### Run AllTalk Setup Script for Standalone Installation

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Open a terminal or command prompt, navigate into the cloned AllTalk directory, and execute the AllTalk setup script to install necessary components for a standalone setup.

```Batch
cd alltalk_tts
atsetup.bat
```

```Shell
cd alltalk_tts
./atsetup.sh
```

--------------------------------

### Perform Quick Setup for AllTalk TTS on Windows

Source: https://github.com/erew123/alltalk_tts/wiki/Install-‐-Standalone-Installation

Sequential commands to set up AllTalk TTS on Windows, including navigating to a preferred directory, cloning the repository, entering the project directory, and executing the setup batch script.

```batch
cd /d C:\path\to\your\preferred\directory
git clone -b alltalkbeta https://github.com/erew123/alltalk_tts
cd alltalk_tts
atsetup.bat
```

--------------------------------

### Start Text Generation Web UI and Load AllTalk Extension

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Return to the main Text Generation Web UI directory and start the application using the appropriate script for your OS. After starting, ensure to load the AllTalk extension from within the Text Generation Web UI's session tab.

```bash
cd ..
start_windows.bat
```

```bash
cd ..
./start_linux.sh
```

```bash
cd ..
start_macos.sh
```

```bash
cd ..
start_wsl.bat
```

--------------------------------

### Perform Quick Setup for AllTalk TTS on Linux

Source: https://github.com/erew123/alltalk_tts/wiki/Install-‐-Standalone-Installation

Sequential commands to set up AllTalk TTS on Linux, including navigating to a preferred directory, cloning the repository, entering the project directory, and executing the setup shell script.

```bash
cd /path/to/your/preferred/directory
git clone -b alltalkbeta https://github.com/erew123/alltalk_tts
cd alltalk_tts
./atsetup.sh
```

--------------------------------

### Run AllTalk Setup Script for Text-generation-webui

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Navigate into the AllTalk extensions directory and execute the AllTalk setup script to install necessary components.

```Batch
cd extensions
cd alltalk_tts
atsetup.bat
```

```Shell
cd extensions
cd alltalk_tts
./atsetup.sh
```

--------------------------------

### Starting and Updating text-generation-webui

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Commands to correctly start or update the text-generation-webui application, ensuring the proper Python environment is used. This includes initial startup scripts and update utilities for various operating systems.

```Batch
start_windows.bat
cmd_windows.bat
update_windows.bat
```

```Shell
./start_linux.sh
./cmd_linux.sh
update_linux.sh
```

```Shell
start_macos.sh
cmd_macos.sh
update_macos.sh
```

```Batch
start_wsl.bat
cmd_wsl.bat
update_wsl.bat
```

```Python
python server.py
```

--------------------------------

### Start Text-generation-webui Python Environment

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Activate the Python environment for Text-generation-webui by running the appropriate batch or shell script in the main directory.

```Batch
cmd_windows.bat
```

```Shell
./cmd_linux.sh
```

--------------------------------

### Start AllTalk from Custom Python Environment

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Command to launch the AllTalk application after it has been successfully installed and configured within a custom Python environment.

```Shell
python script.py
```

--------------------------------

### Activate Python Environment for Text-Generation-webui

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Start the Python virtual environment tailored for your Text-Generation-webui setup using the appropriate script for your operating system.

```Shell
cmd_windows.bat
```

```Shell
./cmd_linux.sh
```

```Shell
cmd_macos.sh
```

```Shell
cmd_wsl.bat
```

--------------------------------

### Example Output: Transformers Version Change Confirmation

Source: https://github.com/erew123/alltalk_tts/wiki/Error-Messages-List

Illustrative output from `pip install` showing the successful uninstallation of an older `transformers` version (e.g., 4.43.3) before installing the specified version, confirming the update.

```Shell
Installing collected packages: transformers
  Attempting uninstall: transformers
    Found existing installation: transformers 4.43.3
    Uninstalling transformers-4.43.3:
      Successfully uninstalled transformers-4.43.3
```

--------------------------------

### Start AllTalk TTS WebUI with DeepSpeed

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Launches the AllTalk TTS web user interface by executing the 'start_alltalk.sh' script, which is configured to enable DeepSpeed for enhanced performance.

```Bash
./start_alltalk.sh
```

--------------------------------

### Clone AllTalk Repository for Standalone Installation

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Navigate to your preferred installation directory and clone the AllTalk TTS repository using Git for a standalone setup. This method is recommended for automatic updates.

```Shell
cd C:\myfiles\
git clone https://github.com/erew123/alltalk_tts
```

