do not have to uninstall any other versions, change any graphics drivers, reinstall torch or anything like that. To keep the download+install as small as possible, you will need to:
-- Download the **xxx (network)** install of the Nvidia Cuda Toolkit 11.8 from [here](https://developer.nvidia.com/cuda-11-8-0-download-archive)
-- When you run the installation, select **Custom Advanced** as your installation type. Uncheck `CUDA`, `Other Components` and `Driver Components` at the top then expand `CUDA` > `Development` > `Compiler` > and select `nvcc` then expand `Libraries` and select `CUBLAS`
-- Back at the top of `CUDA` expand `Runtime` > `Libraries` and select `CUBLAS`. You can now next through the install.
+As mentioned you must have a small portion of the Nvidia CUDA Toolkit **11.8** installed. Not higher or lower versions. Specifically **11.8**. You do not have to uninstall any other versions, change any graphics drivers, reinstall torch or anything like that. This requirement is for Step1 of Finetuning. To keep the download+install as small as possible, you will need to:
+- Download the **xxx (network)** install of the Nvidia CUDA Toolkit 11.8 from [here](https://developer.nvidia.com/cuda-11-8-0-download-archive)
+- Run the installer. At minimum, you need to [minimally] install the `nvcc` compiler and the `CUBLAS` development and runtime libraries:
+  - Select **Custom Advanced** as your installation type.
+  - Uncheck all the checkboxes in the list.
+  - Now check the following elements:
+    - `CUDA` > `Development` > `Compiler` > `nvcc`
+    - `CUDA` > `Development` > `Compiler` > `Libraries` > `CUBLAS`
+    - `CUDA` > `Runtime` > `Libraries` > `CUBLAS`
+  - You can now proceed through the install.
 - When that has installed, open a terminal/command prompt and type `nvcc --version`. If it reports back `Cuda compilation tools, release 11.8.` you are good to go. **Specifically, 11.8**. If not continue to the next step.
-- For both Windows an Linux, you will need to ensure that `nvcc` and the 11.8 cuda library files are in your environments search path. You can undo the changes below after finetuning if you prefer.<br><br>
-  **Windows** - Edit the Windows PATH environment variable and add `C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\bin`<br><br>
-  **Linux** - The path may be different depending on what flavour of Linux you are running, so you may need to seek out specific instructions on the internet. Generic paths **may** be:<br>
-  `export LD_LIBRARY_PATH=/usr/local/cuda-11.8/lib64:${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}` and<br>
-  `export LD_LIBRARY_PATH=/usr/local/cuda-11.8/bin`<br>
-  Add these to your '~/.bashrc' if you want this to be permanent and not something you have to set each time you open a new terminal.<br><br>
-- When you have made the changes, open a new terminal/command prompt and `nvcc --version`. It should report back `Cuda compilation tools, release 11.8.` at which point, you are good to go.
-- If it doesnt report that, check you have correctly set the search environment paths, dont have overlapping other versions of cuda paths etc.
+- For both Windows and Linux, you need to ensure that `nvcc` and the 11.8 cuda library files are in your environments search path. You can undo the changes below after finetuning if you prefer:
+  - **Windows**: Edit the Windows `Path` environment variable and add `C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.8\bin`
+  - **Linux**: The path may be different depending on what flavour of Linux you are running, so you may need to seek out specific instructions on the internet. Generic paths **may** be:
+    - `export LD_LIBRARY_PATH=/usr/local/cuda-11.8/lib64:${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}` and
+    - `export LD_LIBRARY_PATH=/usr/local/cuda-11.8/bin`
+    - Add these to your '~/.bashrc' if you want this to be permanent and not something you have to set each time you open a new terminal.
+- When you have made the changes, open a **new** terminal/command prompt (in order to load the new search paths) and `nvcc --version`. It should report back `Cuda compilation tools, release 11.8.` at which point, you are good to go.
+- If it doesn't report that, check you have correctly set the search environment paths, dont have overlapping other versions of cuda paths etc.
+
+**Note:** Its also important that your Torch and Torchaudio have cuda installed (of any version). If you run the AllTalk diagnostics you can see your Torch and Torchaudio versions listed there. Cuda 11.8 will be listed as `cu118` and Cuda 12.1 as `cu121`. This Torch and Torchaudio is seperate to the above requirement to have the Nvidia CUDA Toolkit installed, so dont confuse the two different requirements. If you dont have Cuda installed on Torch and Torchaudio, Step 2 of Finetuning will fail.
 
 #### ⚫ Starting Finetuning
 **NOTE:** Please make sure you have started AllTalk at least once after updating, so that it downloads the additional files needed for finetuning. 
@@ -292,7 +504,32 @@ As mentioned you must have a small portion of the Nvidia CUDA Toolkit **11.8** i
 11) Follow the on-screen instructions when the web interface starts up.
 12) When you have finished finetuning, the final tab will tell you what to do with your files and how to move your newly trained model to the correct location on disk.
 
-## 🔵🟢🟡 DeepSpeed Installation Options
+#### ⚫ Evaluation Data Percentage
+In the process of finetuning, it's crucial to balance the data used for training the model against the data reserved for evaluating its performance. Typically, a portion of the dataset is set aside as an 'evaluation set' to assess the model's capabilities in dealing with unseen data. On Step 1 of finetuning you have the option to adjust this evaluation data percentage, offering more control over your model training process.<br><br>
+**Why Adjust the Evaluation Percentage?**<br><br>
+Adjusting the evaluation percentage **can** be beneficial in scenarios with limited voice samples. When dealing with a smaller dataset, allocating a slightly larger portion to training could enhance the model's ability to learn from these scarce samples. Conversely, with abundant data, a higher evaluation percentage might be more appropriate to rigorously test the model's performance. There are currently no absolutely optimal split percentages as it varies by dataset.
+- **Default Setting:** The default evaluation percentage is set at 15%, which is a balanced choice for most datasets.
+- **Adjustable Range:** Users can now adjust this percentage, but it’s generally recommend keeping it between 5% and 30%.
+  - **Lower Bound:** A minimum of 5% ensures that there's enough data to evaluate model performance.
+  - **Upper Bound:** Its suggested not exceeding 30% for evaluation to avoid limiting the amount of data available for training.
+
+- **Understanding the Impact:** Before adjusting this setting, it's important to understand its impact on model training and evaluation. Incorrect adjustments can lead to suboptimal model performance.
+- **Gradual Adjustments:** For those unfamiliar with the process, we recommend reading up on training data and training sets, then making small, incremental changes and observing their effects.
+- **Data Quality:** Regardless of the split, the quality of the audio data is paramount. Ensure that your datasets are built from good quality audio with enough data within them.
+
+#### ⚫ Using a Finetuned model in Text-generation-webui
+
+At the end of the finetune process, you will have an option to `Compact and move model to /trainedmodel/` this will compact the raw training file and move it to `/model/trainedmodel/`. When AllTalk starts up within Text-generation-webui, if it finds a model in this location a new loader will appear in the interface for `XTTSv2 FT` and you can use this to load your finetuned model. <br><br>**Be careful** not to train a new model from the base model, then overwrite your current `/model/trainedmodel/` **if** you want a seperately trained model. This is why there is an `OPTION B` to move your just trained model to `/models/lastfinetuned/`.
+
+#### ⚫ Training one model with multiple voices
+
+At the end of the finetune process, you will have an option to `Compact and move model to /trainedmodel/` this will compact the raw training file and move it to `/model/trainedmodel/`. This model will become available when you start up finetuning. You will have a choice to train the Base Model or the `Existing finetuned model` (which is the one in `/model/trainedmodel/`). So you can use this to keep further training this model with additional voices, then copying it back to `/model/trainedmodel/` at the end of training.
+
+#### ⚫ Do I need to keep the raw training data/model?
+
+If you've compacted and moved your model, its highly unlikely you would want to keep that data, however the choice is there to keep it if you wish. It will be between 5-10GB in size, so most people will want to delete it.
+
+### 🔵🟢🟡 DeepSpeed Installation Options
 **NOTE**: You **DO NOT** need to set Text-generation-webUI's **--deepspeed** setting for AllTalk to be able to use DeepSpeed. These are two completely separate things and incorrectly setting that on Text-generation-webUI may cause other complications.
 
 #### 🔵 Linux Installation
@@ -301,6 +538,8 @@ As mentioned you must have a small portion of the Nvidia CUDA Toolkit **11.8** i
 
 ➡️DeepSpeed requires an Nvidia Graphics card!⬅️
 
+- #### DeepSpeed Installation for Text generation webUI
+
 1) Preferably use your built in package manager to install CUDA tools. Alternatively download and install the Nvidia Cuda Toolkit for Linux [Nvidia Cuda Toolkit 11.8 or 12.1](https://developer.nvidia.com/cuda-toolkit-archive)<br><br>
 2) Open a terminal console.<br><br>
 3) Install libaio-dev (however your Linux version installs things) e.g. `sudo apt install libaio-dev`<br><br>
@@ -312,14 +551,37 @@ As mentioned you must have a small portion of the Nvidia CUDA Toolkit **11.8** i
 `export CUDA_HOME=/etc/alternatives/cuda`<br><br>
 **every** time you run `./cmd_linux.sh`.<br> <br>
 If you try to start DeepSpeed with the CUDA_HOME path set incorrectly, expect an error similar to `[Errno 2] No such file or directory: /home/yourname/text-generation-webui/installer_files/env/bin/nvcc`<br> <br>
-9) Now install deepspeed with pip install deepspeed<br><br>
-10) You can now start Text generation webUI `python server.py` ensuring to activate your extensions.<br><br>
+You can also add the `export` line into the start scripts just below the `conda active .......` line, to avoid running the command each time. <br> <br>
+8) Now install deepspeed with pip install deepspeed<br><br>
+9) You can now start Text generation webUI `python server.py` ensuring to activate your extensions.<br><br>
 Just to reiterate, starting Text-generation-webUI with `./start_linux.sh` will overwrite the CUDA_HOME variable unless you have permanently changed it, hence always starting it with `./cmd_linux.sh` **then** setting the environment variable manually (step 7) and **then** `python server.py`, which is how you would need to run it each time, unless you permanently set the environment variable for CUDA_HOME within Text-generation-webUI's standard Python environment.
 <br><br>
 **Removal** - If it became necessary to uninstall DeepSpeed, you can do so with `./cmd_linux.sh` and then `pip uninstall deepspeed`<br><br>
+
+- #### DeepSpeed Installation for standalone alltalk_tts app
+
+1) Preferably use your built in package manager to install CUDA tools. Alternatively download and install the Nvidia Cuda Toolkit for Linux [Nvidia Cuda Toolkit 11.8 or 12.1](https://developer.nvidia.com/cuda-toolkit-archive)<br><br>
+2) Open a terminal console.<br><br>
+3) Install libaio-dev (however your Linux version installs things) e.g. `sudo apt install libaio-dev` If you are using an RPM based distribution the package will probably be named `libaio-devel`.<br><br> 
+4) Navigate to your alltalk_tts folder e.g. `cd alltext_tts`<br><br>
+5) Start the alltalk_tts Python environment `conda activate alltalkenv`<br><br>
+6) You will need to set the **CUDA_HOME** environment variable. Details to change it each time are on the next step. Below is a link to Conda's manual and changing environment variables permanently though its possible changing it permanently could affect other extensions, you would have to test.<br> <br>
+[Conda manual - Environment variables](https://conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html#set-env-vars)<br><br>
+7) Set the environment path for CUDA_HOME e.g. `export CUDA_HOME=/usr/local/cuda-12.1/bin` or `export CUDA_HOME=/etc/alternative/cuda`.  Verify the path on your Linux distro before setting this variable.<br>
+If you try to start DeepSpeed with the CUDA_HOME path set incorrectly, expect an error similar to `[Errno 2] No such file or directory` or `CUDA_HOME does not exist`<br> <br>
+If you set the `env` variable and you receive an error of `[Errno 2] No such file or directory: '/usr/local/cuda-12.1/bin/bin/nvcc'` with a double `bin/bin` path, you can remove the env variable with `unset CUDA_HOME` and add the path to your linux PATH env variable with: `export PATH=$PATH:/usr/local/cuda-12.1/bin`. (Verify the path on your Linux distro before setting this variable.)  However if you are using other applications that use CUDA, you will want to verify that configuring the path did not break those applications. <br><br> 
+8) Now install deepspeed with `pip install deepspeed`<br><br>
+9) You can now start the alltalk_tts webUI with `python script.py`<br><br>
+<br><br>
+**Removal** - If it became necessary to uninstall DeepSpeed, you can do so by entering your `alltalkenv` enviroment `conda activate alltalkenv` and then running `pip uninstall deepspeed`<br><br>
+
+
 </details>
-	
+
 #### 🟢🟡 Windows Installation
+<details>
+	<summary>Click to Expand: Windows DeepSpeed options</summary><br>
+	
 DeepSpeed v11.2 will work on the current default text-generation-webui Python 3.11 environment! You have 2x options for how to setup DeepSpeed on Windows. A quick way (🟢Option 1) and a long way (🟡Option 2).
 
 Thanks to [@S95Sedan](https://github.com/S95Sedan) - They managed to get DeepSpeed 11.2 working on Windows via making some edits to the original Microsoft DeepSpeed v11.2 installation. The original post is [here](https://github.com/oobabooga/text-generation-webui/issues/4734#issuecomment-1843984142).
@@ -444,17 +706,134 @@ def get_shm_size():
 <br><br>
 **Removal** - If it became necessary to uninstall DeepSpeed, you can do so with `cmd_windows.bat` and then `pip uninstall deepspeed`<br><br>
 </details>
+</details>
 
-## 🟠 API Suite and JSON-CURL
+### ⬜ AllTalk TTS Generator
+AllTalk TTS Generator is the solution for converting large volumes of text into speech using the voice of your choice. Whether you're creating audio content or just want to hear text read aloud, the TTS Generator is equipped to handle it all efficiently. Please see here for a quick [demo](https://www.youtube.com/watch?v=hunvXn0mLzc)<br><br>The link to open the TTS generator can be found on the built-in Settings and Documentation page.<br><br>**DeepSpeed** is **highly** recommended to speed up generation. **Low VRAM** would be best turned off and your LLM model unloaded from your GPU VRAM (unload your model). **No Playback** will reduce memory overhead on very large generations (15,000 words or more). Splitting **Export to Wav** into smaller groups will also reduce memory overhead at the point of exporting your wav files (so good for low memory systems). 
+
+#### ⬜ Estimated Throughput
+This will vary by system for a multitude of reasons, however, while generating a 58,000 word document to TTS, with DeepSpeed enabled, LowVram disabled, splitting size 2 and on an Nvidia RTX 4070, throughput was around 1,000 words per minute. Meaning, this took 1 hour to generate the TTS. Exporting to combined wavs took about 2-3 minutes total.
+
+#### ⬜ Quick Start
+- **Text Input:** Enter the text you wish to convert into speech in the 'Text Input' box.
+- **Generate TTS:** Hit this to start the text-to-speech conversion.
+- **Pause/Resume:** Used to pause and resume the playback of the initial generation of wavs or the stream.
+- **Stop Playback:** This will stop the current audio playing back. It does not stop the text from being generated however. 
+Once you have sent text off to be generated, either as a stream or wav file generation, the TTS server will remain busy until this process has competed. As such, think carefully as to how much you want to send to the server. 
+If you are generating wav files and populating the queue, you can generate one lot of text to speech, then input your next lot of text and it will continue adding to the list.
+#### ⬜ TTS Generation Modes
+- **Wav Chunks:** Perfect for creating audio books, or anything you want to keep long term. Breaks down your text into manageable wav files and queues them up. Generation begins automatically, and playback will start after a few chunks have been prepared ahead. You can set the volume to 0 if you don’t want to hear playback. With Wav chunks, you can edit and/or regenerate portions of the TTS as needed.
+- **Streaming:** For immediate playback without the ability to save. Ideal for on-the-fly speech generation and listening. This will not generate wav files and it will play back through your browser. You cannot stop the server generating the TTS once it has been sent.<br><br>
+With wav chunks you can either playback “In Browser” which is the web page you are on, or “On Server” which is through the console/terminal where AllTalk is running from, or "No Playback". Only generation “In Browser” can play back smoothly and populate the Generated TTS List. Setting the Volume will affect the volume level played back both “In Browser” and “On Server”.<br><br>
+For generating **large amounts of TTS**, it's recommended to select the **No Playback** option. This setting minimizes the memory usage in your web browser by avoiding the loading and playing of audio files directly within the browser, which is particularly beneficial for handling extensive audio generations. The definition of large will vary depending on your system RAM availability (will update when I have more information as to guidelines). Once the audio is generated, you can export your list to JSON (for safety) and use the **Play List** option to play back your audio.
+#### ⬜ Playback and List Management
+- **Playback Controls:** Utilize 'Play List' to start from the beginning or 'Stop Playback' to halt at any time.
+- **Custom Start:** Jump into your list at a specific ID to hear a particular section.
+- **Regeneration and Editing:** If a chunk isn't quite right, you can opt to regenerate it or edit the text directly. Click off the text to save changes and hit regenerate for the specific line.
+- **Export/Import List:** Save your TTS list as a JSON file or import one. Note: Existing wav files are needed for playback. Exporting is handy if you want to take your files away into another program and have a list of which wav is which, or if you keep your audio files, but want to come back at a later date, edit one or two lines, regenerate the speech and re-combine the wav’s into one new long wav.
+#### ⬜ Exporting Your Audio
+- **Export to WAV:** Combine all generated TTS from the list, into one single WAV file for easy download and distribution. Its always recommended to export your list to a JSON before exporting, so that you have a backup, should something go wrong. You can simply re-import the list and try exporting again.<br><br>When exporting, there is a file size limit of 1GB and as such you have the option to choose how many files to include in each block of audio exported. 600 is just on the limit of 1GB, depending on the average file size, so 500 or less is a good amount to work with. You can combine the generated files after if you wish, in Audacity or similar.<br><br>Additionally, lower export batches will lower the memory requirements, so if your system is low on memory (maybe 8 or 16GB system), you can use smaller export batches to keep the memory requirement down.
+#### ⬜ Customization and Preferences
+- **Character Voice:** Choose the voice that will read your text.
+- **Language:** Select the language of your text.
+- **Chunk Sizes:** Decide the size of text chunks for generation. Smaller sizes are recommended for better TTS quality.
+#### ⬜ Interface and Accessibility
+- **Dark/Light Mode:** Switch between themes for your visual comfort.
+- **Word Count and Generation Queue:** Keep track of the word count and the generation progress.
+#### ⬜ Notes on Usage
+- For seamless TTS generation, it's advised to keep text chunks under 250 characters, which you can control with the Chunk sizes.
+- Generated audio can be played back from the list, which also highlights the currently playing chunk.
+- The TTS Generator remembers your settings, so you can pick up where you left off even after refreshing the page.
+
+### 🟠 API Suite and JSON-CURL
 ### 🟠Overview
 The Text-to-Speech (TTS) Generation API allows you to generate speech from text input using various configuration options. This API supports both character and narrator voices, providing flexibility for creating dynamic and engaging audio content.
 
-- URL: `http://127.0.0.1:7851/api/tts-generate`<br>
-- Method: `POST`<br>
-- Content-Type: `application/x-www-form-urlencoded`<br>
+#### 🟠 Ready Endpoint<br>
+Check if the Text-to-Speech (TTS) service is ready to accept requests.
 