--------------------------------

### Run AllTalk TTS Setup Script

Source: https://github.com/erew123/alltalk_tts/wiki/Install-‐-Text‐generation‐webui-Installation

Executes the AllTalk TTS setup script, which is responsible for installing all required dependencies and configuring the extension. Users should follow any on-screen instructions or prompts during this process.

```Batch
atsetup.bat
```

```Bash
./atsetup.sh
```

--------------------------------

### Starting Python Environment for Text-Generation-WebUI

Source: https://github.com/erew123/alltalk_tts/wiki/Error-Messages-List

Commands to activate the correct Python environment for the Text-generation-webui project on Windows and Linux, which is crucial for resolving dependency issues and ensuring proper execution.

```Shell
start_environment.bat
```

```Shell
./start_environment.sh
```

--------------------------------

### Install Python Requirements for Text-Generation-webui

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Install or update Python dependencies required for Text-Generation-webui using pip, specifying the requirements file for this setup.

```Python
pip install -r system\requirements\requirements_textgen.txt
```

```Python
pip install -r system/requirements/requirements_textgen.txt
```

--------------------------------

### Activate Python Environment for Standalone AllTalk TTS

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Start the Python virtual environment for the standalone AllTalk TTS application using the appropriate script for your operating system.

```Shell
start_environment.bat
```

```Shell
./start_environment.sh
```

--------------------------------

### Standard TTS Generation `curl` Examples

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Provides `curl` command examples for standard TTS generation, demonstrating how to synthesize speech for a character and with an enabled narrator. It shows parameter usage for text input, filtering, voice selection, language, output file naming, timestamping, and autoplay settings. Note the escaping of double quotes for text input.

```curl
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"
```

```curl
curl -X POST "http://127.0.0.1:7851/api/tts-generate" -d "text_input=*This is text spoken by the narrator* \"This is text spoken by the character\". This is text not inside quotes." -d "text_filtering=standard" -d "character_voice_gen=female_01.wav" -d "narrator_enabled=true" -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"
```

--------------------------------

### Install libaio-dev for DeepSpeed on Linux

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Commands to install the 'libaio-dev' library, a prerequisite for DeepSpeed, using package managers on Debian-based and RPM-based Linux systems.

```bash
sudo apt install libaio-dev
```

```bash
sudo yum install libaio-devel
```

--------------------------------

### Verify PortAudio and sounddevice in Python Environment

Source: https://github.com/erew123/alltalk_tts/wiki/Error-Messages-List

Steps to activate the AllTalk Python environment and then check for or install the `sounddevice` package, ensuring proper integration with PortAudio.

```bash
./start_environment.sh
pip show sounddevice
pip install sounddevice
```

--------------------------------

### Check TTS Service Readiness

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

This API endpoint allows users to verify if the Text-to-Speech service is operational and ready to accept requests. It's a simple GET request with no parameters.

```APIDOC
Endpoint: /api/ready
  Method: GET
  URL: http://127.0.0.1:7851/api/ready
  Response: string (e.g., "Ready")
```

```Bash
curl -X GET "http://127.0.0.1:7851/api/ready"
```

--------------------------------

### Install DeepSpeed Pre-compiled Wheel

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Command to install a DeepSpeed pre-compiled wheel file using pip. This method is used for manual installation when not using the `atsetup.bat` utility. Replace `{deep-speed-wheel-file-name-here}` with the actual file name of the downloaded wheel.

```bash
pip install {deep-speed-wheel-file-name-here}
```

--------------------------------

### Verify PortAudio Installation with pkg-config

Source: https://github.com/erew123/alltalk_tts/wiki/Error-Messages-List

Command to check PortAudio installation using `pkg-config` and its expected output, providing an alternative verification method.

```bash
pkg-config --libs portaudio-2.0
```

--------------------------------

### Verify Python and Pip Installation

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Command to check if Python is correctly installed and accessible in the terminal, which is a prerequisite for custom installations.

```Shell
python --version
```

--------------------------------

### Install or Reinstall PortAudio on Linux

Source: https://github.com/erew123/alltalk_tts/wiki/Error-Messages-List

Commands to update package lists, remove existing PortAudio installations, and install PortAudio and related development packages on Debian/Ubuntu systems to resolve installation issues.

```bash
sudo apt-get update
sudo apt-get remove --purge portaudio19-dev
sudo apt-get install portaudio19-dev python3-pyaudio
sudo apt-get install libasound2-dev
```