-### 🟠 Example command lines
-Standard TTS speech Example (standard text) generating a time-stamped file<br>
+- URL: `http://127.0.0.1:7851/api/ready`<br> - Method: `GET`<br> 
+
+   `curl -X GET "http://127.0.0.1:7851/api/ready"`
+
+  Response: `Ready`
+
+#### 🟠 Voices List Endpoint<br>
+Retrieve a list of available voices for generating speech.
+
+- URL: `http://127.0.0.1:7851/api/voices`<br> - Method: `GET`<br>
+
+   `curl -X GET "http://127.0.0.1:7851/api/voices"`
+
+   JSON return: `{"voices": ["voice1.wav", "voice2.wav", "voice3.wav"]}`
+
+#### 🟠 Current Settings Endpoint<br>
+Retrieve a list of available voices for generating speech.
+
+- URL: `http://127.0.0.1:7851/api/currentsettings`<br> - Method: `GET`<br>
+
+   `curl -X GET "http://127.0.0.1:7851/api/currentsettings"`
+
+   JSON return: ```{"models_available":[{"name":"Coqui","model_name":"API TTS"},{"name":"Coqui","model_name":"API Local"},{"name":"Coqui","model_name":"XTTSv2 Local"}],"current_model_loaded":"XTTSv2 Local","deepspeed_available":true,"deepspeed_status":true,"low_vram_status":true,"finetuned_model":false}```
+
+  `name & model_name` = listing the currently available models.<br>
+  `current_model_loaded` = what model is currently loaded into VRAM.<br>
+  `deepspeed_available` = was DeepSpeed detected on startup and available to be activated.<br>
+  `deepspeed_status` = If DeepSpeed was detected, is it currently activated.<br>
+  `low_vram_status` = Is Low VRAM currently enabled.<br>
+  `finetuned_model` = Was a finetuned model detected. (XTTSv2 FT).<br>
+
+#### 🟠 Preview Voice Endpoint
+Generate a preview of a specified voice with hardcoded settings.
+
+- URL: `http://127.0.0.1:7851/api/previewvoice/`<br> - Method: `POST`<br> - Content-Type: `application/x-www-form-urlencoded`<br>
+
+   `curl -X POST "http://127.0.0.1:7851/api/previewvoice/" -F "voice=female_01.wav"`
+
+   Replace `female_01.wav` with the name of the voice sample you want to hear.
+
+   JSON return: `{"status": "generate-success", "output_file_path": "/path/to/outputs/api_preview_voice.wav", "output_file_url": "http://127.0.0.1:7851/audio/api_preview_voice.wav"}`
+
+#### 🟠 Switching Model Endpoint<br>
+
+- URL: `http://127.0.0.1:7851/api/reload`<br> - Method: `POST`<br><br>
+   `curl -X POST "http://127.0.0.1:7851/api/reload?tts_method=API%20Local"`<br>
+   `curl -X POST "http://127.0.0.1:7851/api/reload?tts_method=API%20TTS"`<br>
+   `curl -X POST "http://127.0.0.1:7851/api/reload?tts_method=XTTSv2%20Local"`<br>
+
+   Switch between the 3 models respectively.
+
+   `curl -X POST "http://127.0.0.1:7851/api/reload?tts_method=XTTSv2%20FT"`<br>
+
+   If you have a finetuned model in `/models/trainedmodel/` (will error otherwise)
+
+   JSON return `{"status": "model-success"}`
+
+#### 🟠 Switch DeepSpeed Endpoint<br>
+
+- URL: `http://127.0.0.1:7851/api/deepspeed`<br> - Method: `POST`<br><br>
+   `curl -X POST "http://127.0.0.1:7851/api/deepspeed?new_deepspeed_value=True"`
+
+   Replace True with False to disable DeepSpeed mode.
+
+   JSON return `{"status": "deepspeed-success"}`
+
+#### 🟠 Switching Low VRAM Endpoint<br>
+
+- URL: `http://127.0.0.1:7851/api/lowvramsetting`<br> - Method: `POST`<br><br>
+   `curl -X POST "http://127.0.0.1:7851/api/lowvramsetting?new_low_vram_value=True"`
+
+   Replace True with False to disable Low VRAM mode.
+
+   JSON return `{"status": "lowvram-success"}`
+
+### 🟠 TTS Generation Endpoint (Standard Generation)
+Streaming endpoint details are further down the page.
+
+- URL: `http://127.0.0.1:7851/api/tts-generate`<br> - Method: `POST`<br> - Content-Type: `application/x-www-form-urlencoded`<br>
+
+### 🟠 Example command lines (Standard Generation)
+Standard TTS generation supports Narration and will generate a wav file/blob. Standard TTS speech Example (standard text) generating a time-stamped file<br>
 
 `curl -X POST "http://127.0.0.1:7851/api/tts-generate" -d "text_input=All of this is text spoken by the character. This is text not inside quotes, though that doesnt matter in the slightest" -d "text_filtering=standard" -d "character_voice_gen=female_01.wav" -d "narrator_enabled=false" -d "narrator_voice_gen=male_01.wav" -d "text_not_inside=character" -d "language=en" -d "output_file_name=myoutputfile" -d "output_file_timestamp=true" -d "autoplay=true" -d "autoplay_volume=0.8"`<br>
 
@@ -508,22 +887,22 @@ Example:
 
 🟠 **language**: Choose the language for TTS. Options:
 
-`ar Arabic`<br>
-`zh-cn Chinese (Simplified)`<br>
-`cs Czech`<br>
-`nl Dutch`<br>
-`en English`<br>
-`fr French`<br>
-`de German`<br>
-`hu Hungarian`<br>
-`it Italian`<br>
-`ja Japanese`<br>
-`ko Korean`<br>
-`pl Polish`<br>
-`pt Portuguese`<br>
-`ru Russian`<br>
-`es Spanish`<br>
-`tr Turkish`<br>
+`ar` Arabic<br>
+`zh-cn` Chinese (Simplified)<br>
+`cs` Czech<br>
+`nl` Dutch<br>
+`en` English<br>
+`fr` French<br>
+`de` German<br>
+`hu` Hungarian<br>
+`it` Italian<br>
+`ja` Japanese<br>
+`ko` Korean<br>
+`pl` Polish<br>
+`pt` Portuguese<br>
+`ru` Russian<br>
+`es` Spanish<br>
+`tr` Turkish<br>
 
 `-d "language=en"`<br>
 
@@ -536,12 +915,12 @@ Example:
 `-d "output_file_timestamp=true"`<br>
 `-d "output_file_timestamp=false"`
 
-🟠 **autoplay**: Feature not yet available. Enable or disable autoplay. Still needs to be specified in the JSON request.
+🟠 **autoplay**: Enable or disable playing the generated TTS to your standard sound output device at time of TTS generation.
 
 `-d "autoplay=true"`<br>
 `-d "autoplay=false"`
 
-🟠 **autoplay_volume**: Feature not yet available. Set the autoplay volume. Should be between 0.1 and 1.0. Still needs to be specified in the JSON request.
+🟠 **autoplay_volume**: Set the autoplay volume. Should be between 0.1 and 1.0. Needs to be specified in the JSON request even if autoplay is false.
 
 `-d "autoplay_volume=0.8"`
 
@@ -550,37 +929,39 @@ The API returns a JSON object with the following properties:
 
 - **status** Indicates whether the generation was successful (generate-success) or failed (generate-failure).<br>
 - **output_file_path** The on-disk location of the generated WAV file.<br>
-- **output_file_url** The HTTP location for accessing the generated WAV file.<br>
+- **output_file_url** The HTTP location for accessing the generated WAV file for browser playback.<br>
+- **output_cache_url** The HTTP location for accessing the generated WAV file as a pushed download.<br>
 
 Example JSON TTS Generation Response:
 
-`{"status": "generate-success", "output_file_path": "C:\text-generation-webui\extensions\alltalk_tts\outputs\myoutputfile_1703149973.wav", "output_file_url": "http://127.0.0.1:7851/audio/myoutputfile_1703149973.wav"}`
+`{"status":"generate-success","output_file_path":"C:\\text-generation-webui\\extensions\\alltalk_tts\\outputs\\myoutputfile_1704141936.wav","output_file_url":"http://127.0.0.1:7851/audio/myoutputfile_1704141936.wav","output_cache_url":"http://127.0.0.1:7851/audiocache/myoutputfile_1704141936.wav"}`
 
-🟠 **Switching Model**<br><br>
-`curl -X POST "http://127.0.0.1:7851/api/reload?tts_method=API%20Local"`<br>
-`curl -X POST "http://127.0.0.1:7851/api/reload?tts_method=API%20TTS"`<br>
-`curl -X POST "http://127.0.0.1:7851/api/reload?tts_method=XTTSv2%20Local"`<br>
+### 🟠 TTS Generation Endpoint (Streaming Generation)
+Streaming TTS generation does NOT support Narration and will generate an audio stream. Streaming TTS speech JavaScript Example:<br>
 
-Switch between the 3 models respectively.
+- URL: `http://localhost:7851/api/tts-generate-streaming`<br> - Method: `POST`<br> - Content-Type: `application/x-www-form-urlencoded`<br><br>
 
-JSON return `{"status": "model-success"}`
-
-🟠 **Switch DeepSpeed**<br><br>
-`curl -X POST "http://127.0.0.1:7851/api/deepspeed?new_deepspeed_value=True"`
-
-Replace True with False to disable DeepSpeed mode.
-
-JSON return `{"status": "deepspeed-success"}`
-
-🟠 **Switching Low VRAM**<br><br>
-`curl -X POST "http://127.0.0.1:7851/api/lowvramsetting?new_low_vram_value=True"`
-
-Replace True with False to disable Low VRAM mode.
-
-JSON return `{"status": "lowvram-success"}`
+```
+// Example parameters
+const text = "Here is some text";
+const voice = "female_01.wav";
+const language = "en";
+const outputFile = "stream_output.wav";
+// Encode the text for URL
+const encodedText = encodeURIComponent(text);
+// Create the streaming URL
+const streamingUrl = `http://localhost:7851/api/tts-generate-streaming?text=${encodedText}&voice=${voice}&language=${language}&output_file=${outputFile}`;
+// Create and play the audio element
+const audioElement = new Audio(streamingUrl);
+audioElement.play(); // Play the audio stream directly
+```
+- **Text (text):** This is the actual text you want to convert to speech. It should be a string and must be URL-encoded to ensure that special characters (like spaces and punctuation) are correctly transmitted in the URL. Example: `Hello World` becomes `Hello%20World` when URL-encoded.<br>
+- **Voice (voice):** This parameter specifies the voice type to be used for the TTS. The value should match one of the available voice options in AllTalks voices folder. This is a string representing the file, like `female_01.wav`.<br>
+- **Language (language):** This setting determines the language in which the text should be spoken. A two-letter language code (like `en` for English, `fr` for French, etc.).<br>
+- **Output File (output_file):** This parameter names the output file where the audio will be streamed. It should be a string representing the file name, such as `stream_output.wav`. AllTalk will not save this as a file in its outputs folder.<br>
+<br>
 
 ### 🔴 Future to-do list
-- Voice output within the command prompt/terminal (TBD).
-- Correct a few spelling mistakes in the documentation.
+- I am maintaining a list of things people request [here](https://github.com/erew123/alltalk_tts/discussions/74)
 - Possibly add some additional TTS engines (TBD).
 - Have a break!

atsetup.bat

@@ -0,0 +1,504 @@
+@echo off
+cd /D "%~dp0"
+
+set PATH=%PATH%;%SystemRoot%\system32
+
+:: Generate the ESC character
+for /F %%a in ('echo prompt $E ^| cmd') do set "ESC=%%a"
+
+:: Standard Colors
+set "BLACK=%ESC%[30m"
+set "RED=%ESC%[31m"
+set "GREEN=%ESC%[32m"
+set "YELLOW=%ESC%[33m"
+set "BLUE=%ESC%[34m"
+set "MAGENTA=%ESC%[35m"
+set "CYAN=%ESC%[36m"
+set "WHITE=%ESC%[37m"
+set "L_BLACK=%ESC%[90m"
+set "L_RED=%ESC%[91m"
+set "L_GREEN=%ESC%[92m"
+set "L_YELLOW=%ESC%[93m"
+set "L_BLUE=%ESC%[94m"
+set "L_MAGENTA=%ESC%[95m"
+set "L_CYAN=%ESC%[96m"
+set "L_WHITE=%ESC%[97m"
+set "RESET=%ESC%[0m"
+
+@rem Check if curl is available
+curl --version >nul 2>&1
+if "%ERRORLEVEL%" NEQ "0" (
+    echo curl is not available on this system. Please install curl then re-run the script https://curl.se/ 
+	echo or perform a manual installation of a Conda Python environment.
+    goto end
+)
+
+:MainMenu
+cls
+echo.
+echo    %L_BLUE%ALLTALK WINDOWS SETUP UTILITY%RESET%
+echo.
+echo    INSTALLATION TYPE
+echo    1) I am using AllTalk as part of %L_GREEN%Text-generation-webui%RESET%
+echo    2) I am using AllTalk as a %L_GREEN%Standalone Application%RESET%
+echo.
+echo    9) %L_RED%Exit/Quit%RESET%
+echo.
+set /p UserOption="    Enter your choice: "
+
+if "%UserOption%"=="1" goto WebUIMenu
+if "%UserOption%"=="2" goto StandaloneMenu
+if "%UserOption%"=="9" goto End
+goto MainMenu
+
+:WebUIMenu
+cls
+echo.
+echo    %L_BLUE%TEXT-GENERATION-WEBUI SETUP%RESET%
+echo.
+echo    Please ensure you have started your Text-generation-webui Python 
+echo    environment. If you have NOT done this, please run %L_GREEN%cmd_windows.bat%RESET% 
+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.
+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.
+echo.   OTHER
+echo    7) 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%"=="4" goto InstallDeepSpeed118TextGen
+if "%WebUIOption%"=="5" goto InstallDeepSpeed121TextGen
+if "%WebUIOption%"=="6" goto UnInstallDeepSpeed
+if "%WebUIOption%"=="7" goto GenerateDiagsTextGen
+if "%WebUIOption%"=="9" goto End
+goto WebUIMenu
+
+:StandaloneMenu
+cls
+echo.
+echo    %L_BLUE%ALLTALK STANDALONE APPLICATION SETUP%RESET%
+echo.
+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.
+echo.   OTHER
+echo    4) 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
+goto StandaloneMenu
+
+:InstallNvidiaTextGen
+pip install -r requirements_nvidia.txt
+if %ERRORLEVEL% neq 0 (
+    echo.
+    echo    There was an error installing the Nvidia requirements.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto WebUIMenu
+)
+Echo.
+echo.
+Echo    Nvidia machine requirements installed successfully.
+Echo. 
+pause
+goto WebUIMenu
+
+:InstallOtherTextGen
+pip install -r requirements_other.txt
+if %ERRORLEVEL% neq 0 (
+    echo. 
+    echo    There was an error installing the Other requirements.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto WebUIMenu
+)
+Echo.
+echo.
+Echo    Other machine requirements installed successfully.
+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
+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-0.11.2+cuda118-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-0.11.2+cuda118-cp311-cp311-win_amd64.whl
+pause
+goto WebUIMenu
+
+:InstallDeepSpeed121TextGen
+echo Downloading DeepSpeed...
+curl -LO https://github.com/erew123/alltalk_tts/releases/download/deepspeed/deepspeed-0.11.2+cuda121-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-0.11.2+cuda121-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-0.11.2+cuda121-cp311-cp311-win_amd64.whl
+pause
+goto WebUIMenu
+
+:UnInstallDeepSpeed
+pip uninstall deepspeed
+if %ERRORLEVEL% neq 0 (
+    echo. 
+    echo    There was an error uninstalling DeepSpeed.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto WebUIMenu
+)
+echo.
+Echo    DeepSpeed uninstalled successfully.
+Echo. 
+pause
+goto WebUIMenu
+
+:GenerateDiagsTextGen
+Python diagnostics.py
+if %ERRORLEVEL% neq 0 (
+    echo.
+    echo    There was an error running diagnostics. Have you correctly started your 
+    echo    Text-generation-webui Python environment with %L_GREEN%cmd_windows.bat%RESET%?
+    echo.
+    pause
+    goto WebUIMenu
+)
+Echo.
+echo.
+Echo    Diagnostics.log generated. Please scroll up to look over the log.
+Echo. 
+pause
+goto WebUIMenu
+
+:InstallCustomStandalone
+set PATH=%PATH%;%SystemRoot%\system32
+
+@rem Check if curl is available
+curl --version >nul 2>&1
+if "%ERRORLEVEL%" NEQ "0" (
+    echo curl is not available on this system. Please install curl then re-run the script https://curl.se/ 
+	echo or perform a manual installation of a Conda Python environment.
+    goto end
+)
+echo "%CD%"| findstr /C:" " >nul && echo This script relies on Miniconda which can not be silently installed under a path with spaces. Please correct your folder names and re-try installation. && goto exit
+
+@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 fix failed install when installing to a separate drive
+set TMP=%cd%\alltalk_environment
+set TEMP=%cd%\alltalk_environment
+
+@rem deactivate existing conda envs as needed to avoid conflicts
+(call conda deactivate && call conda deactivate && call conda deactivate) 2>nul
+
+@rem config
+set INSTALL_DIR=%cd%\alltalk_environment
+set CONDA_ROOT_PREFIX=%cd%\alltalk_environment\conda
+set INSTALL_ENV_DIR=%cd%\alltalk_environment\env
+set MINICONDA_DOWNLOAD_URL=https://repo.anaconda.com/miniconda/Miniconda3-py310_23.3.1-0-Windows-x86_64.exe
+set conda_exists=F
+
+@rem figure out whether git and conda need to be installed
+call "%CONDA_ROOT_PREFIX%\_conda.exe" --version >nul 2>&1
+if "%ERRORLEVEL%" EQU "0" (
+    set conda_exists=T
+    call "%CONDA_ROOT_PREFIX%\condabin\conda.bat" activate "%INSTALL_ENV_DIR%"
+    goto RunScript
+)
+
+@rem download and install conda if not installed
+echo Downloading Miniconda from %MINICONDA_DOWNLOAD_URL% to %INSTALL_DIR%\miniconda_installer.exe
+mkdir "%INSTALL_DIR%"
+call curl -Lk "%MINICONDA_DOWNLOAD_URL%" > "%INSTALL_DIR%\miniconda_installer.exe" || ( echo. && echo Miniconda failed to download. && goto end )
+echo Installing Miniconda to %CONDA_ROOT_PREFIX%
+start /wait "" "%INSTALL_DIR%\miniconda_installer.exe" /InstallationType=JustMe /NoShortcuts=1 /AddToPath=0 /RegisterPython=0 /NoRegistry=1 /S /D=%CONDA_ROOT_PREFIX%
+echo Miniconda version:
+call "%CONDA_ROOT_PREFIX%\_conda.exe" --version || ( echo. && echo Miniconda not found. && goto end )
+
+@rem create the installer env
+echo Packages to install: %PACKAGES_TO_INSTALL%
+call "%CONDA_ROOT_PREFIX%\_conda.exe" create --no-shortcuts -y -k --prefix "%INSTALL_ENV_DIR%" python=3.11 || ( echo. && echo Conda environment creation failed. && goto end )
+
+@rem check if conda environment was actually created
+if not exist "%INSTALL_ENV_DIR%\python.exe" ( echo. && echo Conda environment is empty. && goto end )
+
+@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.
+echo    1. Nvidia graphics card machines
+echo    2. Other machines (mac, amd, etc)
+echo.
+set /p UserChoice="Enter your choice (1 or 2): "
+
+@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
+echo cd /D "%~dp0" >> start_environment.bat
+echo set CONDA_ROOT_PREFIX=%cd%\alltalk_environment\conda >> start_environment.bat
+echo set INSTALL_ENV_DIR=%cd%\alltalk_environment\env >> start_environment.bat
+echo call "%CONDA_ROOT_PREFIX%\condabin\conda.bat" activate "%INSTALL_ENV_DIR%" >> start_environment.bat
+@rem Create start_alltalk.bat to run AllTalk
+echo @echo off > start_alltalk.bat
+echo cd /D "%~dp0" >> start_alltalk.bat
+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
+Echo.
+Echo    start_alltalk.bat has been created.
+Echo    You can now start AllTalk with %L_YELLOW%start_alltalk.bat%RESET%
+Echo.
+pause
+goto StandaloneMenu
+
+:DeleteCustomStandalone
+@rem Check if the alltalk_environment directory exists
+if not exist "%cd%\alltalk_environment\" (
+    echo.
+    echo    %L_GREEN%alltalk_environment%RESET% directory does not exist. No need to delete.
+    echo.
+    pause
+    goto StandaloneMenu
+)
+@rem Check if a Conda environment is active
+if not defined CONDA_PREFIX goto NoCondaEnvDeleteCustomStandalone
+@rem Deactivate Conda environment if it's active
+Echo    Exiting the Conda Environment. Please run %L_GREEN%atsetup.bat%RESET% again and delete the environment.
+conda deactivate
+:NoCondaEnvDeleteCustomStandalone
+echo Deleting "alltalk_environment". Please wait.
+rd /s /q "alltalk_environment"
+del start_alltalk.bat
+del start_environment.bat
+if %ERRORLEVEL% neq 0 (
+    echo.
+    echo    Failed to delete alltalk_environment folder.
+    echo    Please make sure it is not in use and try again.
+    echo.
+    pause
+    goto StandaloneMenu
+)
+echo.
+Echo.
+echo    Environment %L_GREEN%alltalk_environment%RESET% deleted. Please set up the environment again.
+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
+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 diagnostics
+Python diagnostics.py
+if %ERRORLEVEL% neq 0 (
+    echo.
+    echo    There was an error running diagnostics.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto StandaloneMenu
+)
+Echo.
+Echo.
+Echo    Diagnostics.log generated. Please scroll up to look over the log.
+Echo.
+pause
+goto StandaloneMenu
+
+:End
+echo Exiting AllTalk Setup Utility...
+exit /b