--------------------------------

### Example of Standard curl Command in Batch Script

Source: https://github.com/erew123/alltalk_tts/wiki/Error-Messages-List

This snippet shows a typical `curl` command used in a Windows batch script (`atsetup.bat`) for downloading files. It uses the `-LO` flags for remote file download and local output.

```batch
curl -LO https://github.com/erew123/file-blah-blah.....etc..
```

--------------------------------

### Install Faiss and FFmpeg

Source: https://github.com/erew123/alltalk_tts/wiki/Install-‐-Manual-Installation-Guide

Install Faiss-CPU for efficient similarity search and FFmpeg for multimedia processing, both essential components for the project.

```cmd
.\Scripts\conda install -y pytorch::faiss-cpu
.\Scripts\conda install -y conda-forge::ffmpeg=*=*gpl*
.\Scripts\conda install -y -c conda-forge "ffmpeg=*=h*_*" --no-deps
```

```bash
conda install -y pytorch::faiss-cpu
conda install -y -c conda-forge "ffmpeg=*=*gpl*"
conda install -y -c conda-forge "ffmpeg=*=h*_*" --no-deps
```

--------------------------------

### Clone AllTalk TTS Repository

Source: https://github.com/erew123/alltalk_tts/wiki/Install-‐-Manual-Installation-Guide

Clone the AllTalk TTS project repository from GitHub using Git. The 'alltalkbeta' branch is specified for the installation.

```cmd
git clone -b alltalkbeta https://github.com/erew123/alltalk_tts
```

```bash
git clone -b alltalkbeta https://github.com/erew123/alltalk_tts
```

--------------------------------

### Verify CUDA Toolkit Installation

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Runs the 'nvcc --version' command to confirm that the CUDA toolkit is correctly installed and accessible via the configured environment variables, displaying its version information.

```Bash
nvcc --version
```

--------------------------------

### Install Python Dependencies from requirements.txt

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

This command utilizes pip, Python's standard package installer, to read a list of required packages and their versions from a 'requirements.txt' file. It then installs these dependencies into the currently active Python environment, ensuring all necessary libraries are present for the application to function correctly.

```Shell
pip install -r requirements.txt
```

--------------------------------

### Install FFmpeg for Text Generation Web UI

Source: https://github.com/erew123/alltalk_tts/wiki/Error-Messages-List

Instructions to activate the custom Python environment and install FFmpeg using Conda for the Text Generation Web UI, covering both Windows and Linux environments.

```cmd
cmd_windows.bat
cd installer_files\conda\Scripts
conda install -y conda-forge::ffmpeg
```

```bash
./cmd_linux.sh
cd installer_files/conda/Scripts
conda install -y conda-forge::ffmpeg
```

--------------------------------

### Install DeepSpeed Python Package

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Installs the DeepSpeed library using pip, the Python package installer. This command downloads and sets up all required DeepSpeed components within the active Python environment.

```Bash
pip install deepspeed
```

--------------------------------

### Verify CUDA Toolkit Installation

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Command to verify the correct installation and path configuration of the CUDA Toolkit by checking its version. This helps confirm that the environment variables are set correctly.

```bash
nvcc --version
```

--------------------------------

### Navigate to Text-Generation-webui Root Directory

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Change the current directory to the root folder of your Text-Generation-webui installation.

```Shell
cd text-generation-webui
```

--------------------------------

### Install Core Python Requirements

Source: https://github.com/erew123/alltalk_tts/wiki/Install-‐-Manual-Installation-Guide

Navigate back to the main project directory and install the primary Python dependencies listed in 'requirements_standalone.txt' using pip.

```cmd
cd ..
cd ..
pip install -r system\requirements\requirements_standalone.txt
```

```bash
cd ..
pip install -r system/requirements/requirements_standalone.txt
```

--------------------------------

### Uninstall DeepSpeed

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Command to uninstall the DeepSpeed package using pip. This is useful for removing existing DeepSpeed installations, for example, before installing a different version or a pre-compiled wheel.

```bash
pip uninstall deepspeed
```

--------------------------------

### Install AllTalk Dependencies in Conda Environment

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Commands to install AllTalk's required Python packages using pip from the `requirements_standalone.txt` file, with separate commands provided for Windows and Linux/macOS due to differences in path separators.

```Shell
# For Windows
pip install -r system\requirements\requirements_standalone.txt
```

```Shell
# For Linux/Mac
pip install -r system/requirements/requirements_standalone.txt
```

--------------------------------

### Install DeepSpeed Wheel File

Source: https://github.com/erew123/alltalk_tts/wiki/Install-‐-LINUX-‐-Requirements-and-DeepSpeed

Installs a specific DeepSpeed wheel file using pip. Users must replace '[version]' with the correct DeepSpeed version string that matches their Python, PyTorch, and CUDA setup.

```bash
pip install deepspeed-0.14.2+[version]manylinux_2_24_x86_64.whl
```

--------------------------------

### Verify Nvidia CUDA 11.8 Installation

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Command to verify the installed version of Nvidia CUDA Development Toolkit 11.8. A successful output should confirm version 11.8.

```Shell
nvcc --version
```

--------------------------------

### Navigate to Preferred Directory

Source: https://github.com/erew123/alltalk_tts/wiki/Install-‐-Manual-Installation-Guide

Change the current working directory to a user-specified location where the AllTalk TTS project will be installed. This is the initial step for setting up the project environment.

```cmd
cd /d C:\path\to\your\preferred\directory
```

```bash
cd /path/to/your/preferred/directory
```

--------------------------------

### Navigate to AllTalk TTS Extension Directory

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Change the current directory to the 'alltalk_tts' extension folder within your Text-Generation-webui installation.

```Shell
cd extensions/alltalk_tts
```

--------------------------------

### Initial Setup Information Log

Source: https://github.com/erew123/alltalk_tts/wiki/XTTS-Model-Finetuning-Guide-(Advanced-Version)

Displays initial configuration details including the output directory, device usage (CPU/GPU), the specific Whisper model loaded, and the active precision mode (e.g., mixed precision). This helps confirm the environment setup.

```Log
[INFO] Initializing output directory: E:\finetune\testproject
[MODEL] Using device: cuda
[MODEL] Loading Whisper model: large-v3
[MODEL] Using mixed precision
```

--------------------------------

### Install AllTalk TTS Prerequisites on Mac

Source: https://github.com/erew123/alltalk_tts/wiki/Install-‐-Manual-Installation-Guide

Commands to install necessary packages for AllTalk TTS on macOS using Homebrew, including espeak, ffmpeg, gcc, git, and curl. It also includes the command to install Xcode Command Line Tools, which are often required for development on macOS.

```bash
brew install espeak ffmpeg gcc git curl
```

```bash
xcode-select --install
```

--------------------------------

### Execute AllTalk TTS Fine-tuning Process

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Commands to navigate into the AllTalk TTS extension directory, set up necessary CUDA library paths for Linux, and initiate the fine-tuning process using the Python script.

```Shell
cd extensions/alltalk_tts
```

```Shell
export LD_LIBRARY_PATH=`python3 -c 'import os; import nvidia.cublas.lib; import nvidia.cudnn.lib; print(os.path.dirname(nvidia.cublas.lib.__file__) + ":" + os.path.dirname(nvidia.cudnn.lib.__file__))'`
```

```Shell
python finetune.py
```

--------------------------------

### Activate Environment for Text-generation-webui Integration

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Commands to navigate to the Text-generation-webui directory and activate its Python environment using platform-specific scripts, preparing for AllTalk TTS fine-tuning.

```Shell
cd text-generation-webui
cmd_windows.bat
```

```Shell
cd text-generation-webui
./cmd_linux.sh
```

```Shell
cd text-generation-webui
cmd_macos.sh
```

```Shell
cd text-generation-webui
cmd_wsl.bat
```

--------------------------------

### Generate AllTalk TTS Diagnostics Report Manually

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Provides step-by-step instructions for creating a diagnostics log file when the `atsetup` utility is not available. It covers navigating to the correct directories and activating the Python environment for both Text-generation-webui and Standalone AllTalk installations, followed by executing the diagnostics script.

```Batch
cd text-generation-webui
cmd_windows.bat
cd extensions\alltalk_tts
```

```Shell
cd text-generation-webui
./cmd_linux.sh
cd extensions/alltalk_tts
```

```Shell
cd text-generation-webui
cmd_macos.sh
cd extensions/alltalk_tts
```

```Batch
cd text-generation-webui
cmd_wsl.bat
cd extensions\alltalk_tts
```

```Batch
cd alltalk_tts
start_environment.bat
```

```Shell
cd alltalk_tts
./start_environment.sh
```

```Python
python diagnostics.py
```