atsetup.sh

@@ -0,0 +1,443 @@
+#!/bin/bash
+
+# ANSI color codes
+RED='\033[1;31m'
+GREEN='\033[1;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[1;34m'
+CYAN='\033[1;36m'
+MAGENTA='\033[1;35m'
+WHITE='\033[1;37m'
+L_RED='\033[1;91m'
+L_GREEN='\033[1;92m'
+L_YELLOW='\033[1;93m'
+L_BLUE='\033[1;94m'
+L_CYAN='\033[1;96m'
+L_MAGENTA='\033[1;95m'
+NC='\033[0m' # No Color
+
+# Navigate to the script's directory
+cd "$(dirname "$0")"
+
+# Function to check if curl is installed
+check_curl() {
+    if ! command -v curl &> /dev/null; then
+        echo "curl is not available on this system. Please install curl then re-run the script https://curl.se/"
+        echo "or perform a manual installation of a Conda Python environment."
+        exit 1
+    fi
+}
+
+# Main Menu
+main_menu() {
+    while true; do
+        clear
+        echo
+        echo -e "    ${L_BLUE}ALLTALK LINUX SETUP UTILITY${NC}"
+        echo
+        echo "    INSTALLATION TYPE"
+        echo -e "    1) I am using AllTalk as part of ${L_GREEN}Text-generation-webui${NC}"
+        echo -e "    2) I am using AllTalk as a ${L_GREEN}Standalone Application${NC}"
+        echo
+        echo -e "    9)${L_RED} Exit/Quit${NC}"
+        echo
+        read -p "    Enter your choice: " user_option
+
+        case $user_option in
+            1) webui_menu ;;
+            2) standalone_menu ;;
+            9) exit 0 ;;
+            *) echo "Invalid option"; sleep 2 ;;
+        esac
+    done
+}
+
+# Text-generation-webui Menu
+webui_menu() {
+    while true; do
+        clear
+        echo
+        echo -e "    ${L_BLUE}TEXT-GENERATION-WEBUI SETUP${NC}"
+        echo
+        echo -e "    Please ensure you have started your Text-generation-webui Python"
+        echo -e "    environment. If you have NOT done this, please run ${L_GREEN}/cmd_linux.sh${NC}"
+        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
+        echo "    OPTIONAL"
+        echo "    3) Install the Finetuning requirements."
+        echo "    4) Install DeepSpeed."
+        echo "    5) Uninstall DeepSpeed."
+        echo
+        echo "    OTHER"
+        echo "    6) Generate a diagnostics file."
+        echo
+        echo -e "    9)${L_RED} Exit/Quit${NC}"
+        echo
+        read -p "    Enter your choice: " webui_option
+
+        case $webui_option in
+            1) install_nvidia_textgen ;;
+            2) install_other_textgen ;;
+            3) install_finetune_textgen ;;
+            4) install_deepspeed ;;
+            5) uninstall_deepspeed ;;
+            6) generate_diagnostics_textgen ;;
+            9) exit 0 ;;
+            *) echo "Invalid option"; sleep 2 ;;
+        esac
+    done
+}
+
+install_nvidia_textgen() {
+    local requirements_file="requirements_nvidia.txt"
+    echo "    Installing Finetune requirements from $requirements_file..."
+    if ! pip install -r "$requirements_file"; then
+        echo "    There was an error installing the Nvidia requirements."
+        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."
+    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
+    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."
+        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
+}
+
+# Function to install DeepSpeed
+install_deepspeed() {
+    clear
+    echo
+    echo -e "    ${L_BLUE}DEEPSPEED INSTALLATION REQUIREMENTS${NC}"
+    echo
+    echo -e "    - NVIDIA CUDA Toolkit must be installed from your ${L_GREEN}Linux package manager${NC}"
+    echo -e "      or ${L_GREEN}https://developer.nvidia.com/cuda-toolkit-archive${NC}"
+    echo -e "    - The environment variable ${L_GREEN}CUDA_HOME${NC} must be set in your Python env"
+    echo -e "      e.g. export CUDA_HOME=/usr/local/cuda."
+    echo -e "    - ${L_GREEN}libaio-dev${NC} must be installed."
+    echo
+    echo -e "    See the following link for full instructions:"
+    echo -e "    ${L_GREEN}https://github.com/erew123/alltalk_tts?#-deepspeed-installation-options${NC}"
+    echo
+    echo -e "    ${L_BLUE}Please ${L_RED}confirm${L_BLUE} that you have completed these steps before continuing" 
+    echo -e "    with the DeepSpeed installation, or the install ${L_RED}will fail.${NC}"
+    echo
+    read -p "    Have you completed all the above steps? (y/n): " confirm
+
+    if [ "$confirm" != "y" ]; then
+        echo -e "    ${RED}DeepSpeed installation cannot proceed without completing the prerequisites.${NC}"
+        return
+    fi
+
+    echo -e "\n    ${GREEN}Proceeding with DeepSpeed installation...${NC}"
+    pip install deepspeed
+    if [ $? -ne 0 ]; then
+        echo -e "    ${RED}There was an error installing DeepSpeed.${NC}"
+        return
+    fi
+
+    echo -e "    ${GREEN}DeepSpeed installed successfully.${NC}"
+    read -p "    Press any key to continue. " -n 1
+    echo
+}
+
+uninstall_deepspeed() {
+    echo "Uninstalling DeepSpeed..."
+    pip uninstall -y deepspeed
+    if [ $? -ne 0 ]; then
+        echo "    There was an error uninstalling DeepSpeed."
+        echo "    Press any key to return to the menu."
+        read -n 1
+        return
+    fi
+    echo "    DeepSpeed uninstalled successfully."
+    echo "    Press any key to continue."
+    read -n 1
+}
+
+generate_diagnostics_textgen() {
+    # Run diagnostics
+    if ! python diagnostics.py; then
+        echo "    There was an error running diagnostics."
+        read -p "    Press any key to return to the menu. " -n 1
+        echo
+        return
+    fi
+
+    echo "    Diagnostics completed successfully."
+    read -p "    Press any key to continue. " -n 1
+    echo
+}
+
+# Standalone Menu
+standalone_menu() {
+    while true; do
+        clear
+        echo
+        echo -e "    ${L_BLUE}ALLTALK STANDALONE APPLICATION SETUP${NC}"
+        echo
+        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 "    4) Install DeepSpeed."
+        echo
+        echo "    OTHER"        
+        echo "    5) Generate a diagnostics file"
+        echo
+        echo -e "    9)${L_RED} Exit/Quit${NC}"
+        echo
+        read -p "    Enter your choice: " standalone_option
+
+        case $standalone_option in
+            1) install_custom_standalone ;;
+            2) delete_custom_standalone ;;
+            3) install_finetune_standalone ;;
+            4) install_deepspeed ;;
+            5) generate_diagnostics_standalone ;;
+            9) exit 0 ;;
+            *) echo "Invalid option"; sleep 2 ;;
+        esac
+    done
+}
+
+install_custom_standalone() {
+    cd "$(dirname "${BASH_SOURCE[0]}")"
+
+    if [[ "$(pwd)" =~ " " ]]; then
+        echo "This script relies on Miniconda which can not be silently installed under a path with spaces."
+        exit
+    fi
+
+    # Deactivate existing conda envs as needed to avoid conflicts
+    { conda deactivate && conda deactivate && conda deactivate; } 2> /dev/null
+
+    OS_ARCH=$(uname -m)
+    case "${OS_ARCH}" in
+        x86_64*)    OS_ARCH="x86_64" ;;
+        arm64* | aarch64*) OS_ARCH="aarch64" ;;
+        *)          echo "Unknown system architecture: $OS_ARCH! This script runs only on x86_64 or arm64" && exit ;;
+    esac
+
+    # Config
+    INSTALL_DIR="$(pwd)/alltalk_environment"
+    CONDA_ROOT_PREFIX="${INSTALL_DIR}/conda"
+    INSTALL_ENV_DIR="${INSTALL_DIR}/env"
+    MINICONDA_DOWNLOAD_URL="https://repo.anaconda.com/miniconda/Miniconda3-py310_23.3.1-0-Linux-${OS_ARCH}.sh"
+
+    if [ ! -x "${CONDA_ROOT_PREFIX}/bin/conda" ]; then
+        echo "Downloading Miniconda from $MINICONDA_DOWNLOAD_URL to ${INSTALL_DIR}/miniconda_installer.sh"
+        mkdir -p "${INSTALL_DIR}"
+        curl -L "${MINICONDA_DOWNLOAD_URL}" -o "${INSTALL_DIR}/miniconda_installer.sh"
+        chmod +x "${INSTALL_DIR}/miniconda_installer.sh"
+        bash "${INSTALL_DIR}/miniconda_installer.sh" -b -p "${CONDA_ROOT_PREFIX}"
+        echo "Miniconda installed."
+    fi
+
+    if [ ! -d "${INSTALL_ENV_DIR}" ]; then
+        "${CONDA_ROOT_PREFIX}/bin/conda" create -y --prefix "${INSTALL_ENV_DIR}" python=3.11
+        echo "Conda environment created at ${INSTALL_ENV_DIR}."
+    fi
+
+    # Activate the environment and install requirements
+    source "${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
+    echo "    1. Nvidia graphics card machines"
+    echo "    2. Other machines (mac, amd, etc)"
+    echo
+    read -p "    Enter your choice (1 or 2): " user_choice
+
+    if [ "$user_choice" == "1" ]; then
+    	pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --upgrade --force-reinstall --index-url https://download.pytorch.org/whl/cu121
+    	pip install numpy==1.24.4
+	pip install typing-extensions>=4.8.0
+	pip install networkx<3.0.0,>=2.5.0
+    	pip install fsspec>=2023.6.0
+	pip install soundfile==0.12.1
+    	pip install uvicorn==0.24.0.post1
+        pip install transformers>=4.37.1
+    	pip install TTS==0.21.3
+    	pip install fastapi==0.104.1
+    	pip install Jinja2==3.1.2
+    	pip install requests==2.31.0
+    	pip install tqdm==4.66.1
+    	pip install importlib-metadata==4.8.1
+    	pip install packaging==23.2
+    	pip install pydantic==1.10.13
+    	pip install sounddevice==0.4.6
+    	pip install python-multipart==0.0.6
+        pip install cutlet>=0.3.0
+    	pip install unidic-lite>=1.0.8
+    else
+        pip install -r requirements_other.txt
+    fi
+    # Create start_environment.sh to run AllTalk
+    cat << EOF > start_environment.sh
+#!/bin/bash
+cd "$(dirname "${BASH_SOURCE[0]}")"
+if [[ "$(pwd)" =~ " " ]]; then echo This script relies on Miniconda which can not be silently installed under a path with spaces. && exit; fi
+# deactivate existing conda envs as needed to avoid conflicts
+{ conda deactivate && conda deactivate && conda deactivate; } 2> /dev/null
+# config
+CONDA_ROOT_PREFIX="$(pwd)/alltalk_environment/conda"
+INSTALL_ENV_DIR="$(pwd)/alltalk_environment/env"
+# environment isolation
+export PYTHONNOUSERSITE=1
+unset PYTHONPATH
+unset PYTHONHOME
+export CUDA_PATH="$INSTALL_ENV_DIR"
+export CUDA_HOME="$CUDA_PATH"
+# 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
+source "${CONDA_ROOT_PREFIX}/etc/profile.d/conda.sh"
+conda activate "${INSTALL_ENV_DIR}"
+python script.py
+EOF
+    chmod +x start_alltalk.sh
+    chmod +x start_environment.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
+    read -p "    Press any key to continue. " -n 1
+}
+
+
+delete_custom_standalone() {
+    local env_dir="$PWD/alltalk_environment"
+    # Check if the alltalk_environment directory exists
+    if [ ! -d "$env_dir" ]; then
+        echo "    \"$env_dir\" directory does not exist. No need to delete."
+        read -p "    Press any key to continue. " -n 1
+        echo
+        return
+    fi
+    # Check if a Conda environment is active and deactivate it
+    if [ -n "$CONDA_PREFIX" ]; then
+        echo "    Exiting the Conda environment. You may need to start ./atstart.sh again"
+        conda deactivate
+    fi
+    echo "Deleting \"$env_dir\". Please wait."
+    rm -rf "$env_dir"
+    if [ -d "$env_dir" ]; then
+        echo "    Failed to delete \"$env_dir\" folder."
+        echo "    Please make sure it is not in use and try again."
+    else
+        echo "    Environment \"$env_dir\" deleted successfully."
+    fi
+    read -p "    Press any key to continue. " -n 1
+    echo
+}
+
+install_finetune_standalone() {
+    local env_dir="$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 "    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}"
+    if ! python diagnostics.py; then
+        echo "    There was an error running diagnostics."
+        read -p "    Press any key to return to the menu. " -n 1
+        echo
+        return
+    fi
+    echo "    Diagnostics completed successfully."
+    read -p "    Press any key to continue. " -n 1
+    echo
+}
+
+
+# Start the main menu
+main_menu

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"}
+{
+    "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"
+}

diagnostics.py

@@ -6,6 +6,7 @@ try:
     import torch
     import os  # Import the os module
     import re
+    import sys
     import glob
     import textwrap
     import packaging.version
@@ -17,7 +18,7 @@ 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")
     print("\033[92mcmd_linux.sh\033[0m, \033[92mcmd_windows.bat\033[0m, \033[92mcmd_macos.sh\033[0m, or \033[92mcmd_wsl.bat\033[0m")
-    print("\033[94mand then try running the diagnostics again.\033[0m")
+    print("\033[94mfrom the text-generation-webui directory, and then try running the diagnostics again.\033[0m")
     exit(1)
 
 try:
@@ -110,6 +111,18 @@ def log_system_info():
     # Package versions using importlib_metadata
     package_versions = {d.metadata['Name']: d.version for d in distributions()}
 
+    # Python environment information
+    python_executable = sys.executable
+    python_version_info = sys.version_info
+    python_virtual_env = os.environ.get('VIRTUAL_ENV', 'N/A')
+
+    # Conda environment information
+    conda_env = os.environ.get('CONDA_DEFAULT_ENV', 'N/A')
+
+    # Get Path environment information
+    search_path = sys.path
+    path_env = os.environ.get('PATH', 'N/A')
+
     # Compare with requirements file
     requirements_file = get_requirements_file()
     if requirements_file:
@@ -134,14 +147,24 @@ def log_system_info():
 
     # Log and print information
     logging.info(f"OS Version: {os_version}")
-    logging.info(f"Note: Windows 11 build is 10.x.22xxx")
-    logging.info(f"Python Version: {python_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("\nPython Search Path:")
+    for path in search_path:
+        logging.info(f"  {path}")
+    logging.info("\nOS PATH Environment Variable:")
+    for path in path_env.split(';'):
+        logging.info(f"  {path}")
     if required_packages:  # Check if the dictionary is not empty
-        logging.info("Package Versions:")
+        logging.info("\nPackage Versions:")
         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')
@@ -153,12 +176,22 @@ def log_system_info():
 
     # 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[92mWindows 11 build is 10.x.22xxx\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")
-    print(f"\033[94mPython Version:\033[0m \033[92m{python_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())
@@ -182,6 +215,13 @@ def log_system_info():
 
             # 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("\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")
+        print("installed for Torch or Torchaudio in this Python environment. This will cause you problems")
+        print("with \033[94mAllTalk\033[0m and \033[94mFinetuning.\033[0m You may have to 'pip install' a new version of torch and")
+        print("torchaudio, using '\033[94m--upgrade --force-reinstall\033[0m' with the correct version of PyTorch for\033[0m")
+        print("your Python environment.\033[0m")
         print("\033[94m\nRequirements file specifier meanings:\033[0m")
         explanation = textwrap.dedent("""
         == Exact version              != Any version except          < Less than               

docker-compose-cuda.yml

@@ -0,0 +1,20 @@
+version: '3.8'
+services:
+  alltalk-tts:
+    image: erew123/alltalk_tts:cuda
+    restart: unless-stopped
+    ports:
+      - "7851:7851"
+    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:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [ gpu ]

docker-compose.yml

@@ -0,0 +1,13 @@
+version: '3.8'
+services:
+  alltalk-tts:
+    image: erew123/alltalk_tts:cpu
+    restart: unless-stopped
+    ports:
+      - "7851:7851"
+    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

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"
+}

finetune.py

@@ -14,6 +14,7 @@ import gc
 import time
 import shutil
 import pandas
+import glob
 import json
 from pathlib import Path
 from tqdm import tqdm
@@ -40,12 +41,27 @@ if modeldownload_config_file_path.exists():
     # Extract settings from the loaded JSON
     base_path = Path(settings.get("base_path", ""))
     model_path = Path(settings.get("model_path", ""))
+    base_model_path = Path(settings.get("model_path", ""))
     files_to_download = settings.get("files_to_download", {})
 else:
     # Default settings if the JSON file doesn't exist or is empty
     print("[FINETUNE]  \033[91mWarning\033[0m modeldownload.json is missing. Please run this script in the /alltalk_tts/ folder")
     sys.exit(1)
 
+##################################################
+#### Check to see if a finetuned model exists ####
+##################################################
+# Set the path to the directory
+trained_model_directory = this_dir / "models" / "trainedmodel"
+# Check if the directory "trainedmodel" exists
+finetuned_model = trained_model_directory.exists()
+# If the directory exists, check for the existence of the required files
+# 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", "mel_stats.pth", "dvae.pth"]
+    finetuned_model = all((trained_model_directory / file).exists() for file in required_files)
+basemodel_or_finetunedmodel = True
+
 #####################
 #### STEP 1 BITS ####
 #####################
@@ -59,10 +75,10 @@ def create_temporary_file(folder, suffix=".wav"):
     unique_filename = f"custom_tempfile_{int(time.time())}_{random.randint(1, 1000)}{suffix}"
     return os.path.join(folder, unique_filename)
 
-def format_audio_list(target_language, whisper_model, out_path, gradio_progress=progress):
+def format_audio_list(target_language, whisper_model, out_path, eval_split_number, gradio_progress=progress):
     audio_files = [os.path.join(audio_folder, file) for file in os.listdir(audio_folder) if file.endswith(('.mp3', '.flac', '.wav'))]
     buffer=0.2
-    eval_percentage=0.15
+    eval_percentage = eval_split_number / 100.0
     speaker_name="coqui"
     audio_total_size = 0
     os.makedirs(out_path, exist_ok=True)
@@ -71,6 +87,7 @@ def format_audio_list(target_language, whisper_model, out_path, gradio_progress=
     print("[FINETUNE] \033[94mPart of AllTalk\033[0m https://github.com/erew123/alltalk_tts/")
     print("[FINETUNE] \033[94mCoqui Public Model License\033[0m")
     print("[FINETUNE] \033[94mhttps://coqui.ai/cpml.txt\033[0m")
+    print(f"[FINETUNE] \033[94mWhisper model: \033[92m{whisper_model} \033[94mLanguage: \033[92m{target_language} \033[94mEvaluation data percentage: \033[92m{eval_split_number}%\033[0m")
     print("[FINETUNE] \033[94mStarting Step 1\033[0m - Preparing Audio/Generating the dataset")
     # Write the target language to lang.txt in the output directory
     lang_file_path = os.path.join(out_path, "lang.txt")
@@ -270,6 +287,8 @@ def format_audio_list(target_language, whisper_model, out_path, gradio_progress=
     # deallocate VRAM and RAM
     del asr_model, final_eval_set, final_training_set, new_data_df, existing_metadata
     gc.collect()
+    existing_train_df = None
+    existing_eval_df = None
     print("[FINETUNE] Train CSV:", train_metadata_path)
     print("[FINETUNE] Eval CSV:", eval_metadata_path)
     print("[FINETUNE] Audio Total:", audio_total_size)
@@ -287,6 +306,13 @@ from TTS.tts.layers.xtts.trainer.gpt_trainer import GPTArgs, GPTTrainer, GPTTrai
 from TTS.utils.manage import ModelManager
 
 
+def basemodel_or_finetunedmodel_choice(value):
+    global basemodel_or_finetunedmodel 
+    if value == "Base Model":
+        basemodel_or_finetunedmodel = True
+    elif value == "Existing finetuned model":
+        basemodel_or_finetunedmodel = False
+
 def train_gpt(language, num_epochs, batch_size, grad_acumm, train_csv, eval_csv, output_path, max_audio_length=255995):
     #  Logging parameters
     RUN_NAME = "XTTS_FT"
@@ -319,12 +345,22 @@ def train_gpt(language, num_epochs, batch_size, grad_acumm, train_csv, eval_csv,
     # Add here the configs of the datasets
     DATASETS_CONFIG_LIST = [config_dataset]
 
-    # XTTS model checkpoints for fine-tuning.
-    TOKENIZER_FILE = str(this_dir / base_path / model_path / "vocab.json")  # vocab.json file
-    XTTS_CHECKPOINT = str(this_dir / base_path / model_path / "model.pth")  # model.pth file
-    XTTS_CONFIG_FILE = str(this_dir / base_path / model_path / "config.json")  # config.json file
-    DVAE_CHECKPOINT = str(this_dir / base_path / model_path / "dvae.pth")
-    MEL_NORM_FILE = str(this_dir / base_path / model_path / "mel_stats.pth")
+    if basemodel_or_finetunedmodel:
+        # BASE XTTS model checkpoints for fine-tuning.
+        print("[FINETUNE] Starting finetuning on Base Model")
+        TOKENIZER_FILE = str(this_dir / base_path / model_path / "vocab.json")
+        XTTS_CHECKPOINT = str(this_dir / base_path / model_path / "model.pth")
+        XTTS_CONFIG_FILE = str(this_dir / base_path / model_path / "config.json")
+        DVAE_CHECKPOINT = str(this_dir / base_path / model_path / "dvae.pth")
+        MEL_NORM_FILE = str(this_dir / base_path / model_path / "mel_stats.pth")
+    else:
+        # FINETUNED XTTS model checkpoints for fine-tuning.
+        print("[FINETUNE] Starting finetuning on Existing Finetuned Model")
+        TOKENIZER_FILE = str(this_dir / base_path / "trainedmodel" / "vocab.json")
+        XTTS_CHECKPOINT = str(this_dir / base_path / "trainedmodel" / "model.pth")
+        XTTS_CONFIG_FILE = str(this_dir / base_path / "trainedmodel" / "config.json")
+        DVAE_CHECKPOINT = str(this_dir / base_path / "trainedmodel" / "dvae.pth")
+        MEL_NORM_FILE = str(this_dir / base_path / "trainedmodel" / "mel_stats.pth")
 
     # init args and config
     model_args = GPTArgs(
@@ -415,9 +451,14 @@ def train_gpt(language, num_epochs, batch_size, grad_acumm, train_csv, eval_csv,
     trainer_out_path = trainer.output_path
 
     # deallocate VRAM and RAM
-    del model, trainer, train_samples, eval_samples
+    del model, trainer, train_samples, eval_samples, config, model_args, config_dataset
     gc.collect()
-
+    train_samples = None
+    eval_samples = None
+    config_dataset = None
+    trainer = None
+    model = None
+    model_args = None
     return XTTS_CONFIG_FILE, XTTS_CHECKPOINT, TOKENIZER_FILE, trainer_out_path, speaker_ref
 
 ##########################
@@ -495,7 +536,222 @@ xtts_config_files = find_jsons(main_directory, "config.json")
 # XTTS vocab files (vocab.json)
 xtts_vocab_files = find_jsons(main_directory, "vocab.json")
 