--------------------------------

### Windows Batch Script to Start AllTalk TTS

Source: https://github.com/erew123/alltalk_tts/wiki/Install-‐-Manual-Installation-Guide

A Windows batch script designed to initialize and start the AllTalk TTS application. It sets environment variables for Conda paths, activates the designated Python environment, and then executes the main 'script.py' to launch the application.

```batch
@echo off
cd /D "%~dp0"
set CONDA_ROOT_PREFIX=C:\myfolder\alltalk_tts\alltalk_environment\conda
set INSTALL_ENV_DIR=C:\myfolder\alltalk_tts\alltalk_environment\env
call "%CONDA_ROOT_PREFIX%\condabin\conda.bat" activate "%INSTALL_ENV_DIR%"
call python script.py
```

--------------------------------

### Run AllTalk Standalone with Text Generation Web UI Environment

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Instructions for launching AllTalk as a standalone application by first activating the Text Generation Web UI's Python environment and then executing the AllTalk script from its directory.

```Shell
# Activate Text Generation Web UI Python Environment (choose one based on OS)
cmd_windows.bat
./cmd_linux.sh
cmd_macos.sh
cmd_wsl.bat

# Navigate to the AllTalk Directory
cd extensions
cd alltalk_tts

# Start AllTalk
python script.py
```

--------------------------------

### Navigate to AllTalk Directory and Create Environment Folder

Source: https://github.com/erew123/alltalk_tts/wiki/Install-‐-Manual-Installation-Guide

Change into the newly cloned 'alltalk_tts' directory and then create a dedicated 'alltalk_environment' subdirectory for managing the project's virtual environment and dependencies.

```cmd
cd alltalk_tts
mkdir alltalk_environment
cd alltalk_environment
```

```bash
cd alltalk_tts
mkdir alltalk_environment
cd alltalk_environment
```

--------------------------------

### Launch AllTalk TTS XTTS Finetuning Script

Source: https://github.com/erew123/alltalk_tts/wiki/XTTS-Model-Finetuning-Guide-(Simple-Version)

This snippet provides the command-line instructions to initiate the XTTS model finetuning process for standalone AllTalk installations. It includes separate commands for Linux and Windows environments.

```bash
# For standalone AllTalk:
cd alltalk_tts
./start_finetune.sh    # (Linux)
start_finetune.bat     # (Windows)
```

--------------------------------

### Clone AllTalk TTS Repository

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Command to clone the AllTalk TTS repository from GitHub to set up a new instance, typically used after renaming an old installation.

```bash
git clone https://github.com/erew123/alltalk_tts
```

--------------------------------

### Curl Certificate Validation Error Example

Source: https://github.com/erew123/alltalk_tts/wiki/Error-Messages-List

An example of the `curl` error message `CRYPT_E_NO_REVOCATION_CHECK` which indicates issues with SSL/TLS certificate validation. This error often stems from problems with system clock settings, outdated `curl` versions, outdated root certificates, or network/firewall restrictions preventing communication with Certificate Authorities.

```bash
curl: (35) schannel: next InitializeSecurityContext failed: CRYPT_E_NO_REVOCATION_CHECK
```

--------------------------------

### Activate Fine-tuning Environment for Standalone AllTalk

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Commands to navigate to the AllTalk TTS directory and launch the fine-tuning environment using platform-specific batch or shell scripts for standalone AllTalk users.

```Shell
cd alltalk_tts
start_finetune.bat
```

```Shell
cd alltalk_tts
./start_finetune.sh
```

--------------------------------

### Install Python Requirements for Standalone AllTalk TTS

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Install or update Python dependencies required for the standalone AllTalk TTS application using pip, specifying the requirements file for this setup.

```Python
pip install -r system\requirements\requirements_standalone.txt
```

```Python
pip install -r system/requirements/requirements_standalone.txt
```

--------------------------------

### Clone AllTalk TTS Repository into Text Generation Web UI Extensions

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Navigate into the 'extensions' directory within your Text Generation Web UI installation, then clone the AllTalk TTS GitHub repository. Finally, change into the newly cloned 'alltalk_tts' directory.

```bash
cd extensions
git clone https://github.com/erew123/alltalk_tts
cd alltalk_tts
```