+##########################
+#### STEP 4 AND OTHER ####
+##########################
 
+def find_latest_best_model(folder_path):
+    search_path = folder_path / "XTTS_FT-*" / "best_model.pth"
+    files = glob.glob(str(search_path), recursive=True)
+    latest_file = max(files, key=os.path.getctime, default=None)
+    return latest_file
+
+def compact_model():
+    this_dir = Path(__file__).parent.resolve()
+
+    best_model_path_str = find_latest_best_model(this_dir / "finetune" / "tmp-trn" / "training")
+
+    # Check if the best model file exists
+    if best_model_path_str is None:
+        print("[FINETUNE] No trained model was found.")
+        return "No trained model was found."
+
+    # Convert model_path_str to Path
+    best_model_path = Path(best_model_path_str)
+
+    # Attempt to load the model
+    try:
+        checkpoint = torch.load(best_model_path, map_location=torch.device("cpu"))
+    except Exception as e:
+        print("[FINETUNE] Error loading checkpoint:", e)
+        raise
+
+    del checkpoint["optimizer"]
+
+    for key in list(checkpoint["model"].keys()):
+        if "dvae" in key:
+            del checkpoint["model"][key]
+
+    # Define the target directory
+    target_dir = this_dir / "models" / "trainedmodel"
+
+    # Create the target directory if it doesn't exist
+    target_dir.mkdir(parents=True, exist_ok=True)
+
+    # Save the modified checkpoint in the target directory
+    torch.save(checkpoint, target_dir / "model.pth")
+
+    # Specify the files you want to copy
+    files_to_copy = ["vocab.json", "config.json", "dvae.pth", "mel_stats.pth"]
+
+    for file_name in files_to_copy:
+        src_path = this_dir / base_path / base_model_path / file_name
+        dest_path = target_dir / file_name
+        shutil.copy(str(src_path), str(dest_path))
+
+    source_wavs_dir = this_dir / "finetune" / "tmp-trn" / "wavs"
+    target_wavs_dir = target_dir / "wavs"
+    target_wavs_dir.mkdir(parents=True, exist_ok=True)
+
+    # Iterate through files in the source directory
+    for file_path in source_wavs_dir.iterdir():
+        # Check if it's a file and larger than 1000 KB
+        if file_path.is_file() and file_path.stat().st_size > 1000 * 1024:
+            # Copy the file to the target directory
+            shutil.copy(str(file_path), str(target_wavs_dir / file_path.name))
+    
+    print("[FINETUNE] Model copied to '/models/trainedmodel/'")
+    return "Model copied to '/models/trainedmodel/'"
+
+
+def compact_lastfinetuned_model():
+    this_dir = Path(__file__).parent.resolve()
+
+    best_model_path_str = find_latest_best_model(this_dir / "finetune" / "tmp-trn" / "training")
+
+    # Check if the best model file exists
+    if best_model_path_str is None:
+        print("[FINETUNE] No trained model was found.")
+        return "No trained model was found."
+
+    # Convert model_path_str to Path
+    best_model_path = Path(best_model_path_str)
+
+    # Attempt to load the model
+    try:
+        checkpoint = torch.load(best_model_path, map_location=torch.device("cpu"))
+    except Exception as e:
+        print("[FINETUNE] Error loading checkpoint:", e)
+        raise
+
+    del checkpoint["optimizer"]
+
+    for key in list(checkpoint["model"].keys()):
+        if "dvae" in key:
+            del checkpoint["model"][key]
+
+    # Define the target directory
+    target_dir = this_dir / "models" / "lastfinetuned"
+
+    # Create the target directory if it doesn't exist
+    target_dir.mkdir(parents=True, exist_ok=True)
+
+    # Save the modified checkpoint in the target directory
+    torch.save(checkpoint, target_dir / "model.pth")
+
+    # Specify the files you want to copy
+    files_to_copy = ["vocab.json", "config.json", "dvae.pth", "mel_stats.pth"]
+
+    for file_name in files_to_copy:
+        src_path = this_dir / base_path / base_model_path / file_name
+        dest_path = target_dir / file_name
+        shutil.copy(str(src_path), str(dest_path))
+
+    source_wavs_dir = this_dir / "finetune" / "tmp-trn" / "wavs"
+    target_wavs_dir = target_dir / "wavs"
+    target_wavs_dir.mkdir(parents=True, exist_ok=True)
+
+    # Iterate through files in the source directory
+    for file_path in source_wavs_dir.iterdir():
+        # Check if it's a file and larger than 1000 KB
+        if file_path.is_file() and file_path.stat().st_size > 1000 * 1024:
+            # Copy the file to the target directory
+            shutil.copy(str(file_path), str(target_wavs_dir / file_path.name))
+    
+    print("[FINETUNE] Model copied to '/models/lastfinetuned/'")
+    return "Model copied to '/models/lastfinetuned/'"
+
+
+def compact_legacy_model():
+    this_dir = Path(__file__).parent.resolve()
+
+    best_model_path_str = os.path.join(this_dir, "finetune", "best_model.pth")
+
+    # Check if the best model file exists
+    if not os.path.exists(best_model_path_str):
+        print("[FINETUNE] No model called best_model.pth was found in /finetune/")
+        return "No model called best_model.pth was found in /finetune/"
+
+    # Convert model_path_str to Path
+    best_model_path = Path(best_model_path_str)
+
+    # Attempt to load the model
+    try:
+        checkpoint = torch.load(best_model_path, map_location=torch.device("cpu"))
+    except Exception as e:
+        print("[FINETUNE] Error loading checkpoint:", e)
+        raise
+
+    del checkpoint["optimizer"]
+
+    for key in list(checkpoint["model"].keys()):
+        if "dvae" in key:
+            del checkpoint["model"][key]
+
+    # Define the target directory
+    target_dir = this_dir / "finetune"
+
+    # Create the target directory if it doesn't exist
+    target_dir.mkdir(parents=True, exist_ok=True)
+
+    # Save the modified checkpoint in the target directory
+    torch.save(checkpoint, target_dir / "model.pth")
+
+    print("[FINETUNE] model.pth created in '/finetune/'")
+    return "model.pth created in '/finetune/'"
+
+
+def delete_training_data():
+    # Define the folder to be deleted
+    folder_to_delete = Path(this_dir / "finetune" / "tmp-trn")
+
+    # Check if the folder exists before deleting
+    if folder_to_delete.exists():
+        # Iterate over all files and subdirectories
+        for item in folder_to_delete.iterdir():
+            # Exclude trainer_0_log.txt from deletion
+            if item.name != "trainer_0_log.txt":
+                try:
+                    if item.is_file():
+                        item.unlink()
+                    elif item.is_dir():
+                        shutil.rmtree(item)
+                except PermissionError:
+                    print(f"[FINETUNE] PermissionError: Could not delete {item}. Skipping.")
+
+        print(f"[FINETUNE] Folder {folder_to_delete} contents (excluding trainer_0_log.txt) deleted successfully.")
+        return "Folder '/finetune/tmp-trn/' contents (excluding trainer_0_log.txt) deleted successfully."
+    else:
+        print(f"[FINETUNE] Folder {folder_to_delete} does not exist.")
+        return "Folder '/finetune/tmp-trn/' does not exist."
+
+
+def delete_voice_sample_contents():
+    # Define the folder to be cleared
+    folder_to_clear = Path(this_dir / "finetune" / "put-voice-samples-in-here")
+
+    # Check if the folder exists before clearing its contents
+    if folder_to_clear.exists() and folder_to_clear.is_dir():
+        # List all files and subdirectories in the folder
+        for item in os.listdir(folder_to_clear):
+            item_path = folder_to_clear / item
+            if item_path.is_file():
+                # If it's a file, remove it
+                os.remove(item_path)
+            elif item_path.is_dir():
+                # If it's a subdirectory, remove it recursively
+                shutil.rmtree(item_path)
+
+        print(f"[FINETUNE] Contents of {folder_to_clear} deleted successfully.")
+        return f"Contents of 'put-voice-samples-in-here deleted' successfully."
+    else:
+        print(f"[FINETUNE] Folder {folder_to_clear} does not exist.")
+        return f"Folder 'put-voice-samples-in-here' does not exist."
+
+
+#######################
+#### OTHER Generic ####
+#######################
 # define a logger to redirect 
 class Logger:
     def __init__(self, filename="finetune.log"):
@@ -620,20 +876,21 @@ if __name__ == "__main__":
                 f"""
                 ## <u>Finetuning Information</u><br>
                 ### 🟥 <u>Important Note</u>
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟥 <span style="color: #3366ff;">finetune.py</span> needs to be run from the <span style="color: #3366ff;">/alltalk_tts/</span> folder. Don't move the location of this script.
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟥 Have you run AllTalk at least once? It needs to have downloaded+updated the voice model, before we can finetune it.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - <span style="color: #3366ff;">finetune.py</span> needs to be run from the <span style="color: #3366ff;">/alltalk_tts/</span> folder. Don't move the location of this script.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - Have you run AllTalk at least once? It needs to have downloaded+updated the voice model, before we can finetune it.
                 ### 🟦 <u>What you need to run finetuning</u>
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 An Nvidia GPU. Tested on Windows with extended shared VRAM and training used about 16GB's total (which worked on a 12GB card).
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 I have not been able to test this on a GPU with less than 12GB of VRAM, so cannot say if it will work or how that would affect performance.
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 <span style="color: red;">Version 11.8</span> of Nvidia cuBLAS and cuDNN (guide below). Only 11.8 of cuBLAS and cuDNN work for this process currently.
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 Minimum <span style="color: red;">18GB</span> free disk space (most of it is used temporarily).
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 Some decent quality audio, multiple files if you like. Minimum of 2 minutes and Ive tested up to 20 minutes of audio.
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 There is no major need to chop down your audio files into small slices as Step 1 will do that for you automatically and prepare the training set. Ive been testing with 5 minute long clips.
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 This process will need access to all your GPU and VRAM, so close any other software that's using your GPU currently.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - An Nvidia GPU. Tested on Windows with extended shared VRAM and training used about 16GB's total (which worked on a 12GB card).
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - If you have multiple Nvidia GPU's in your system, please see this [important note](https://github.com/erew123/alltalk_tts#-i-have-multiple-gpus-and-i-have-problems-running-finetuning).
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - I have not been able to test this on a GPU with less than 12GB of VRAM, so cannot say if it will work or how that would affect performance.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - <span style="color: red;">Version 11.8</span> of Nvidia cuBLAS and cuDNN (guide below). Only 11.8 of cuBLAS and cuDNN work for this process currently.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - Minimum <span style="color: red;">18GB</span> free disk space (most of it is used temporarily).
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - Some decent quality audio, multiple files if you like. Minimum of 2 minutes and Ive tested up to 20 minutes of audio.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - There is no major need to chop down your audio files into small slices as Step 1 will do that for you automatically and prepare the training set. Ive been testing with 5 minute long clips.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - This process will need access to all your GPU and VRAM, so close any other software that's using your GPU currently.
                 ### 🟨 <u>Setting up cuBLAS and cuDNN <span style="color: red;">Version 11.8</span></u>
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟨 If you have the <span style="color: #3366ff;;">Nvidia CUDA Toolkit Version 11.8</span> installed and can type <span style="color: #3366ff;;">nvcc --version</span> at the command prompt/terminal and it reports <span style="color: #00a000;">Cuda compilation tools, release 11.8</span> you should be good to go. 
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟨 If you dont have the toolkit installed, the idea is just to install the smallest bit possible and this will not affect or impact other things on your system.
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟨 You will need to download the Nvidia Cuda Toolkit 11.8<span style="color: #3366ff;"> network</span> install from [here](https://developer.nvidia.com/cuda-11-8-0-download-archive) 
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - If you have the <span style="color: #3366ff;;">Nvidia CUDA Toolkit Version 11.8</span> installed and can type <span style="color: #3366ff;;">nvcc --version</span> at the command prompt/terminal and it reports <span style="color: #00a000;">Cuda compilation tools, release 11.8</span> you should be good to go. 
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - If you dont have the toolkit installed, the idea is just to install the smallest bit possible and this will not affect or impact other things on your system.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - You will need to download the Nvidia Cuda Toolkit 11.8<span style="color: #3366ff;"> network</span> install from [here](https://developer.nvidia.com/cuda-11-8-0-download-archive) 
                 #### &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 1) Run the installer and select <span style="color: #3366ff;">Custom Advanced</span> Uncheck <span style="color: #3366ff;">everything</span> at the top then expand <span style="color: #3366ff;">CUDA</span>, <span style="color: #3366ff;">Development</span> > <span style="color: #3366ff;">Compiler</span> > and select <span style="color: #3366ff;;">nvcc</span> then expand <span style="color: #3366ff;;">Libraries</span> and select <span style="color: #3366ff;;">CUBLAS</span>.
                 #### &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 2) Back at the top of <span style="color: #3366ff;">CUDA</span>, expand <span style="color: #3366ff;">Runtime</span> > <span style="color: #3366ff;">Libraries</span> and select <span style="color: #3366ff;">CUBLAS</span>. Click <span style="color: #3366ff;;">Next</span>, accept the default path (taking a note of its location) and let the install run. 
                 #### &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 3) You should be able to drop to your terminal or command prompt and type <span style="color: #3366ff;">nvcc --version</span> and have it report <span style="color: #00a000;">Cuda compilation tools, release 11.8</span>. If it does you are good to go. If it doesn't > Step 4.
@@ -657,16 +914,18 @@ if __name__ == "__main__":
                 f"""
                 ## <u>STEP 1 - Preparing Audio/Generating the dataset</u><br>
                 ### 🟦 <u>What you need to do</u>
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 Please read Coqui's guide on what makes a good dataset [here](https://docs.coqui.ai/en/latest/what_makes_a_good_dataset.html#what-makes-a-good-dataset)
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 Place your audio files in <span style="color: #3366ff;">{str(audio_folder)}</span>                
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 Your audio samples can be in the format <span style="color: #3366ff;">mp3, wav,</span> or <span style="color: #3366ff;">flac.</span>
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 You will need a minimum of <span style="color: #3366ff;">2 minutes</span> of audio in either one or multiple audio files. 
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 When you have completed Steps 1, 2, and 3, you are welcome to delete your samples from "put-voice-samples-in-here".<br>
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - Please read Coqui's guide on what makes a good dataset [here](https://docs.coqui.ai/en/latest/what_makes_a_good_dataset.html#what-makes-a-good-dataset)
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - Place your audio files in <span style="color: #3366ff;">{str(audio_folder)}</span>                
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - Your audio samples can be in the format <span style="color: #3366ff;">mp3, wav,</span> or <span style="color: #3366ff;">flac.</span>
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - You will need a minimum of <span style="color: #3366ff;">2 minutes</span> of audio in either one or multiple audio files. Very small sample files cause errors, so I would suggest 30 seconds and longer samples. 
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - When you have completed Steps 1, 2, and 3, you are welcome to delete your samples from "put-voice-samples-in-here".
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - FYI Anecdotal evidence suggests that the Whisper 2 model may yield superior results in audio splitting and dataset creation.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - If this step is failing, it will be worth running the diagnostics with atsetup and confirming you have cu118 or cu112 listed against your torch and torchaudio.<br>
                 ### 🟨 <u>What this step is doing</u>
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟨 With step one, we are going to be stripping your audio file(s) into smaller files, using Whisper to find spoken words/sentences, compile that into excel sheets of training data, ready for finetuning the model on Step 2.
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟨 Whilst you can choose multiple Whisper models, its best only to use the 1 model as each one is about 3GB in size and will download to your local huggingface cache on first-time use. If and when you have completed training, you wish to delete this 3GB model from your system, you are welcome to do so.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - With step one, we are going to be stripping your audio file(s) into smaller files, using Whisper to find spoken words/sentences, compile that into excel sheets of training data, ready for finetuning the model on Step 2.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - Whilst you can choose multiple Whisper models, its best only to use the 1 model as each one is about 3GB in size and will download to your local huggingface cache on first-time use. If and when you have completed training, you wish to delete this 3GB model from your system, you are welcome to do so.
                 ### 🟩 <u>How long will this take?</u>
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟩 First time, it needs to download the Whisper model which is 3GB. After that a few minutes on an average 3-4 year old system.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - First time, it needs to download the Whisper model which is 3GB. After that a few minutes on an average 3-4 year old system.
                 """
             )
                  
@@ -675,41 +934,49 @@ if __name__ == "__main__":
                 value=out_path,
                 visible=False,
             )
+            with gr.Row():
+                whisper_model = gr.Dropdown(
+                    label="Whisper Model",
+                    value="large-v3",
+                    choices=[
+                        "large-v3",
+                        "large-v2",
+                        "large",
+                        "medium",
+                        "small"
+                    ],
+                )
 
-            whisper_model = gr.Dropdown(
-                label="Whisper Model",
-                value="large-v3",
-                choices=[
-                    "large-v3",
-                    "large-v2",
-                    "large",
-                    "medium",
-                    "small"
-                ],
-            )
+                lang = gr.Dropdown(
+                    label="Dataset Language",
+                    value="en",
+                    choices=[
+                        "en",
+                        "es",
+                        "fr",
+                        "de",
+                        "it",
+                        "pt",
+                        "pl",
+                        "tr",
+                        "ru",
+                        "nl",
+                        "cs",
+                        "ar",
+                        "zh",
+                        "hu",
+                        "ko",
+                        "ja"
+                    ],
+                )
 
-            lang = gr.Dropdown(
-                label="Dataset Language",
-                value="en",
-                choices=[
-                    "en",
-                    "es",
-                    "fr",
-                    "de",
-                    "it",
-                    "pt",
-                    "pl",
-                    "tr",
-                    "ru",
-                    "nl",
-                    "cs",
-                    "ar",
-                    "zh",
-                    "hu",
-                    "ko",
-                    "ja"
-                ],
-            )
+                eval_split_number = gr.Number(
+                    label="Evaluation data Split (the % to use for Evaluation data)",
+                    value=15,  # Default value
+                    minimum=5,  # Minimum value
+                    maximum=95,  # Maximum value
+                    step=1,  # Increment step
+                )
             progress_data = gr.Label(
                 label="Progress:"
             )
@@ -721,14 +988,14 @@ if __name__ == "__main__":
 
             prompt_compute_btn = gr.Button(value="Step 1 - Create dataset")
         
-            def preprocess_dataset(language,  whisper_model, out_path, progress=gr.Progress(track_tqdm=True)):
+            def preprocess_dataset(language,  whisper_model, out_path, eval_split_number, progress=gr.Progress(track_tqdm=True)):
                 clear_gpu_cache()
                 test_for_audio_files = [file for file in os.listdir(audio_folder) if any(file.lower().endswith(ext) for ext in ['.wav', '.mp3', '.flac'])]
                 if not test_for_audio_files:
                     return "I cannot find any mp3, wav or flac files in the folder called 'put-voice-samples-in-here'", "", ""
                 else:
                     try:
-                        train_meta, eval_meta, audio_total_size = format_audio_list(target_language=language, whisper_model=whisper_model ,out_path=out_path, gradio_progress=progress)
+                        train_meta, eval_meta, audio_total_size = format_audio_list(target_language=language, whisper_model=whisper_model, out_path=out_path, eval_split_number=eval_split_number, gradio_progress=progress)
                     except:
                         traceback.print_exc()
                         error = traceback.format_exc()
@@ -744,6 +1011,7 @@ if __name__ == "__main__":
 
                 print("[FINETUNE] Dataset Generated. Move to Step 2")
                 return "Dataset Generated. Move to Step 2", train_meta, eval_meta
+            
 #######################
 #### GRADIO STEP 2 ####
 #######################
@@ -753,51 +1021,67 @@ if __name__ == "__main__":
                 f"""
                 ## <u>STEP 2 - Fine-tuning the XTTS Encoder</u><br>
                 ### 🟦 <u>What you need to do</u>
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 The <span style="color: #3366ff;">Train CSV</span> and <span style="color: #3366ff;">Eval CSV</span> should already be populated. If not, just go back to Step 1 and click the button again.             
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 If for any reason it crashed, close the app and re-start the finetuning and kick it off again, clicking through setp 1 (it doesnt need to regenerate the data)
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 The settings below are factory and should be ok.<br>
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - The <span style="color: #3366ff;">Train CSV</span> and <span style="color: #3366ff;">Eval CSV</span> should already be populated. If not, just go back to Step 1 and click the button again.             
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - If for any reason it crashed, close the app and re-start the finetuning and kick it off again, clicking through setp 1 (it doesnt need to regenerate the data)
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - The settings below are factory and should be ok.<br>
                 ### 🟨 <u>What this step is doing</u>
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟨 Very simply put, it's taking all our wav files generated in Step 1, along with our recorded speech in out excel documents and its training the model on that voice.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - Very simply put, it's taking all our wav files generated in Step 1, along with our recorded speech in out excel documents and its training the model on that voice.
                 ### 🟩 <u>How long will this take?</u>
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟩 On a RTX 4070 with factory settings (as below) and 20 minutes of audio, this took 20 minutes. Again, it will vary by system and how much audio you are throwing at it. You have time to go make a coffee.
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟩 Look at your command prompt/terminal window if you want to see what it is doing.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - On a RTX 4070 with factory settings (as below) and 20 minutes of audio, this took 20 minutes. Again, it will vary by system and how much audio you are throwing at it. You have time to go make a coffee.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - Look at your command prompt/terminal window if you want to see what it is doing.
                 """
             )
+            with gr.Row():
+                train_csv = gr.Textbox(
+                    label="Train CSV:",
+                )
+                eval_csv = gr.Textbox(
+                    label="Eval CSV:",
+                )
+            with gr.Row():
+                num_epochs =  gr.Slider(
+                    label="Number of epochs:",
+                    minimum=1,
+                    maximum=100,
+                    step=1,
+                    value=args.num_epochs,
+                )
+                batch_size = gr.Slider(
+                    label="Batch size:",
+                    minimum=2,
+                    maximum=512,
+                    step=1,
+                    value=args.batch_size,
+                )
+                grad_acumm = gr.Slider(
+                    label="Grad accumulation steps:",
+                    minimum=2,
+                    maximum=128,
+                    step=1,
+                    value=args.grad_acumm,
+                )
+                max_audio_length = gr.Slider(
+                    label="Max permitted audio size in seconds:",
+                    minimum=2,
+                    maximum=20,
+                    step=1,
+                    value=args.max_audio_length,
+                )
+            with gr.Row():
+                model_to_train_choices = ["Base Model"]
+                if finetuned_model:
+                    model_to_train_choices.append("Existing finetuned model")
+                model_to_train = gr.Radio(
+                    choices=model_to_train_choices,
+                    label="Which model do you want to train?",
+                    value="Base Model"
+                )
+                gr.Markdown(
+                f"""
+                ##### If you have an existing finetuned model in <span style="color: #3366ff;">/models/trainedmodel/</span> you will have an option to select <span style="color: #3366ff;">Existing finetuned model</span>, allowing you to further train it. Otherwise, you will only have Base Model as an option.
+                """
+                )
 
-            train_csv = gr.Textbox(
-                label="Train CSV:",
-            )
-            eval_csv = gr.Textbox(
-                label="Eval CSV:",
-            )
-            num_epochs =  gr.Slider(
-                label="Number of epochs:",
-                minimum=1,
-                maximum=100,
-                step=1,
-                value=args.num_epochs,
-            )
-            batch_size = gr.Slider(
-                label="Batch size:",
-                minimum=2,
-                maximum=512,
-                step=1,
-                value=args.batch_size,
-            )
-            grad_acumm = gr.Slider(
-                label="Grad accumulation steps:",
-                minimum=2,
-                maximum=128,
-                step=1,
-                value=args.grad_acumm,
-            )
-            max_audio_length = gr.Slider(
-                label="Max permitted audio size in seconds:",
-                minimum=2,
-                maximum=20,
-                step=1,
-                value=args.max_audio_length,
-            )
             progress_train = gr.Label(
                 label="Progress:"
             )
@@ -839,16 +1123,16 @@ if __name__ == "__main__":
                 f"""
                 ## <u>STEP 3 -  Inference/Testing</u><br>
                 ### 🟥 <u>Important Note</u>
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟥 This step will error if you are using TTS version 0.22.0. Please re-run  <span style="color: #3366ff;">pip install -r requirements_finetune.txt</span> if it errors loading the model.
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟥 If you dont see multiple speaker reference files and you used more than 3 minutes of speech, try refreshing the page as it may not have loaded them correctly.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - This step will error if you are using TTS version 0.22.0. Please re-run  <span style="color: #3366ff;">pip install -r requirements_finetune.txt</span> if it errors loading the model.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - If you dont see multiple speaker reference files and you used more than 3 minutes of speech, try refreshing the page as it may not have loaded them correctly.
                 ### 🟦 <u>What you need to do</u>
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 The model is now trained and you are at the testing stage. Hopefully all the dropdowns should be pre-populated now.
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 You need to <span style="color: #3366ff;">Load Fine-tuned XTTS model</span> and then select your <span style="color: #3366ff;">Speaker Reference Audio</span>. You can choose various <span style="color: #3366ff;">Speaker Reference Audios</span> to see which works best.
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 All the <span style="color: #3366ff;">Speaker Reference Audios</span> in the dropdown are ones that are <span style="color: #3366ff;">8 seconds</span> long or more. You can use one of these later for your voice sample in All Talk, so remember the one you like.
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 Some <span style="color: #3366ff;">Speaker Reference Audios</span> are a bit long and may cause issues generating the TTS, so try different ones.
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 Once you are happy, move to the next tab for instruction on cleaning out the training data and how to copy your newly trained model over your current model.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - The model is now trained and you are at the testing stage. Hopefully all the dropdowns should be pre-populated now.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - You need to <span style="color: #3366ff;">Load Fine-tuned XTTS model</span> and then select your <span style="color: #3366ff;">Speaker Reference Audio</span>. You can choose various <span style="color: #3366ff;">Speaker Reference Audios</span> to see which works best.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - All the <span style="color: #3366ff;">Speaker Reference Audios</span> in the dropdown are ones that are <span style="color: #3366ff;">8 seconds</span> long or more. You can use one of these later for your voice sample in All Talk, so remember the one you like.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - Some <span style="color: #3366ff;">Speaker Reference Audios</span> are a bit long and may cause issues generating the TTS, so try different ones.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - Once you are happy, move to the next tab for instruction on cleaning out the training data and how to copy your newly trained model over your current model.
                 ### 🟨 <u>What this step is doing</u>
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟨 Its loading the finetuned model into memory, loading a voice sample and generating TTS, so that you can test out how well fine tuning worked.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - Its loading the finetuned model into memory, loading a voice sample and generating TTS, so that you can test out how well fine tuning worked.
                 """
             )
 
@@ -941,22 +1225,57 @@ if __name__ == "__main__":
                 f"""
                 ## <u>What to do next</u><br>
                 ### 🟦 <u>What you need to do</u>
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 The wav(s) you liked from <span style="color: #3366ff;">Speaker Reference Audios</span> are in <span style="color: #3366ff;">/finetune/tmp-trn/wavs/</span> so copy the one(s) you selected to your <span style="color: #3366ff;">/alltalk_tts/voices/</span> samples folder.
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 You can delete your original samples from inside of the <span style="color: #3366ff;">/finetune/put-voice-samples-in-here/</span> folder.
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 In the folder <span style="color: #3366ff;">/finetune/tmp-trn/training/XTTS_FT(date here)/</span> you will find your <span style="color: #3366ff;">best_model.pth</span>, <span style="color: #3366ff;">config.json</span> and <span style="color: #3366ff;">vocab.json</span> (also the last epoch training best_model_xxx.pth)
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 You can delete the last epoch training model file <span style="color: #3366ff;">best_model_xxx.pth</span> (the one with the numbers).
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 You will need to rename <span style="color: #3366ff;">best_model.pth</span> to <span style="color: #3366ff;">model.pth</span>.
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 You will close the Finetuning application and copy your 3 files listed above over the top of the existing model files inside your <span style="color: #3366ff;">/alltalk_tts/models/xttsv2_2.0.2/</span> folder. 
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟦 Start up Alltalk and you should be off and running. Preferably use the <span style="color: #3366ff;">XTTS Local</span> method for best results. 
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - You have a few options below:
+                #### &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 🔹 Compact &amp; move model. This will compress the raw finetuned model and move it, along with any large enough wav files created to one of two locations (please read text next to the button).<br>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; You can use the wav files in that location as sample voices with your model. Models moved to <span style="color: #3366ff;">/models/trainedmodel/</span> will be loadable within Text-gen-webui on the <span style="color: #3366ff;">XTTSv2 FT</span> loader.
+                #### &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 🔹 Delete Generated Training data. This will delete the finetuned model and any other training data generated during this process. You will more than likely want to do this after you have Compacted &amp; moved the model.
+                #### &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 🔹 Delete original voice samples. This will delete the voice samples you placed in put-voice-samples-in-here (if you no longer have a use for them).
+                #### &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 🔹 Compress a legacy finetuned model. For any models that were generated pre the current version of finetuning, you can still compact them down.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - Instructions on using the finetuned model in Text-generation-webui and also further tuning this model you just created are on <span style="color: #3366ff;">OPTION A - Compact and move model to '/trainedmodel/'</span>.
                 ### 🟨 <u>Clearing up disk space</u>
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟨 When you are happy with everything, you can delete the <span style="color: #3366ff;">/alltalk_tts/finetune/tmp-trn/</span> folder. This will delete all training data that was generated.
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟨 If you are not going to train anything again, you can delete the whisper model from inside of your huggingface cache (3GB approx) 
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - If you are not going to train anything again, you can delete the whisper model from inside of your huggingface cache (3GB approx) 
                 #### &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; Linux <span style="color: #3366ff;">~/.cache/huggingface/hub/(folder-here)</span>
                 #### &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; Windows <span style="color: #3366ff;">C:&bsol;users&lpar;your-username&rpar;&bsol;.cache&bsol;huggingface&bsol;hub&bsol;(folder-here)</span>.
-                #### &nbsp;&nbsp;&nbsp;&nbsp; 🟨 You can also uninstall the Nvidia CUDA 11.8 Toolkit if you wish and remove your environment variable entries.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - You can also uninstall the Nvidia CUDA 11.8 Toolkit if you wish and remove your environment variable entries.
                 """
             )
-
+            final_progress_data = gr.Label(
+                label="Progress:"
+            )
+            with gr.Row():
+                compact_btn = gr.Button(value="OPTION A - Compact and move model to '/trainedmodel/'")
+                gr.Markdown(
+                f"""
+                ##### This will compact the model and move it, along with the reference wav's to <span style="color: #3366ff;">/models/trainedmodel/</span> and will <span style="color: red;">OVERWRITE</span> any model in that location. This model will become available to load in Text-gen-webui with the <span style="color: #3366ff;">XTTSv2 FT</span> loader. It will also be detected by Finetune as a model that can be further trained (Reload finetune.py).
+                """
+                )
+            with gr.Row():
+                compact_lastfinetuned_btn = gr.Button(value="OPTION B - Compact and move model to '/lastfinetuned/'")
+                gr.Markdown(
+                f"""
+                ##### This will compact the model and move it, along with the reference wav's to <span style="color: #3366ff;">/models/lastfinetuned/</span> and will <span style="color: red;">OVERWRITE</span> any model in that location. This will just leave you a finetuned model that you can do with as you please. It will <span style="color: red;">NOT</span> be available in Text-gen-webui unless you copy it over one of the other model loader locations.
+                """
+                )
+            with gr.Row():
+                delete_training_btn = gr.Button(value="Delete generated training data")
+                gr.Markdown(
+                f"""
+                ##### This will <span style="color: red;">DELETE</span> your training data and the raw finetuned model from <span style="color: #3366ff;">/finetune/tmp-trn/</span>.
+                """
+                )
+            with gr.Row():
+                delete_voicesamples_btn = gr.Button(value="Delete original voice samples")
+                gr.Markdown(
+                f"""
+                ##### This will <span style="color: red;">DELETE</span> your original voice samples from <span style="color: #3366ff;">/finetune/put-voice-samples-in-here/</span>.
+                """
+                )
+            with gr.Row():
+                compact_legacy_btn = gr.Button(value="Compact a legacy finetuned model")
+                gr.Markdown(
+                f"""
+                ##### This will compact your old finetuned models from 5GB to 1.9GB. Place your 5GB <span style="color: #3366ff;">base_model.pth</span> file in <span style="color: #3366ff;">/finetune/</span> (rename your file to <span style="color: #3366ff;">base_model.pth</span> if necessary). This will generate you a <span style="color: #3366ff;">model.pth</span> file.
+                """
+                )
 
             prompt_compute_btn.click(
                 fn=preprocess_dataset,
@@ -964,6 +1283,7 @@ if __name__ == "__main__":
                     lang,
                     whisper_model,
                     out_path,
+                    eval_split_number,
                 ],
                 outputs=[
                     progress_data,
@@ -1007,6 +1327,28 @@ if __name__ == "__main__":
                 ],
                 outputs=[progress_gen, tts_output_audio, reference_audio],
             )
+            
+            compact_btn.click(
+                fn=compact_model,
+                outputs=[final_progress_data],
+            )
+            compact_lastfinetuned_btn.click(
+                fn=compact_lastfinetuned_model,
+                outputs=[final_progress_data],
+            )
+            delete_training_btn.click(
+                fn=delete_training_data,
+                outputs=[final_progress_data],
+            )
+            delete_voicesamples_btn.click(
+                fn=delete_voice_sample_contents,
+                outputs=[final_progress_data],
+            )
+            compact_legacy_btn.click(
+                fn=compact_legacy_model,
+                outputs=[final_progress_data],
+            )
+            model_to_train.change(basemodel_or_finetunedmodel_choice, model_to_train, None)
 
     demo.queue().launch(
         show_api=False,

finetune/compact.py

@@ -0,0 +1,26 @@
+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.")

launch.sh

@@ -0,0 +1,5 @@
+#!/bin/sh
+python modeldownload.py
+uvicorn tts_server:app --host 0.0.0.0 --port 7851 --workers 1 --proxy-headers &
+sleep 5
+python script.py

modeldownload.json

@@ -8,6 +8,7 @@
         "model.pth": "https://huggingface.co/coqui/XTTS-v2/resolve/v2.0.2/model.pth?download=true",
         "dvae.pth": "https://huggingface.co/coqui/XTTS-v2/resolve/v2.0.2/dvae.pth?download=true",
         "mel_stats.pth": "https://huggingface.co/coqui/XTTS-v2/resolve/v2.0.2/mel_stats.pth?download=true",
+        "speakers_xtts.pth": "https://huggingface.co/coqui/XTTS-v2/resolve/v2.0.2/speakers_xtts.pth?download=true",
         "vocab.json": "https://huggingface.co/coqui/XTTS-v2/resolve/v2.0.2/vocab.json?download=true"
     }
-}
+}

nvidia.Dockerfile

@@ -0,0 +1,20 @@
+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
+ENTRYPOINT ["sh", "-c", "./launch.sh"]

requirements_nvidia.txt

@@ -1,6 +1,7 @@
 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
@@ -11,3 +12,7 @@ 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

requirements_other.txt

@@ -1,6 +1,7 @@
 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
 torchaudio>=2.1.0
@@ -11,3 +12,7 @@ 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

@@ -16,18 +16,28 @@ import numpy as np
 import soundfile as sf
 import uuid
 
+######################################
+#### ALLTALK ALLOWED STARTUP TIME ####
+######################################
+startup_wait_time = 120
+
+# You can change the above setting to a larger number to allow AllTAlk more time to start up. The default setting is 120 seconds (2 minutes).
+# On some older systems you may need to allow AllTalk more time. So you could set it to 240 (4 minutes) which will give AllTalk more to load.
+
 #################################################################
 #### LOAD PARAMS FROM confignew.json - REQUIRED FOR BRANDING ####
 #################################################################
 # 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)
@@ -48,6 +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
@@ -60,6 +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"]
@@ -77,11 +89,15 @@ with open(this_dir / "languages.json", encoding="utf8") as f:
     languages = json.load(f)
 # Create a global lock
 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 ####
 #########################
@@ -143,6 +159,22 @@ def check_required_files():
 # STARTUP Call Check routine
 check_required_files()
 
+##################################################
+#### Check to see if a finetuned model exists ####
+##################################################
+# Set the path to the directory
+trained_model_directory = this_dir / "models" / "trainedmodel"
+# Check if the directory "trainedmodel" exists
+finetuned_model = trained_model_directory.exists()
+# If the directory exists, check for the existence of the required files
+# 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
+    )
+if finetuned_model:
+    print(f"[{params['branding']}Startup] Finetuned model \033[93mDetected\033[0m")
 
 ####################################################
 #### SET GRADIO BUTTONS BASED ON confignew.json ####
@@ -158,6 +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 ####
 ######################
@@ -215,68 +248,88 @@ 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")
+# Check if we're running in docker
+if os.path.isfile("/.dockerenv"):
     print(
-        f"[{params['branding']}Startup] Readme available here:",
-        f"http://{params['ip_address']}:{params['port_number']}",
+        f"[{params['branding']}Startup] \033[94mRunning in Docker. Please wait.\033[0m"
     )
 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 = 120  # Adjust the timeout as needed
-
-# Introduce a delay before starting the check loop
-time.sleep(25)  # Wait 25 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
+    # 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 120 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(1)
-else:
-    print(
-        f"[{params['branding']}Startup] Startup timed out. Check the server logs for more information."
-    )
-    # 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)
+
 
 #####################################
 #### MODEL LOADING AND UNLOADING ####
 #####################################
 # MODEL - Swap model based on Gradio selection API TTS, API Local, XTTSv2 Local
 def send_reload_request(tts_method):
+    global tts_method_xtts_ft
     try:
         params["tts_model_loaded"] = False
         url = f"{base_url}/api/reload"
@@ -295,17 +348,26 @@ def send_reload_request(tts_method):
                 params["tts_method_api_tts"] = True
                 params["deepspeed_activate"] = False
                 audio_path = this_dir / "templates" / "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"
+                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"
+                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"
+                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
@@ -314,6 +376,7 @@ def send_reload_request(tts_method):
         )
         return {"status": "error", "message": str(e)}
 
+
 ##################
 #### LOW VRAM ####
 ##################
@@ -354,7 +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)
@@ -428,9 +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:
@@ -461,12 +528,19 @@ def voice_preview(string):
     output_file = Path(params["output_folder_wav"]) / "voice_preview.wav"
     # Generate the audio
     language_code = languages.get(params["language"])
+    temperature = params["local_temperature"]
+    repetition_penalty = params["local_repetition_penalty"]
     # Convert the WindowsPath object to a string before using it in JSON payload
     output_file_str = output_file.as_posix()
     # Lock before making the generate request
     with process_lock:
         generate_response = send_generate_request(
-            string, params["voice"], language_code, output_file_str
+            string,
+            params["voice"],
+            language_code,
+            temperature,
+            repetition_penalty,
+            output_file_str,
         )
     # Check if lock is already acquired
     if process_lock.locked():
@@ -483,6 +557,55 @@ def voice_preview(string):
         return f"[{params['branding']}Server] Audio generation failed. Status: {generate_response.get('status')}"
 
 
+def process_text(text):
+    # Normalize HTML encoded quotes
+    text = html.unescape(text)
+
+    # Replace ellipsis with a single dot
+    text = re.sub(r"\.{3,}", ".", text)
+
+    # Pattern to identify combined narrator and character speech
+    combined_pattern = r'(\*[^*"]+\*|"[^"*]+")'
+
+    # List to hold parts of speech along with their type
+    ordered_parts = []
+
+    # Track the start of the next segment
+    start = 0
+
+    # Find all matches
+    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()
+            if 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()))
+        elif matched_text.startswith('"') and matched_text.endswith('"'):
+            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('"')))
+            else:
+                ordered_parts.append(("character", matched_text.strip('"').strip("*")))
+
+        # Update the start of the next segment
+        start = match.end()
+
+    # Add any remaining text after the last match as ambiguous
+    if start < len(text):
+        ambiguous_text = text[start:].strip()
+        if ambiguous_text:
+            ordered_parts.append(("ambiguous", ambiguous_text))
+
+    return ordered_parts
+
+
 #################################
 #### TTS STANDARD GENERATION ####
 #################################
@@ -491,94 +614,103 @@ 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)
     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"]
     # Create a list to store generated audio paths
     audio_files = []
     if process_lock.acquire(blocking=False):
         try:
             if params["narrator_enabled"]:
-                # print(original_string)
-                # Do Some basic stripping and remove any double CR's
-                processed_string = (
-                    original_string
-                    .replace("***", "*")
-                    .replace("**", "*")
-                    .replace("\n\n", "\n")
-                )
-                # Clean up two asterisks (narrators) being made between a newline, making it one sentence.
-                processed_string = re.sub(r'\.\*\n\*', '. ', processed_string)
-                # Clean up a few other bits.
-                processed_string = (
-                    processed_string
-                    .replace("&#x27;", "'")
-                    .replace("\n", " ")
-                    # Add special characters to the quote so that we can use it to identify things later after its been split
-                    .replace('&quot;', '&quot;<')
-                    # Capture new conversations which wont have things like &quote in them
-                    .replace('"', '&quot;<')
-                )
-                #capturing another outlier in inital character paragraph
-                # print("processed string 1 is:", processed_string)
-                processed_string = processed_string.replace('&quot;<. *', '&quot;< *"')
-                processed_string = processed_string.replace('< *"', '< *')
-                processed_string = processed_string.replace('. *', '< *')
-                # print("processed string 2 is:", processed_string)
-                # Set up a tracking of the individual wav files.
+                processed_parts = process_text(original_string)
+
                 audio_files_all_paragraphs = []
-                # Split the line using &quot; and ".* " (so end of sentences, leaving special characters added to the start of all OTHER sentences, bar possibly the first one if its starting with a *
-                parts = re.split(r'&quot;|\.\*', processed_string)
-                audio_files_paragraph = []
-                for i, part in enumerate(parts):
+                for part_type, part in processed_parts:
                     # Skip parts that are too short
-                    if len(part.strip()) <= 1:
+                    if len(part.strip()) <= 3:
                         continue
-                    # Figure out which type of line it is, then replace characters as necessary to avoid TTS trying to pronunce them, htmlunescape after. 
-                    # Character will always be a < with a letter immediately after it
-                    if '<' in part and '< *' not in part and '<*' not in part and '<  *' not in part and '< ' not in part and '<  ' not in part:
-                        cleaned_part = html.unescape(part.replace('<', ''))
-                        voice_to_use = params["voice"]
-                    #Narrator will always be an * or < with an * a position or two after it.
-                    elif '<*' in part or '< *' in part or '<  *' in part or '*' in part:
-                        cleaned_part = html.unescape(part.replace('<*', '').replace('< *', '').replace('<  *', '').replace('*', ''))
+
+                    # Determine the voice to use based on the part type
+                    if part_type == "narrator":
                         voice_to_use = params["narrator_voice"]
-                    #If the other two dont capture it, aka, the AI gave no * or &quot; on the line, use non_quoted_text_is aka user interface, user can choose Char or Narrator
-                    elif non_quoted_text_is:
-                        cleaned_part = html.unescape(part.replace('< ', '').replace('<  ', '').replace('<  ', ''))
+                        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
                     else:
-                        cleaned_part = html.unescape(part.replace('< ', '').replace('<  ', '').replace('<  ', ''))
-                        voice_to_use = params["narrator_voice"]
-                    # Generate that TTS and output to a file
+                        # 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"
+                        )
+                        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)
+                    # 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)
+                    # Remove all newline characters (single or multiple)
+                    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, 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_paragraph.append(audio_path)
-                # Accumulate audio files within the paragraph
-                audio_files_all_paragraphs.extend(audio_files_paragraph)
+                    audio_files_all_paragraphs.append(audio_path)
+
                 # Combine audio files across paragraphs
                 final_output_file = combine(
                     audio_files_all_paragraphs, params["output_folder_wav"], state
                 )
             else:
-                processed_string = (
-                    original_string
-                    .replace("***", "")
-                    .replace("**", "")
-                    .replace("*", "")
-                    .replace("\n\n", "\n")
-                    .replace("&#x27;", "'")
-                )
-                cleaned_part = html.unescape(processed_string)                
+                # 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)
+                # 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)
+                # 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.
-                output_filename = get_output_filename(state)
+                if "character_menu" in state:
+                    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_str = output_file.as_posix()
+                output_file = get_output_filename(state)
                 generate_response = send_generate_request(
-                    cleaned_part, params["voice"], language_code, output_filename
+                    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
@@ -618,22 +750,29 @@ def output_modifier(string, state):
 
 
 def get_output_filename(state):
-     # Check if character name exists and if not, just call it TTSOUT_
     if "character_menu" in state:
-        return Path(f'{params["output_folder_wav"]}/{state["character_menu"]}_{int(time.time())}.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_{int(time.time())}.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, output_file):
+def send_generate_request(
+    text, voice, language, temperature, repetition_penalty, output_file
+):
     url = f"{base_url}/api/generate"
     payload = {
         "text": text,
         "voice": voice,
         "language": language,
+        "temperature": temperature,
+        "repetition_penalty": repetition_penalty,
         "output_file": output_file,
     }
     headers = {"Content-Type": "application/json"}
@@ -658,12 +797,14 @@ 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":
@@ -671,6 +812,7 @@ 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
@@ -678,42 +820,56 @@ def input_modifier(string, state):
     shared.processing_message = "*Is recording a voice message...*"
     return string
 
-def custom_css():
-    path_to_css = Path(f"{this_dir}/style.css")
-    return open(path_to_css, "r").read()
-
 
 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="Activate TTS")
-            autoplay = gr.Checkbox(
-                value=params["autoplay"], label="Play TTS automatically"
-            )
+            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():
-            show_text = gr.Checkbox(
-                value=params["show_text"], label="Show message text under audio player"
+            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_play = gr.HTML(visible=False)
             remove_trailing_dots = gr.Checkbox(
-                value=params["remove_trailing_dots"],
-                label='Remove trailing "." from text segments before generation',
+                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"]
+            if finetuned_model:
+                model_loader_choices.append("XTTSv2 FT")
+            tts_radio_buttons = gr.Radio(
+                choices=model_loader_choices,
+                label="TTS Method (Each method sounds slightly different)",
+                value=gr_modelchoice,  # Set the default value
+            )
+            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:
-                    # Handle the case where the default voice is not in the list (choose a default value or update it)
                     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="Default Voice",
+                    label="Character Voice",
                     value=default_voice,
                     allow_custom_value=True,
                 )
@@ -727,14 +883,11 @@ def ui():
                     "refresh-button",
                 )
 
-            language = gr.Dropdown(
-                languages.keys(),
-                label="Language",
-                allow_custom_value=True,
-                value=params["language"],
-            )
-
+        # Language, Narrator voice
         with gr.Row():
+            language = gr.Dropdown(
+                languages.keys(), label="Language", value=params["language"]
+            )
             with gr.Row():
                 narrator_voice_gr = gr.Dropdown(
                     get_available_voices(),
@@ -751,40 +904,42 @@ def ui():
                     },
                     "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"],
+            )
+
+        # 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 Activation",
+                    label="Narrator",
                     value="Enabled" if params.get("narrator_enabled") else "Disabled",
                 )
                 non_quoted_text_is_gr = gr.Radio(
-                    choices={"Char": "true", "Narrator": "false"},
-                    label='Text NOT inside of * or " is',
-                    value="Char" if non_quoted_text_is else "Narrator",
+                    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>"
                 )
 
-        with gr.Row():
-            low_vram = gr.Checkbox(
-                value=params["low_vram"], label="Low VRAM mode (Read NOTE)"
-            )
-            low_vram_play = gr.HTML(visible=False)
-            deepspeed_checkbox = gr.Checkbox(
-                value=params["deepspeed_activate"],
-                label="Activate DeepSpeed (Read NOTE)",
-                visible=deepspeed_installed,
-            )
-            deepspeed_checkbox_play = gr.HTML(visible=False)
-
-        with gr.Row():
-            tts_radio_buttons = gr.Radio(
-                choices=["API TTS", "API Local", "XTTSv2 Local"],
-                label="Select TTS Generation Method (Read NOTE)",
-                value=gr_modelchoice,  # Set the default value
-            )
-            tts_radio_buttons_play = gr.HTML(visible=False)
-            explanation_text = gr.HTML(
-                f"<p>NOTE: Switching Model Type, Low VRAM & DeepSpeed, each takes 15 seconds. Each TTS generation method has a slightly different sound. DeepSpeed checkbox is only visible if DeepSpeed is present. Readme & Settings: <a href='http://{params['ip_address']}:{params['port_number']}'>http://{params['ip_address']}:{params['port_number']}</a>"
-            )
-
+        # Preview speech
         with gr.Row():
             preview_text = gr.Text(
                 show_label=False,
@@ -854,18 +1009,34 @@ 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
     )
     voice.change(lambda x: params.update({"voice": x}), voice, None)
     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,
+    )
+
     # 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)

style.css

@@ -1,8 +0,0 @@
-.SDAP .hires_opts input[type="number"] {
-    width: 6em !important;
-}
-
-/* silero_tts preview */
-.form:has(> #silero_preview_text) {
-    min-width: 75%
-}

templates/STfiles/alltalk.js

@@ -0,0 +1,833 @@
+import { doExtrasFetch, getApiUrl, modules } from '../../extensions.js';
+import { saveTtsProviderSettings } from './index.js';
+
+export { AllTalkTtsProvider };
+
+class AllTalkTtsProvider {
+    //########//
+    // Config //
+    //########//
+
+    settings = {};
+    constructor() {
+        // Initialize with default settings if they are not already set
+        this.settings = {
+            provider_endpoint: this.settings.provider_endpoint || 'http://localhost:7851',
+            language: this.settings.language || 'en',
+            voiceMap: this.settings.voiceMap || {},
+            at_generation_method: this.settings.at_generation_method || 'standard_generation',
+            narrator_enabled: this.settings.narrator_enabled || 'false',
+            at_narrator_text_not_inside: this.settings.at_narrator_text_not_inside || 'narrator',
+            narrator_voice_gen: this.settings.narrator_voice_gen || 'female_01.wav',
+            finetuned_model: this.settings.finetuned_model || 'false'
+        };
+        // Separate property for dynamically updated settings from the server
+        this.dynamicSettings = {
+            modelsAvailable: [],
+            currentModel: '',
+            deepspeed_available: false,
+            deepSpeedEnabled: false,
+            lowVramEnabled: false,
+        };
+    }
+    ready = false;
+    voices = [];
+    separator = '. ';
+    audioElement = document.createElement('audio');
+
+    languageLabels = {
+        'Arabic': 'ar',
+        'Brazilian Portuguese': 'pt',
+        'Chinese': 'zh-cn',
+        'Czech': 'cs',
+        'Dutch': 'nl',
+        'English': 'en',
+        'French': 'fr',
+        'German': 'de',
+        'Italian': 'it',
+        'Polish': 'pl',
+        'Russian': 'ru',
+        'Spanish': 'es',
+        'Turkish': 'tr',
+        'Japanese': 'ja',
+        'Korean': 'ko',
+        'Hungarian': 'hu',
+        'Hindi': 'hi',
+    };
+
+    get settingsHtml() {
+        let html = `<div class="at-settings-separator">AllTalk Settings</div>`;
+
+        html += `<div class="at-settings-row">
+
+        <div class="at-settings-option">
+            <label for="at_generation_method">AllTalk TTS Generation Method</label>
+                <select id="at_generation_method">
+                <option value="standard_generation">Standard Audio Generation (AT Narrator - Optional)</option>
+                <option value="streaming_enabled">Streaming Audio Generation (AT Narrator - Disabled)</option>
+        </select>
+        </div>
+        </div>`;
+
+        html += `<div class="at-settings-row">
+
+        <div class="at-settings-option">
+            <label for="at_narrator_enabled">AT Narrator</label>
+                <select id="at_narrator_enabled">
+                <option value="true">Enabled</option>
+                <option value="false">Disabled</option>
+        </select>
+        </div>
+
+        <div class="at-settings-option">
+            <label for="at_narrator_text_not_inside">Text Not Inside * or " is</label>
+                <select id="at_narrator_text_not_inside">
+                <option value="narrator">Narrator</option>
+                <option value="character">Character</option>
+        </select>
+        </div>
+
+    </div>`;
+
+        html += `<div class="at-settings-row">
+        <div class="at-settings-option">
+            <label for="narrator_voice">Narrator Voice</label>
+            <select id="narrator_voice">`;
+        if (this.voices) {
+            for (let voice of this.voices) {
+                html += `<option value="${voice.voice_id}">${voice.name}</option>`;
+            }
+        }
+        html += `</select>
+        </div>
+        <div class="at-settings-option">
+            <label for="language_options">Language</label>
+            <select id="language_options">`;
+        for (let language in this.languageLabels) {
+            html += `<option value="${this.languageLabels[language]}" ${this.languageLabels[language] === this.settings?.language ? 'selected="selected"' : ''}>${language}</option>`;
+        }
+        html += `</select>
+        </div>
+    </div>`;
+
+
+        html += `<div class="at-model-endpoint-row">
+    <div class="at-model-option">
+            <label for="switch_model">Switch Model</label>
+            <select id="switch_model">
+            <option value="api_tts">API TTS</option>
+            <option value="api_local">API Local</option>
+            <option value="xttsv2_local">XTTSv2 Local</option>
+        </select>
+        </div>
+
+        <div class="at-endpoint-option">
+            <label for="at_server">AllTalk Endpoint:</label>
+            <input id="at_server" type="text" class="text_pole" maxlength="80" value="${this.settings.provider_endpoint}"/>
+        </div>
+   </div>`;
+
+
+        html += `<div class="at-model-endpoint-row">
+    <div class="at-settings-option">
+        <label for="low_vram">Low VRAM</label>
+        <input id="low_vram" type="checkbox"/>
+    </div>
+    <div class="at-settings-option">
+        <label for="deepspeed">DeepSpeed</label>
+        <input id="deepspeed" type="checkbox"/>
+    </div>
+    <div class="at-settings-option status-option">
+        <span>Status: <span id="status_info">Ready</span></span>
+    </div>
+    <div class="at-settings-option empty-option">
+        <!-- This div remains empty for spacing -->
+    </div>
+</div>`;
+
+
+        html += `<div class="at-website-row">
+        <div class="at-website-option">
+        <span>AllTalk <a target="_blank" href="${this.settings.provider_endpoint}">Config & Docs</a>.</span>
+    </div>
+
+    <div class="at-website-option">
+        <span>AllTalk <a target="_blank" href="https://github.com/erew123/alltalk_tts/">Website</a>.</span>
+    </div>
+</div>`;
+
+        html += `<div class="at-website-row">
+<div class="at-website-option">
+<span><strong>Text-generation-webui</strong> users - Uncheck <strong>Enable TTS</strong> in Text-generation-webui.</span>
+</div>
+</div>`;
+
+        return html;
+    }
+
+
+    //#################//
+    // Startup ST & AT //
+    //#################//
+
+    async loadSettings(settings) {
+        updateStatus('Offline');
+
+        if (Object.keys(settings).length === 0) {
+            console.info('Using default AllTalk TTS Provider settings');
+        } else {
+            // Populate settings with provided values, ignoring server-provided settings
+            for (const key in settings) {
+                if (key in this.settings) {
+                    this.settings[key] = settings[key];
+                } else {
+                    console.debug(`Ignoring non-user-configurable setting: ${key}`);
+                }
+            }
+        }
+
+        // Update UI elements to reflect the loaded settings
+        $('#at_server').val(this.settings.provider_endpoint);
+        $('#language_options').val(this.settings.language);
+        //$('#voicemap').val(this.settings.voiceMap);
+        $('#at_generation_method').val(this.settings.at_generation_method);
+        $('#at_narrator_enabled').val(this.settings.narrator_enabled);
+        $('#at_narrator_text_not_inside').val(this.settings.at_narrator_text_not_inside);
+        $('#narrator_voice').val(this.settings.narrator_voice_gen);
+
+        console.debug('AllTalkTTS: Settings loaded');
+        try {
+            // Check if TTS provider is ready
+            await this.checkReady();
+            await this.updateSettingsFromServer(); // Fetch dynamic settings from the TTS server
+            await this.fetchTtsVoiceObjects(); // Fetch voices only if service is ready
+            this.updateNarratorVoicesDropdown();
+            this.updateLanguageDropdown();
+            this.setupEventListeners();
+            this.applySettingsToHTML();
+            updateStatus('Ready');
+        } catch (error) {
+            console.error("Error loading settings:", error);
+            updateStatus('Offline');
+        }
+    }
+
+    applySettingsToHTML() {
+        // Apply loaded settings or use defaults
+        const narratorVoiceSelect = document.getElementById('narrator_voice');
+        const atNarratorSelect = document.getElementById('at_narrator_enabled');
+        const textNotInsideSelect = document.getElementById('at_narrator_text_not_inside');
+        const generationMethodSelect = document.getElementById('at_generation_method');
+        this.settings.narrator_voice = this.settings.narrator_voice_gen;
+        // Apply settings to Narrator Voice dropdown
+        if (narratorVoiceSelect && this.settings.narrator_voice) {
+            narratorVoiceSelect.value = this.settings.narrator_voice.replace('.wav', '');
+        }
+        // Apply settings to AT Narrator Enabled dropdown
+        if (atNarratorSelect) {
+            // Sync the state with the checkbox in index.js
+            const ttsPassAsterisksCheckbox = document.getElementById('tts_pass_asterisks'); // Access the checkbox from index.js
+            const ttsNarrateQuotedCheckbox = document.getElementById('tts_narrate_quoted'); // Access the checkbox from index.js
+            const ttsNarrateDialoguesCheckbox = document.getElementById('tts_narrate_dialogues'); // Access the checkbox from index.js
+            // Sync the state with the checkbox in index.js
+            if (this.settings.narrator_enabled) {
+                ttsPassAsterisksCheckbox.checked = false;
+                $('#tts_pass_asterisks').click(); // Simulate a click event
+                $('#tts_pass_asterisks').trigger('change');
+            }
+            if (!this.settings.narrator_enabled) {
+                ttsPassAsterisksCheckbox.checked = true;
+                $('#tts_pass_asterisks').click(); // Simulate a click event
+                $('#tts_pass_asterisks').trigger('change');
+            }
+            // Uncheck and set tts_narrate_quoted to false if narrator is enabled
+            if (this.settings.narrator_enabledd) {
+                ttsNarrateQuotedCheckbox.checked = true;
+                ttsNarrateDialoguesCheckbox.checked = true;
+                // Trigger click events instead of change events
+                $('#tts_narrate_quoted').click();
+                $('#tts_narrate_quoted').trigger('change');
+                $('#tts_narrate_dialogues').click();
+                $('#tts_narrate_dialogues').trigger('change');
+            }
+            atNarratorSelect.value = this.settings.narrator_enabled.toString();
+            this.settings.narrator_enabled = this.settings.narrator_enabled.toString();
+        }
+        // Apply settings to the Language dropdown
+        const languageSelect = document.getElementById('language_options');
+        if (languageSelect && this.settings.language) {
+            languageSelect.value = this.settings.language;
+        }
+        // Apply settings to Text Not Inside dropdown
+        if (textNotInsideSelect && this.settings.text_not_inside) {
+            textNotInsideSelect.value = this.settings.text_not_inside;
+            this.settings.at_narrator_text_not_inside = this.settings.text_not_inside;
+        }
+        // Apply settings to Generation Method dropdown
+        if (generationMethodSelect && this.settings.at_generation_method) {
+            generationMethodSelect.value = this.settings.at_generation_method;
+        }
+        // Additional logic to disable/enable dropdowns based on the selected generation method
+        const isStreamingEnabled = this.settings.at_generation_method === 'streaming_enabled';
+        if (isStreamingEnabled) {
+            // Disable certain dropdowns when streaming is enabled
+            if (atNarratorSelect) atNarratorSelect.disabled = true;
+            if (textNotInsideSelect) textNotInsideSelect.disabled = true;
+            if (narratorVoiceSelect) narratorVoiceSelect.disabled = true;
+        } else {
+            // Enable dropdowns for standard generation
+            if (atNarratorSelect) atNarratorSelect.disabled = false;
+            if (textNotInsideSelect) textNotInsideSelect.disabled = !this.settings.narrator_enabled;
+            if (narratorVoiceSelect) narratorVoiceSelect.disabled = !this.settings.narrator_enabled;
+        }
+        const modelSelect = document.getElementById('switch_model');
+        if (this.settings.finetuned_model === 'true') {
+            const ftOption = document.createElement('option');
+            ftOption.value = 'XTTSv2 FT';
+            ftOption.textContent = 'XTTSv2 FT';
+            modelSelect.appendChild(ftOption);
+        }
+    }
+
+    //##############################//
+    // Check AT Server is Available //
+    //##############################//
+
+    async checkReady() {
+        try {
+            const response = await fetch(`${this.settings.provider_endpoint}/api/ready`);
+            // Check if the HTTP request was successful
+            if (!response.ok) {
+                throw new Error(`HTTP Error Response: ${response.status} ${response.statusText}`);
+            }
+            const statusText = await response.text();
+            // Check if the response is 'Ready'
+            if (statusText === 'Ready') {
+                this.ready = true; // Set the ready flag to true
+                console.log('TTS service is ready.');
+            } else {
+                this.ready = false;
+                console.log('TTS service is not ready.');
+            }
+        } catch (error) {
+            console.error('Error checking TTS service readiness:', error);
+            this.ready = false; // Ensure ready flag is set to false in case of error
+        }
+    }
+
+    //######################//
+    // Get Available Voices //
+    //######################//
+
+    async fetchTtsVoiceObjects() {
+        const response = await fetch(`${this.settings.provider_endpoint}/api/voices`);
+        if (!response.ok) {
+            const errorText = await response.text();
+            throw new Error(`HTTP ${response.status}: ${errorText}`);
+        }
+        const data = await response.json();
+        const voices = data.voices.map(filename => {
+            const voiceName = filename.replace('.wav', '');
+            return {
+                name: voiceName,
+                voice_id: voiceName,
+                preview_url: null, // Preview URL will be dynamically generated
+                lang: 'en' // Default language
+            };
+        });
+        this.voices = voices; // Assign to the class property
+        return voices; // Also return this list
+    }
+
+    //##########################################//
+    // Get Current AT Server Config & Update ST //
+    //##########################################//
+
+    async updateSettingsFromServer() {
+        try {
+            // Fetch current settings
+            const response = await fetch(`${this.settings.provider_endpoint}/api/currentsettings`);
+            if (!response.ok) {
+                throw new Error(`Failed to fetch current settings: ${response.statusText}`);
+            }
+            const currentSettings = await response.json();
+            // Update internal settings
+            this.settings.modelsAvailable = currentSettings.models_available;
+            this.settings.currentModel = currentSettings.current_model_loaded;
+            this.settings.deepspeed_available = currentSettings.deepspeed_available;
+            this.settings.deepSpeedEnabled = currentSettings.deepspeed_status;
+            this.settings.lowVramEnabled = currentSettings.low_vram_status;
+            this.settings.finetuned_model = currentSettings.finetuned_model
+            // Update HTML elements
+            this.updateModelDropdown();
+            this.updateCheckboxes();
+        } catch (error) {
+            console.error(`Error updating settings from server: ${error}`);
+        }
+    }
+
+    //###################################################//
+    // Get Current AT Server Config & Update ST (Models) //
+    //###################################################//
+
+    updateModelDropdown() {
+        const modelSelect = document.getElementById('switch_model');
+        if (modelSelect) {
+            modelSelect.innerHTML = ''; // Clear existing options
+            this.settings.modelsAvailable.forEach(model => {
+                const option = document.createElement('option');
+                option.value = model.model_name;
+                option.textContent = model.model_name; // Use model_name instead of name
+                option.selected = model.model_name === this.settings.currentModel;
+                modelSelect.appendChild(option);
+            });
+        }
+    }
+
+    //#######################################################//
+    // Get Current AT Server Config & Update ST (DS and LVR) //
+    //#######################################################//
+
+    updateCheckboxes() {
+        const deepspeedCheckbox = document.getElementById('deepspeed');
+        const lowVramCheckbox = document.getElementById('low_vram');
+        if (lowVramCheckbox) lowVramCheckbox.checked = this.settings.lowVramEnabled;
+        if (deepspeedCheckbox) {
+            deepspeedCheckbox.checked = this.settings.deepSpeedEnabled;
+            deepspeedCheckbox.disabled = !this.settings.deepspeed_available; // Disable checkbox if deepspeed is not available
+        }
+    }
+
+    //###############################################################//
+    // Get Current AT Server Config & Update ST (AT Narrator Voices) //
+    //###############################################################//
+
+    updateNarratorVoicesDropdown() {
+        const narratorVoiceSelect = document.getElementById('narrator_voice');
+        if (narratorVoiceSelect && this.voices) {
+            // Clear existing options
+            narratorVoiceSelect.innerHTML = '';
+            // Add new options
+            for (let voice of this.voices) {
+                const option = document.createElement('option');
+                option.value = voice.voice_id;
+                option.textContent = voice.name;
+                narratorVoiceSelect.appendChild(option);
+            }
+        }
+    }
+
+    //######################################################//
+    // Get Current AT Server Config & Update ST (Languages) //
+    //######################################################//
+
+    updateLanguageDropdown() {
+        const languageSelect = document.getElementById('language_options');
+        if (languageSelect) {
+            // Ensure default language is set
+            this.settings.language = this.settings.language;
+
+            languageSelect.innerHTML = '';
+            for (let language in this.languageLabels) {
+                const option = document.createElement('option');
+                option.value = this.languageLabels[language];
+                option.textContent = language;
+                if (this.languageLabels[language] === this.settings.language) {
+                    option.selected = true;
+                }
+                languageSelect.appendChild(option);
+            }
+        }
+    }
+
+    //########################################//
+    // Start AT TTS extenstion page listeners //
+    //########################################//
+
+    setupEventListeners() {
+
+        let debounceTimeout;
+        const debounceDelay = 500; // Milliseconds
+
+        // Define the event handler function
+        const onModelSelectChange = async (event) => {
+            console.log("Model select change event triggered"); // Debugging statement
+            const selectedModel = event.target.value;
+            console.log(`Selected model: ${selectedModel}`); // Debugging statement 
+            // Set status to Processing
+            updateStatus('Processing');
+            try {
+                const response = await fetch(`${this.settings.provider_endpoint}/api/reload?tts_method=${encodeURIComponent(selectedModel)}`, {
+                    method: 'POST'
+                });
+                if (!response.ok) {
+                    throw new Error(`HTTP Error: ${response.status}`);
+                }
+                const data = await response.json();
+                console.log("POST response data:", data); // Debugging statement 
+                // Set status to Ready if successful
+                updateStatus('Ready');
+            } catch (error) {
+                console.error("POST request error:", error); // Debugging statement
+                // Set status to Error in case of failure
+                updateStatus('Error');
+            }
+
+            // Handle response or error
+        };
+
+        const debouncedModelSelectChange = (event) => {
+            clearTimeout(debounceTimeout);
+            debounceTimeout = setTimeout(() => {
+                onModelSelectChange(event);
+            }, debounceDelay);
+        };
+
+        // Switch Model Listener
+        const modelSelect = document.getElementById('switch_model');
+        if (modelSelect) {
+            // Remove the event listener if it was previously added
+            modelSelect.removeEventListener('change', debouncedModelSelectChange);
+            // Add the debounced event listener
+            modelSelect.addEventListener('change', debouncedModelSelectChange);
+        }
+
+        // DeepSpeed Listener
+        const deepspeedCheckbox = document.getElementById('deepspeed');
+        if (deepspeedCheckbox) {
+            deepspeedCheckbox.addEventListener('change', async (event) => {
+                const deepSpeedValue = event.target.checked ? 'True' : 'False';
+                // Set status to Processing
+                updateStatus('Processing');
+                try {
+                    const response = await fetch(`${this.settings.provider_endpoint}/api/deepspeed?new_deepspeed_value=${deepSpeedValue}`, {
+                        method: 'POST'
+                    });
+                    if (!response.ok) {
+                        throw new Error(`HTTP Error: ${response.status}`);
+                    }
+                    const data = await response.json();
+                    console.log("POST response data:", data); // Debugging statement
+                    // Set status to Ready if successful
+                    updateStatus('Ready');
+                } catch (error) {
+                    console.error("POST request error:", error); // Debugging statement
+                    // Set status to Error in case of failure
+                    updateStatus('Error');
+                }
+            });
+        }
+
+        // Low VRAM Listener
+        const lowVramCheckbox = document.getElementById('low_vram');
+        if (lowVramCheckbox) {
+            lowVramCheckbox.addEventListener('change', async (event) => {
+                const lowVramValue = event.target.checked ? 'True' : 'False';
+                // Set status to Processing
+                updateStatus('Processing');
+                try {
+                    const response = await fetch(`${this.settings.provider_endpoint}/api/lowvramsetting?new_low_vram_value=${lowVramValue}`, {
+                        method: 'POST'
+                    });
+                    if (!response.ok) {
+                        throw new Error(`HTTP Error: ${response.status}`);
+                    }
+                    const data = await response.json();
+                    console.log("POST response data:", data); // Debugging statement
+                    // Set status to Ready if successful
+                    updateStatus('Ready');
+                } catch (error) {
+                    console.error("POST request error:", error); // Debugging statement
+                    // Set status to Error in case of failure
+                    updateStatus('Error');
+                }
+            });
+        }
+
+        // Narrator Voice Dropdown Listener
+        const narratorVoiceSelect = document.getElementById('narrator_voice');
+        if (narratorVoiceSelect) {
+            narratorVoiceSelect.addEventListener('change', (event) => {
+                this.settings.narrator_voice_gen = `${event.target.value}.wav`;
+                this.onSettingsChange(); // Save the settings after change
+            });
+        }
+
+        const textNotInsideSelect = document.getElementById('at_narrator_text_not_inside');
+        if (textNotInsideSelect) {
+            textNotInsideSelect.addEventListener('change', (event) => {
+                this.settings.text_not_inside = event.target.value;
+                this.onSettingsChange(); // Save the settings after change
+            });
+        }
+
+        // AT Narrator Dropdown Listener
+        const atNarratorSelect = document.getElementById('at_narrator_enabled');
+        const ttsPassAsterisksCheckbox = document.getElementById('tts_pass_asterisks'); // Access the checkbox from index.js
+        const ttsNarrateQuotedCheckbox = document.getElementById('tts_narrate_quoted'); // Access the checkbox from index.js
+        const ttsNarrateDialoguesCheckbox = document.getElementById('tts_narrate_dialogues'); // Access the checkbox from index.js
+
+        if (atNarratorSelect && textNotInsideSelect && narratorVoiceSelect) {
+            atNarratorSelect.addEventListener('change', (event) => {
+                const isNarratorEnabled = event.target.value === 'true';
+                this.settings.narrator_enabled = isNarratorEnabled; // Update the setting here
+                textNotInsideSelect.disabled = !isNarratorEnabled;
+                narratorVoiceSelect.disabled = !isNarratorEnabled;
+
+                // Sync the state with the checkbox in index.js
+                if (isNarratorEnabled) {
+                    ttsPassAsterisksCheckbox.checked = false;
+                    $('#tts_pass_asterisks').click(); // Simulate a click event
+                    $('#tts_pass_asterisks').trigger('change');
+                }
+                if (!isNarratorEnabled) {
+                    ttsPassAsterisksCheckbox.checked = true;
+                    $('#tts_pass_asterisks').click(); // Simulate a click event
+                    $('#tts_pass_asterisks').trigger('change');
+                }
+                // Uncheck and set tts_narrate_quoted to false if narrator is enabled
+                if (isNarratorEnabled) {
+                    ttsNarrateQuotedCheckbox.checked = true;
+                    ttsNarrateDialoguesCheckbox.checked = true;
+                    // Trigger click events instead of change events
+                    $('#tts_narrate_quoted').click();
+                    $('#tts_narrate_quoted').trigger('change');
+                    $('#tts_narrate_dialogues').click();
+                    $('#tts_narrate_dialogues').trigger('change');
+                }
+                this.onSettingsChange(); // Save the settings after change
+            });
+        }
+
+
+        // Event Listener for AT Generation Method Dropdown
+        const atGenerationMethodSelect = document.getElementById('at_generation_method');
+        const atNarratorEnabledSelect = document.getElementById('at_narrator_enabled');
+        if (atGenerationMethodSelect) {
+            atGenerationMethodSelect.addEventListener('change', (event) => {
+                const selectedMethod = event.target.value;
+
+                if (selectedMethod === 'streaming_enabled') {
+                    // Disable and unselect AT Narrator
+                    atNarratorEnabledSelect.disabled = true;
+                    atNarratorEnabledSelect.value = 'false';
+                    textNotInsideSelect.disabled = true;
+                    narratorVoiceSelect.disabled = true;
+                } else if (selectedMethod === 'standard_generation') {
+                    // Enable AT Narrator
+                    atNarratorEnabledSelect.disabled = false;
+                }
+                this.settings.at_generation_method = selectedMethod; // Update the setting here
+                this.onSettingsChange(); // Save the settings after change
+            });
+        }
+
+        // Listener for Language Dropdown
+        const languageSelect = document.getElementById('language_options');
+        if (languageSelect) {
+            languageSelect.addEventListener('change', (event) => {
+                this.settings.language = event.target.value;
+                this.onSettingsChange(); // Save the settings after change
+            });
+        }
+
+        // Listener for AllTalk Endpoint Input
+        const atServerInput = document.getElementById('at_server');
+        if (atServerInput) {
+            atServerInput.addEventListener('input', (event) => {
+                this.settings.provider_endpoint = event.target.value;
+                this.onSettingsChange(); // Save the settings after change
+            });
+        }
+
+    }
+
+    //#############################//
+    // Store ST interface settings //
+    //#############################//
+
+    onSettingsChange() {
+        // Update settings based on the UI elements
+        //this.settings.provider_endpoint = $('#at_server').val();
+        this.settings.language = $('#language_options').val();
+        //this.settings.voiceMap = $('#voicemap').val();
+        this.settings.at_generation_method = $('#at_generation_method').val();
+        this.settings.narrator_enabled = $('#at_narrator_enabled').val();
+        this.settings.at_narrator_text_not_inside = $('#at_narrator_text_not_inside').val();
+        this.settings.narrator_voice_gen = $('#narrator_voice').val();
+        // Save the updated settings
+        saveTtsProviderSettings();
+    }
+
+    //#########################//
+    // ST Handle Reload button //
+    //#########################//
+
+    async onRefreshClick() {
+        await this.checkReady(); // Check if the TTS provider is ready
+        await this.loadSettings(this.settings); // Reload the settings
+        // Additional actions as needed
+    }
+
+    //##################//
+    // Preview AT Voice //
+    //##################//
+
+    async previewTtsVoice(voiceName) {
+        try {
+            // Prepare data for POST request
+            const postData = new URLSearchParams();
+            postData.append("voice", `${voiceName}.wav`);
+            // Making the POST request
+            const response = await fetch(`${this.settings.provider_endpoint}/api/previewvoice/`, {
+                method: "POST",
+                headers: {
+                    'Content-Type': 'application/x-www-form-urlencoded'
+                },
+                body: postData,
+            });
+            if (!response.ok) {
+                const errorText = await response.text();
+                console.error(`[previewTtsVoice] Error Response Text:`, errorText);
+                throw new Error(`HTTP ${response.status}: ${errorText}`);
+            }
+            // Assuming the server returns a URL to the .wav file
+            const data = await response.json();
+            if (data.output_file_url) {
+                // Use an audio element to play the .wav file
+                const audioElement = new Audio(data.output_file_url);
+                audioElement.play().catch(e => console.error("Error playing audio:", e));
+            } else {
+                console.warn("[previewTtsVoice] No output file URL received in the response");
+                throw new Error("No output file URL received in the response");
+            }
+
+        } catch (error) {
+            console.error("[previewTtsVoice] Exception caught during preview generation:", error);
+            throw error;
+        }
+    }
+
+    //#####################//
+    //  Populate ST voices //
+    //#####################//
+
+    async getVoice(voiceName, generatePreview = false) {
+        // Ensure this.voices is populated
+        if (this.voices.length === 0) {
+            // Fetch voice objects logic
+        }
+        // Find the object where the name matches voiceName
+        const match = this.voices.find(voice => voice.name === voiceName);
+        if (!match) {
+            // Error handling
+        }
+        // Generate preview URL only if requested
+        if (!match.preview_url && generatePreview) {
+            // Generate preview logic
+        }
+        return match; // Return the found voice object
+    }
+
+    //##########################################//
+    //  Generate TTS Streaming or call Standard //
+    //##########################################//
+
+    async generateTts(inputText, voiceId) {
+        try {
+            if (this.settings.at_generation_method === 'streaming_enabled') {
+                // Construct the streaming URL
+                const streamingUrl = `${this.settings.provider_endpoint}/api/tts-generate-streaming?text=${encodeURIComponent(inputText)}&voice=${encodeURIComponent(voiceId)}.wav&language=${encodeURIComponent(this.settings.language)}&output_file=stream_output.wav`;
+                console.log("Streaming URL:", streamingUrl);
+        
+                // Return the streaming URL directly
+                return streamingUrl; 
+            } else {
+                // For standard method
+                const outputUrl = await this.fetchTtsGeneration(inputText, voiceId);
+                const audioResponse = await fetch(outputUrl);
+                if (!audioResponse.ok) {
+                    throw new Error(`HTTP ${audioResponse.status}: Failed to fetch audio data`);
+                }
+                return audioResponse; // Return the fetch response directly
+            }
+        } catch (error) {
+            console.error("Error in generateTts:", error);
+            throw error;
+        }
+    }
+
+
+    //####################//
+    //  Generate Standard //
+    //####################//
+
+    async fetchTtsGeneration(inputText, voiceId) {
+        // Prepare the request payload
+        const requestBody = new URLSearchParams({
+            'text_input': inputText,
+            'text_filtering': "standard",
+            'character_voice_gen': voiceId + ".wav",
+            'narrator_enabled': this.settings.narrator_enabled,
+            'narrator_voice_gen': this.settings.narrator_voice_gen + ".wav",
+            'text_not_inside': this.settings.at_narrator_text_not_inside,
+            'language': this.settings.language,
+            'output_file_name': "st_output",
+            'output_file_timestamp': "true",
+            'autoplay': "false",
+            'autoplay_volume': "0.8"
+        }).toString();
+
+        try {
+            const response = await doExtrasFetch(
+                `${this.settings.provider_endpoint}/api/tts-generate`,
+                {
+                    method: 'POST',
+                    headers: {
+                        'Content-Type': 'application/x-www-form-urlencoded',
+                        'Cache-Control': 'no-cache',
+                    },
+                    body: requestBody
+                }
+            );
+
+            if (!response.ok) {
+                const errorText = await response.text();
+                console.error(`[fetchTtsGeneration] Error Response Text:`, errorText);
+                // toastr.error(response.statusText, 'TTS Generation Failed');
+                throw new Error(`HTTP ${response.status}: ${errorText}`);
+            }
+            const data = await response.json();
+            const outputUrl = data.output_file_url;
+            return outputUrl; // Return only the output_file_url
+        } catch (error) {
+            console.error("[fetchTtsGeneration] Exception caught:", error);
+            throw error; // Rethrow the error for further handling
+        }
+    }
+}
+
+//#########################//
+//  Update Status Messages //
+//#########################//
+
+function updateStatus(message) {
+    const statusElement = document.getElementById('status_info');
+    if (statusElement) {
+        statusElement.textContent = message;
+        switch (message) {
+            case 'Offline':
+                statusElement.style.color = 'red';
+                break;
+            case 'Ready':
+                statusElement.style.color = 'lightgreen';
+                break;
+            case 'Processing':
+                statusElement.style.color = 'blue';
+                break;
+            case 'Error':
+                statusElement.style.color = 'red';
+                break;
+        }
+    }
+}

templates/STfiles/style.css

@@ -0,0 +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; 
+}

templates/tts_chunk_player/crunker.d.ts

@@ -0,0 +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;
+}

templates/tts_chunk_player/crunker.esm.js

@@ -0,0 +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
+//# sourceMappingURL=crunker.esm.js.map

templates/tts_chunk_player/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,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

templates/tts_chunk_player/howler.min.js

@@ -0,0 +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 */
+!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

templates/word_addin/1995fcd6d39cade7d871.js

@@ -0,0 +1,2 @@
+/*! 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

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

@@ -0,0 +1 @@
+/*! regenerator-runtime -- Copyright (c) 2014-present, Facebook, Inc. -- license (MIT): https://github.com/facebook/regenerator/blob/main/LICENSE */

templates/word_addin/1fda685b81e1123773f6.css

@@ -0,0 +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;
+}

templates/word_addin/commands.html

@@ -0,0 +1 @@
+<!doctype html><html><head><meta charset="UTF-8"/><meta http-equiv="X-UA-Compatible" content="IE=Edge"/><script src="https://appsforoffice.microsoft.com/lib/1.1/hosted/office.js"></script><script defer="defer" src="polyfill.js"></script><script defer="defer" src="commands.js"></script></head><body></body></html>

templates/word_addin/commands.js

@@ -0,0 +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()}}();
+//# sourceMappingURL=commands.js.map

templates/word_addin/commands.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"commands.js","mappings":"YACA,IAAIA,EAAsB,CAAC,ECD3BA,EAAoBC,EAAI,WACvB,GAA0B,iBAAfC,WAAyB,OAAOA,WAC3C,IACC,OAAOC,MAAQ,IAAIC,SAAS,cAAb,EAChB,CAAE,MAAOC,GACR,GAAsB,iBAAXC,OAAqB,OAAOA,MACxC,CACA,CAPuB,GCOxBC,OAAOC,SAAQ,WACb,KAuBuB,oBAATC,KACVA,KACkB,oBAAXH,OACPA,YACkB,IAAXI,EAAAA,EACPA,EAAAA,OACAC,GAMJC,OA5BF,SAAgBC,GACd,IAAMC,EAAU,CACdC,KAAMR,OAAOS,aAAaC,4BAA4BC,qBACtDJ,QAAS,oBACTK,KAAM,aACNC,YAAY,GAIdb,OAAOc,QAAQC,QAAQC,KAAKC,qBAAqBC,aAAa,SAAUX,GAGxED,EAAMa,WACR,C","sources":["webpack://office-addin-taskpane-js/webpack/bootstrap","webpack://office-addin-taskpane-js/webpack/runtime/global","webpack://office-addin-taskpane-js/./src/commands/commands.js"],"sourcesContent":["// The require scope\nvar __webpack_require__ = {};\n\n","__webpack_require__.g = (function() {\n\tif (typeof globalThis === 'object') return globalThis;\n\ttry {\n\t\treturn this || new Function('return this')();\n\t} catch (e) {\n\t\tif (typeof window === 'object') return window;\n\t}\n})();","/*\n * Copyright (c) Microsoft Corporation. All rights reserved. Licensed under the MIT license.\n * See LICENSE in the project root for license information.\n */\n\n/* global global, Office, self, window */\n\nOffice.onReady(() => {\n  // If needed, Office.js is ready to be called\n});\n\n/**\n * Shows a notification when the add-in command is executed.\n * @param event {Office.AddinCommands.Event}\n */\nfunction action(event) {\n  const message = {\n    type: Office.MailboxEnums.ItemNotificationMessageType.InformationalMessage,\n    message: \"Performed action.\",\n    icon: \"Icon.80x80\",\n    persistent: true,\n  };\n\n  // Show a notification message\n  Office.context.mailbox.item.notificationMessages.replaceAsync(\"action\", message);\n\n  // Be sure to indicate when the add-in command function is complete\n  event.completed();\n}\n\nfunction getGlobal() {\n  return typeof self !== \"undefined\"\n    ? self\n    : typeof window !== \"undefined\"\n    ? window\n    : typeof global !== \"undefined\"\n    ? global\n    : undefined;\n}\n\nconst g = getGlobal();\n\n// The add-in command functions need to be available in global scope\ng.action = action;\n"],"names":["__webpack_require__","g","globalThis","this","Function","e","window","Office","onReady","self","global","undefined","action","event","message","type","MailboxEnums","ItemNotificationMessageType","InformationalMessage","icon","persistent","context","mailbox","item","notificationMessages","replaceAsync","completed"],"sourceRoot":""}

templates/word_addin/manifest.xml

@@ -0,0 +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>

templates/word_addin/polyfill.js

@@ -0,0 +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
+//# sourceMappingURL=polyfill.js.map

templates/word_addin/polyfill.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"polyfill.js","mappings":"qCAOA,IAAIA,EAAW,SAAUC,GACvB,aAEA,IAGIC,EAHAC,EAAKC,OAAOC,UACZC,EAASH,EAAGI,eACZC,EAAiBJ,OAAOI,gBAAkB,SAAUC,EAAKC,EAAKC,GAAQF,EAAIC,GAAOC,EAAKC,KAAO,EAE7FC,EAA4B,mBAAXC,OAAwBA,OAAS,CAAC,EACnDC,EAAiBF,EAAQG,UAAY,aACrCC,EAAsBJ,EAAQK,eAAiB,kBAC/CC,EAAoBN,EAAQO,aAAe,gBAE/C,SAASC,EAAOZ,EAAKC,EAAKE,GAOxB,OANAR,OAAOI,eAAeC,EAAKC,EAAK,CAC9BE,MAAOA,EACPU,YAAY,EACZC,cAAc,EACdC,UAAU,IAELf,EAAIC,EACb,CACA,IAEEW,EAAO,CAAC,EAAG,GACb,CAAE,MAAOI,GACPJ,EAAS,SAASZ,EAAKC,EAAKE,GAC1B,OAAOH,EAAIC,GAAOE,CACpB,CACF,CAEA,SAASc,EAAKC,EAASC,EAASC,EAAMC,GAEpC,IAAIC,EAAiBH,GAAWA,EAAQvB,qBAAqB2B,EAAYJ,EAAUI,EAC/EC,EAAY7B,OAAO8B,OAAOH,EAAe1B,WACzC8B,EAAU,IAAIC,EAAQN,GAAe,IAMzC,OAFAtB,EAAeyB,EAAW,UAAW,CAAErB,MAAOyB,EAAiBV,EAASE,EAAMM,KAEvEF,CACT,CAaA,SAASK,EAASC,EAAI9B,EAAK+B,GACzB,IACE,MAAO,CAAEC,KAAM,SAAUD,IAAKD,EAAGG,KAAKjC,EAAK+B,GAC7C,CAAE,MAAOf,GACP,MAAO,CAAEgB,KAAM,QAASD,IAAKf,EAC/B,CACF,CAlBAxB,EAAQyB,KAAOA,EAoBf,IAAIiB,EAAyB,iBACzBC,EAAyB,iBACzBC,EAAoB,YACpBC,EAAoB,YAIpBC,EAAmB,CAAC,EAMxB,SAASf,IAAa,CACtB,SAASgB,IAAqB,CAC9B,SAASC,IAA8B,CAIvC,IAAIC,EAAoB,CAAC,EACzB7B,EAAO6B,EAAmBnC,GAAgB,WACxC,OAAOoC,IACT,IAEA,IAAIC,EAAWhD,OAAOiD,eAClBC,EAA0BF,GAAYA,EAASA,EAASG,EAAO,MAC/DD,GACAA,IAA4BnD,GAC5BG,EAAOoC,KAAKY,EAAyBvC,KAGvCmC,EAAoBI,GAGtB,IAAIE,EAAKP,EAA2B5C,UAClC2B,EAAU3B,UAAYD,OAAO8B,OAAOgB,GAgBtC,SAASO,EAAsBpD,GAC7B,CAAC,OAAQ,QAAS,UAAUqD,SAAQ,SAASC,GAC3CtC,EAAOhB,EAAWsD,GAAQ,SAASnB,GACjC,OAAOW,KAAKS,QAAQD,EAAQnB,EAC9B,GACF,GACF,CA+BA,SAASqB,EAAc5B,EAAW6B,GAChC,SAASC,EAAOJ,EAAQnB,EAAKwB,EAASC,GACpC,IAAIC,EAAS5B,EAASL,EAAU0B,GAAS1B,EAAWO,GACpD,GAAoB,UAAhB0B,EAAOzB,KAEJ,CACL,IAAI0B,EAASD,EAAO1B,IAChB5B,EAAQuD,EAAOvD,MACnB,OAAIA,GACiB,iBAAVA,GACPN,EAAOoC,KAAK9B,EAAO,WACdkD,EAAYE,QAAQpD,EAAMwD,SAASC,MAAK,SAASzD,GACtDmD,EAAO,OAAQnD,EAAOoD,EAASC,EACjC,IAAG,SAASxC,GACVsC,EAAO,QAAStC,EAAKuC,EAASC,EAChC,IAGKH,EAAYE,QAAQpD,GAAOyD,MAAK,SAASC,GAI9CH,EAAOvD,MAAQ0D,EACfN,EAAQG,EACV,IAAG,SAASI,GAGV,OAAOR,EAAO,QAASQ,EAAOP,EAASC,EACzC,GACF,CAzBEA,EAAOC,EAAO1B,IA0BlB,CAEA,IAAIgC,EAgCJhE,EAAe2C,KAAM,UAAW,CAAEvC,MA9BlC,SAAiB+C,EAAQnB,GACvB,SAASiC,IACP,OAAO,IAAIX,GAAY,SAASE,EAASC,GACvCF,EAAOJ,EAAQnB,EAAKwB,EAASC,EAC/B,GACF,CAEA,OAAOO,EAaLA,EAAkBA,EAAgBH,KAChCI,EAGAA,GACEA,GACR,GAKF,CA0BA,SAASpC,EAAiBV,EAASE,EAAMM,GACvC,IAAIuC,EAAQ/B,EAEZ,OAAO,SAAgBgB,EAAQnB,GAC7B,GAAIkC,IAAU7B,EACZ,MAAM,IAAI8B,MAAM,gCAGlB,GAAID,IAAU5B,EAAmB,CAC/B,GAAe,UAAXa,EACF,MAAMnB,EAKR,OAAOoC,GACT,CAKA,IAHAzC,EAAQwB,OAASA,EACjBxB,EAAQK,IAAMA,IAED,CACX,IAAIqC,EAAW1C,EAAQ0C,SACvB,GAAIA,EAAU,CACZ,IAAIC,EAAiBC,EAAoBF,EAAU1C,GACnD,GAAI2C,EAAgB,CAClB,GAAIA,IAAmB/B,EAAkB,SACzC,OAAO+B,CACT,CACF,CAEA,GAAuB,SAAnB3C,EAAQwB,OAGVxB,EAAQ6C,KAAO7C,EAAQ8C,MAAQ9C,EAAQK,SAElC,GAAuB,UAAnBL,EAAQwB,OAAoB,CACrC,GAAIe,IAAU/B,EAEZ,MADA+B,EAAQ5B,EACFX,EAAQK,IAGhBL,EAAQ+C,kBAAkB/C,EAAQK,IAEpC,KAA8B,WAAnBL,EAAQwB,QACjBxB,EAAQgD,OAAO,SAAUhD,EAAQK,KAGnCkC,EAAQ7B,EAER,IAAIqB,EAAS5B,EAASX,EAASE,EAAMM,GACrC,GAAoB,WAAhB+B,EAAOzB,KAAmB,CAO5B,GAJAiC,EAAQvC,EAAQiD,KACZtC,EACAF,EAEAsB,EAAO1B,MAAQO,EACjB,SAGF,MAAO,CACLnC,MAAOsD,EAAO1B,IACd4C,KAAMjD,EAAQiD,KAGlB,CAA2B,UAAhBlB,EAAOzB,OAChBiC,EAAQ5B,EAGRX,EAAQwB,OAAS,QACjBxB,EAAQK,IAAM0B,EAAO1B,IAEzB,CACF,CACF,CAMA,SAASuC,EAAoBF,EAAU1C,GACrC,IAAIkD,EAAalD,EAAQwB,OACrBA,EAASkB,EAAS7D,SAASqE,GAC/B,GAAI1B,IAAWzD,EAOb,OAHAiC,EAAQ0C,SAAW,KAGA,UAAfQ,GAA0BR,EAAS7D,SAAiB,SAGtDmB,EAAQwB,OAAS,SACjBxB,EAAQK,IAAMtC,EACd6E,EAAoBF,EAAU1C,GAEP,UAAnBA,EAAQwB,SAMK,WAAf0B,IACFlD,EAAQwB,OAAS,QACjBxB,EAAQK,IAAM,IAAI8C,UAChB,oCAAsCD,EAAa,aAN5CtC,EAYb,IAAImB,EAAS5B,EAASqB,EAAQkB,EAAS7D,SAAUmB,EAAQK,KAEzD,GAAoB,UAAhB0B,EAAOzB,KAIT,OAHAN,EAAQwB,OAAS,QACjBxB,EAAQK,IAAM0B,EAAO1B,IACrBL,EAAQ0C,SAAW,KACZ9B,EAGT,IAAIwC,EAAOrB,EAAO1B,IAElB,OAAM+C,EAOFA,EAAKH,MAGPjD,EAAQ0C,EAASW,YAAcD,EAAK3E,MAGpCuB,EAAQsD,KAAOZ,EAASa,QAQD,WAAnBvD,EAAQwB,SACVxB,EAAQwB,OAAS,OACjBxB,EAAQK,IAAMtC,GAUlBiC,EAAQ0C,SAAW,KACZ9B,GANEwC,GA3BPpD,EAAQwB,OAAS,QACjBxB,EAAQK,IAAM,IAAI8C,UAAU,oCAC5BnD,EAAQ0C,SAAW,KACZ9B,EA+BX,CAqBA,SAAS4C,EAAaC,GACpB,IAAIC,EAAQ,CAAEC,OAAQF,EAAK,IAEvB,KAAKA,IACPC,EAAME,SAAWH,EAAK,IAGpB,KAAKA,IACPC,EAAMG,WAAaJ,EAAK,GACxBC,EAAMI,SAAWL,EAAK,IAGxBzC,KAAK+C,WAAWC,KAAKN,EACvB,CAEA,SAASO,EAAcP,GACrB,IAAI3B,EAAS2B,EAAMQ,YAAc,CAAC,EAClCnC,EAAOzB,KAAO,gBACPyB,EAAO1B,IACdqD,EAAMQ,WAAanC,CACrB,CAEA,SAAS9B,EAAQN,GAIfqB,KAAK+C,WAAa,CAAC,CAAEJ,OAAQ,SAC7BhE,EAAY4B,QAAQiC,EAAcxC,MAClCA,KAAKmD,OAAM,EACb,CA8BA,SAAS/C,EAAOgD,GACd,GAAIA,EAAU,CACZ,IAAIC,EAAiBD,EAASxF,GAC9B,GAAIyF,EACF,OAAOA,EAAe9D,KAAK6D,GAG7B,GAA6B,mBAAlBA,EAASd,KAClB,OAAOc,EAGT,IAAKE,MAAMF,EAASG,QAAS,CAC3B,IAAIC,GAAK,EAAGlB,EAAO,SAASA,IAC1B,OAASkB,EAAIJ,EAASG,QACpB,GAAIpG,EAAOoC,KAAK6D,EAAUI,GAGxB,OAFAlB,EAAK7E,MAAQ2F,EAASI,GACtBlB,EAAKL,MAAO,EACLK,EAOX,OAHAA,EAAK7E,MAAQV,EACbuF,EAAKL,MAAO,EAELK,CACT,EAEA,OAAOA,EAAKA,KAAOA,CACrB,CACF,CAGA,MAAO,CAAEA,KAAMb,EACjB,CAGA,SAASA,IACP,MAAO,CAAEhE,MAAOV,EAAWkF,MAAM,EACnC,CA8MA,OAnnBApC,EAAkB3C,UAAY4C,EAC9BzC,EAAegD,EAAI,cAAe,CAAE5C,MAAOqC,EAA4B1B,cAAc,IACrFf,EACEyC,EACA,cACA,CAAErC,MAAOoC,EAAmBzB,cAAc,IAE5CyB,EAAkB4D,YAAcvF,EAC9B4B,EACA9B,EACA,qBAaFlB,EAAQ4G,oBAAsB,SLine truncated

templates/word_addin/taskpane.html

@@ -0,0 +1,106 @@
+<!doctype html>
+<html>
+
+<head>
+    <meta charset="UTF-8" />
+    <meta http-equiv="X-UA-Compatible" content="IE=Edge" />
+    <meta name="viewport" content="width=device-width,initial-scale=1">
+    <title>AllTalk TTS Add-in</title>
+    <script src="https://appsforoffice.microsoft.com/lib/1.1/hosted/office.js"></script>
+    <link rel="stylesheet"
+        href="https://static2.sharepointonline.com/files/fabric/office-ui-fabric-core/11.0.0/css/fabric.min.css" />
+    <link href="1fda685b81e1123773f6.css" rel="stylesheet" />
+    <style>
+        label {
+            font-weight: 700;
+            display: block;
+            margin-top: 10px
+        }
+
+        select {
+            width: 100%;
+            padding: 5px
+        }
+
+        .nice-button {
+            background-color: #0078d4;
+            color: #fff;
+            padding: 10px 20px;
+            border: none;
+            border-radius: 5px;
+            cursor: pointer;
+            font-size: 16px;
+            transition: background-color .3s ease
+        }
+
+        .nice-button:hover {
+            background-color: #005a9e
+        }
+
+        #audioSource {
+            width: 300px;
+            height: 50px
+        }
+
+        .input-container {
+            display: flex;
+            flex-direction: column;
+            margin-right: 10px
+        }
+
+        .input-group {
+            display: flex;
+            justify-content: start;
+            align-items: flex-end
+        }
+
+        .input-group>.input-container {
+            flex: 1
+        }
+
+        input {
+            width: 100%
+        }
+    </style>
+    <script defer="defer" src="polyfill.js"></script>
+    <script defer="defer" src="taskpane.js"></script>
+</head>
+
+<body class="ms-font-m ms-welcome ms-Fabric">
+    <header class="ms-welcome__header ms-bgColor-neutralLighter"><img width="90" height="90"
+            src="http://127.0.0.1:7851/api/word_addin/assets/logo-filled.png" alt="AllTalk TTS" title="AllTalk TTS" />
+        <h1 class="ms-font-su">AllTalk TTS</h1>
+    </header>
+    <main class="ms-welcome__main"><textarea id="text" rows="4" placeholder="Enter text here"
+            style="display:none"></textarea> <label for="voice">Voice:</label> <select id="voice" name="voice"
+            required></select> <label for="language">Language:</label> <select id="language" name="language"
+            value="English" required>
+            <option value="en" selected="selected">English</option>
+            <option value="ar">Arabic</option>
+            <option value="zh-cn">Chinese</option>
+            <option value="cs">Czech</option>
+            <option value="nl">Dutch</option>
+            <option value="fr">French</option>
+            <option value="de">German</option>
+            <option value="hu">Hungarian</option>
+            <option value="it">Italian</option>
+            <option value="ja">Japanese</option>
+            <option value="ko">Korean</option>
+            <option value="pl">Polish</option>
+            <option value="pt">Portuguese</option>
+            <option value="ru">Russian</option>
+            <option value="es">Spanish</option>
+            <option value="tr">Turkish</option>
+        </select><br><audio id="audioSource" controls autoplay></audio><br><button id="sendTextButton"
+            class="nice-button">Send Text to TTS</button><br><br><br><br>
+        <div class="input-group">
+            <div class="input-container"><label for="serverIP">Server IP:</label> <input id="serverIP" name="serverIP"
+                    value="127.0.0.1" required></div>
+            <div class="input-container"><label for="portNumber">Port Number:</label> <input type="number"
+                    id="portNumber" name="portNumber" value="7851" required></div>
+        </div>
+    </main>
+    <script src="1995fcd6d39cade7d871.js"></script>
+</body>
+
+</html>

templates/word_addin/taskpane.js

@@ -0,0 +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
+//# sourceMappingURL=taskpane.js.map

templates/word_addin/taskpane.js.LICENSE.txt

@@ -0,0 +1 @@
+/*! regenerator-runtime -- Copyright (c) 2014-present, Facebook, Inc. -- license (MIT): https://github.com/facebook/regenerator/blob/main/LICENSE */

templates/word_addin/taskpane.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"taskpane.js","mappings":";kDAEAA,EAAOC,QAAU,SAAUC,EAAKC,GAM9B,OALKA,IAEHA,EAAU,CAAC,GAGRD,GAKLA,EAAME,OAAOF,EAAIG,WAAaH,EAAII,QAAUJ,GAExCC,EAAQI,OAEVL,GAAOC,EAAQI,MAGbJ,EAAQK,iBAAmB,oBAAoBC,KAAKP,GAC/C,IAAKQ,OAAOR,EAAK,KAGnBA,GAfEA,CAgBX,wOCxBIS,EAA2B,CAAC,EAGhC,SAASC,EAAoBC,GAE5B,IAAIC,EAAeH,EAAyBE,GAC5C,QAAqBE,IAAjBD,EACH,OAAOA,EAAab,QAGrB,IAAID,EAASW,EAAyBE,GAAY,CAGjDZ,QAAS,CAAC,GAOX,OAHAe,EAAoBH,GAAUb,EAAQA,EAAOC,QAASW,GAG/CZ,EAAOC,OACf,CAGAW,EAAoBK,EAAID,ECxBxBJ,EAAoBM,EAAI,SAASlB,GAChC,IAAImB,EAASnB,GAAUA,EAAOK,WAC7B,WAAa,OAAOL,EAAgB,OAAG,EACvC,WAAa,OAAOA,CAAQ,EAE7B,OADAY,EAAoBQ,EAAED,EAAQ,CAAEE,EAAGF,IAC5BA,CACR,ECNAP,EAAoBQ,EAAI,SAASnB,EAASqB,GACzC,IAAI,IAAIC,KAAOD,EACXV,EAAoBY,EAAEF,EAAYC,KAASX,EAAoBY,EAAEvB,EAASsB,IAC5EE,OAAOC,eAAezB,EAASsB,EAAK,CAAEI,YAAY,EAAMC,IAAKN,EAAWC,IAG3E,ECPAX,EAAoBiB,EAAI,WACvB,GAA0B,iBAAfC,WAAyB,OAAOA,WAC3C,IACC,OAAOC,MAAQ,IAAIC,SAAS,cAAb,EAChB,CAAE,MAAOC,GACR,GAAsB,iBAAXC,OAAqB,OAAOA,MACxC,CACA,CAPuB,GCAxBtB,EAAoBY,EAAI,SAASW,EAAKC,GAAQ,OAAOX,OAAOY,UAAUC,eAAeC,KAAKJ,EAAKC,EAAO,aCAtG,IAAII,EACA5B,EAAoBiB,EAAEY,gBAAeD,EAAY5B,EAAoBiB,EAAEa,SAAW,IACtF,IAAIC,EAAW/B,EAAoBiB,EAAEc,SACrC,IAAKH,GAAaG,IACbA,EAASC,gBACZJ,EAAYG,EAASC,cAAcC,MAC/BL,GAAW,CACf,IAAIM,EAAUH,EAASI,qBAAqB,UAC5C,GAAGD,EAAQE,OAEV,IADA,IAAIC,EAAIH,EAAQE,OAAS,EAClBC,GAAK,IAAMT,GAAWA,EAAYM,EAAQG,KAAKJ,GAExD,CAID,IAAKL,EAAW,MAAM,IAAIU,MAAM,yDAChCV,EAAYA,EAAUW,QAAQ,OAAQ,IAAIA,QAAQ,QAAS,IAAIA,QAAQ,YAAa,KACpFvC,EAAoBwC,EAAIZ,KClBxB5B,EAAoByC,EAAIV,SAASW,SAAWC,KAAKb,SAASc,gRCC1DC,EAAA,kBAAAxB,CAAA,MAAAyB,EAAAzB,EAAA,GAAA0B,EAAAlC,OAAAY,UAAAnB,EAAAyC,EAAArB,eAAAd,EAAAC,OAAAC,gBAAA,SAAAgC,EAAAzB,EAAA0B,GAAAD,EAAAzB,GAAA0B,EAAAC,KAAA,EAAAX,EAAA,mBAAAY,OAAAA,OAAA,GAAAxC,EAAA4B,EAAAa,UAAA,aAAAC,EAAAd,EAAAe,eAAA,kBAAAC,EAAAhB,EAAAiB,aAAA,yBAAAC,EAAAT,EAAAzB,EAAA0B,GAAA,OAAAlC,OAAAC,eAAAgC,EAAAzB,EAAA,CAAA2B,MAAAD,EAAAhC,YAAA,EAAAyC,cAAA,EAAAC,UAAA,IAAAX,EAAAzB,EAAA,KAAAkC,EAAA,aAAAT,GAAAS,EAAA,SAAAT,EAAAzB,EAAA0B,GAAA,OAAAD,EAAAzB,GAAA0B,CAAA,WAAAW,EAAAZ,EAAAzB,EAAA0B,EAAAzC,GAAA,IAAA+B,EAAAhB,GAAAA,EAAAI,qBAAAkC,EAAAtC,EAAAsC,EAAAlD,EAAAI,OAAA+C,OAAAvB,EAAAZ,WAAA0B,EAAA,IAAAU,EAAAvD,GAAA,WAAAM,EAAAH,EAAA,WAAAuC,MAAAc,EAAAhB,EAAAC,EAAAI,KAAA1C,CAAA,UAAAsD,EAAAjB,EAAAzB,EAAA0B,GAAA,WAAAiB,KAAA,SAAAC,IAAAnB,EAAAnB,KAAAN,EAAA0B,GAAA,OAAAD,GAAA,OAAAkB,KAAA,QAAAC,IAAAnB,EAAA,EAAAzB,EAAAqC,KAAAA,EAAA,IAAAQ,EAAA,iBAAAC,EAAA,iBAAAC,EAAA,YAAAC,EAAA,YAAAC,EAAA,YAAAX,IAAA,UAAAY,IAAA,UAAAC,IAAA,KAAAhC,EAAA,GAAAe,EAAAf,EAAA/B,GAAA,8BAAAD,EAAAK,OAAA4D,eAAAC,EAAAlE,GAAAA,EAAAA,EAAAmE,EAAA,MAAAD,GAAAA,IAAA3B,GAAAzC,EAAAqB,KAAA+C,EAAAjE,KAAA+B,EAAAkC,GAAA,IAAAzD,EAAAuD,EAAA/C,UAAAkC,EAAAlC,UAAAZ,OAAA+C,OAAApB,GAAA,SAAAoC,EAAA9B,GAAA,0BAAA+B,SAAA,SAAAxD,GAAAkC,EAAAT,EAAAzB,GAAA,SAAAyB,GAAA,YAAAgC,QAAAzD,EAAAyB,EAAA,gBAAAiC,EAAAjC,EAAAzB,GAAA,SAAA2D,EAAAjC,EAAAnC,EAAAyB,EAAA5B,GAAA,IAAA0C,EAAAY,EAAAjB,EAAAC,GAAAD,EAAAlC,GAAA,aAAAuC,EAAAa,KAAA,KAAAX,EAAAF,EAAAc,IAAAC,EAAAb,EAAAL,MAAA,OAAAkB,GAAA,UAAAe,EAAAf,IAAA5D,EAAAqB,KAAAuC,EAAA,WAAA7C,EAAA6D,QAAAhB,EAAAiB,SAAAC,MAAA,SAAAtC,GAAAkC,EAAA,OAAAlC,EAAAT,EAAA5B,EAAA,aAAAqC,GAAAkC,EAAA,QAAAlC,EAAAT,EAAA5B,EAAA,IAAAY,EAAA6D,QAAAhB,GAAAkB,MAAA,SAAAtC,GAAAO,EAAAL,MAAAF,EAAAT,EAAAgB,EAAA,aAAAP,GAAA,OAAAkC,EAAA,QAAAlC,EAAAT,EAAA5B,EAAA,IAAAA,EAAA0C,EAAAc,IAAA,KAAAlB,EAAAnC,EAAA,gBAAAoC,MAAA,SAAAF,EAAAxC,GAAA,SAAA+E,IAAA,WAAAhE,GAAA,SAAAA,EAAA0B,GAAAiC,EAAAlC,EAAAxC,EAAAe,EAAA0B,EAAA,WAAAA,EAAAA,EAAAA,EAAAqC,KAAAC,EAAAA,GAAAA,GAAA,aAAAvB,EAAAzC,EAAA0B,EAAAzC,GAAA,IAAAM,EAAAsD,EAAA,gBAAA7B,EAAA5B,GAAA,GAAAG,IAAAwD,EAAA,UAAA9B,MAAA,mCAAA1B,IAAAyD,EAAA,cAAAhC,EAAA,MAAA5B,EAAA,OAAAuC,MAAAF,EAAAwC,MAAA,OAAAhF,EAAAiF,OAAAlD,EAAA/B,EAAA2D,IAAAxD,IAAA,KAAA0C,EAAA7C,EAAAkF,SAAA,GAAArC,EAAA,KAAAE,EAAAoC,EAAAtC,EAAA7C,GAAA,GAAA+C,EAAA,IAAAA,IAAAiB,EAAA,gBAAAjB,CAAA,cAAA/C,EAAAiF,OAAAjF,EAAAoF,KAAApF,EAAAqF,MAAArF,EAAA2D,SAAA,aAAA3D,EAAAiF,OAAA,IAAA3E,IAAAsD,EAAA,MAAAtD,EAAAyD,EAAA/D,EAAA2D,IAAA3D,EAAAsF,kBAAAtF,EAAA2D,IAAA,gBAAA3D,EAAAiF,QAAAjF,EAAAuF,OAAA,SAAAvF,EAAA2D,KAAArD,EAAAwD,EAAA,IAAA5B,EAAAuB,EAAA1C,EAAA0B,EAAAzC,GAAA,cAAAkC,EAAAwB,KAAA,IAAApD,EAAAN,EAAAgF,KAAAjB,EAAAF,EAAA3B,EAAAyB,MAAAK,EAAA,gBAAAtB,MAAAR,EAAAyB,IAAAqB,KAAAhF,EAAAgF,KAAA,WAAA9C,EAAAwB,OAAApD,EAAAyD,EAAA/D,EAAAiF,OAAA,QAAAjF,EAAA2D,IAAAzB,EAAAyB,IAAA,YAAAwB,EAAApE,EAAA0B,GAAA,IAAAzC,EAAAyC,EAAAwC,OAAA3E,EAAAS,EAAA6B,SAAA5C,GAAA,GAAAM,IAAAkC,EAAA,OAAAC,EAAAyC,SAAA,eAAAlF,GAAAe,EAAA6B,SAAA4C,SAAA/C,EAAAwC,OAAA,SAAAxC,EAAAkB,IAAAnB,EAAA2C,EAAApE,EAAA0B,GAAA,UAAAA,EAAAwC,SAAA,WAAAjF,IAAAyC,EAAAwC,OAAA,QAAAxC,EAAAkB,IAAA,IAAA8B,UAAA,oCAAAzF,EAAA,aAAAgE,EAAA,IAAAjC,EAAA0B,EAAAnD,EAAAS,EAAA6B,SAAAH,EAAAkB,KAAA,aAAA5B,EAAA2B,KAAA,OAAAjB,EAAAwC,OAAA,QAAAxC,EAAAkB,IAAA5B,EAAA4B,IAAAlB,EAAAyC,SAAA,KAAAlB,EAAA,IAAA7D,EAAA4B,EAAA4B,IAAA,OAAAxD,EAAAA,EAAA6E,MAAAvC,EAAA1B,EAAA2E,YAAAvF,EAAAuC,MAAAD,EAAAkD,KAAA5E,EAAA6E,QAAA,WAAAnD,EAAAwC,SAAAxC,EAAAwC,OAAA,OAAAxC,EAAAkB,IAAAnB,GAAAC,EAAAyC,SAAA,KAAAlB,GAAA7D,GAAAsC,EAAAwC,OAAA,QAAAxC,EAAAkB,IAAA,IAAA8B,UAAA,oCAAAhD,EAAAyC,SAAA,KAAAlB,EAAA,UAAA6B,EAAArD,GAAA,IAAAzB,EAAA,CAAA+ELine truncated