--------------------------------

### Control DeepSpeed Endpoint

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

API endpoint and example `curl` command to enable or disable DeepSpeed mode for TTS generation. This setting can optimize performance. Returns a status JSON upon success.

```APIDOC
Endpoint: /api/deepspeed
Method: POST
Parameters:
  new_deepspeed_value: boolean (query parameter) - Set to True to enable, False to disable DeepSpeed mode.
Returns:
  JSON: {"status": "deepspeed-success"}
```

```curl
curl -X POST "http://127.0.0.1:7851/api/deepspeed?new_deepspeed_value=True"
```

--------------------------------

### Install DeepSpeed

Source: https://github.com/erew123/alltalk_tts/wiki/Install-‐-Manual-Installation-Guide

Install the DeepSpeed library, which is used for optimizing large-scale model training and inference. The installation method varies by OS.

```cmd
curl -LO https://github.com/erew123/alltalk_tts/releases/download/DeepSpeed-14.0/deepspeed-0.14.0+ce78a63-cp311-cp311-win_amd64.whl
pip install deepspeed-0.14.0+ce78a63-cp311-cp311-win_amd64.whl
del deepspeed-0.14.0+ce78a63-cp311-cp311-win_amd64.whl
```

```bash
pip install deepspeed
```

--------------------------------

### Resolve Python ModuleNotFoundError

Source: https://github.com/erew123/alltalk_tts/wiki/Error-Messages-List

This snippet provides a comprehensive guide to troubleshoot and resolve 'ModuleNotFoundError' in Python projects, typically caused by missing or incorrectly installed packages. It covers environment activation, dependency installation, package reinstallation, and cache management.

```Batch
start_environment.bat
```

```Shell
./start_environment.sh
```

```Shell
pip install -r requirements.txt
```

```Shell
pip uninstall XXXXXXX
```

```Shell
pip install XXXXXXX --upgrade --force-reinstall
```

```Shell
pip cache purge
```

--------------------------------

### XTTS Model Training Configuration Example

Source: https://github.com/erew123/alltalk_tts/wiki/XTTS-Model-Finetuning-Guide-(Advanced-Version)

An example Python dictionary demonstrating recommended configuration settings for high-quality XTTS model training, specifying the optimizer, learning rate, batch size, gradient accumulation steps, and scheduler.

```python
# Example configuration for high-quality training
config = {
    'optimizer': 'AdamW',
    'learning_rate': 1e-5,
    'batch_size': 8,
    'gradient_accumulation_steps': 4,
    'scheduler': 'CosineAnnealingWarmRestarts'
}
```

--------------------------------

### Initialize AllTalkAPI and Display Server Information

Source: https://github.com/erew123/alltalk_tts/wiki/API-‐-Best-Practices-AllTalk-API-Integration

This example demonstrates the fundamental steps to set up and verify the AllTalkAPI connection. It shows how to create an instance of the `AllTalkAPI` class, initialize the connection, and then call `display_server_info()` to retrieve and print the current server settings and capabilities. Error handling for initialization failure is included.

```python
if __name__ == "__main__":
    # Create an instance of the AllTalkAPI
    api = AllTalkAPI()
    
    # Initialize the API and fetch server information
    if api.initialize():
        print("AllTalk API initialized successfully.")
        
        # Display all server information
        api.display_server_info()
    else:
        print("Failed to initialize AllTalk API.")
```

--------------------------------

### Access AllTalk via Local IP Address

Source: https://github.com/erew123/alltalk_tts/wiki/Error-Messages-List

Example of accessing the AllTalk web interface using a local IP address instead of 'localhost' or '127.0.0.1'. This can help resolve connectivity issues related to network configurations.

```text
http://192.168.1.20:7852/?__theme=dark
```

--------------------------------

### Changing Web Server Port in confignew.json

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Example of how to modify the port number in the 'confignew.json' file to resolve conflicts where another application is already using the default port 7851. Users can change it to any available port.

```JSON
"port_number": "7851"
```

```JSON
"port_number": "7602"
```

--------------------------------

### Generate AllTalk TTS Diagnostics with Setup Utility

Source: https://github.com/erew123/alltalk_tts/blob/main/system/admin.html

Instructions for using the `atsetup` utility to automatically create a diagnostics file. This method is recommended for both Windows and Linux users if the utility is available and functional.

```Shell
atsetup.bat
```

```Shell
./atsetup.sh
```

--------------------------------

### Get Current TTS Model Settings

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

This endpoint retrieves the current configuration and status of the Text-to-Speech service, including available models, the currently loaded model, and DeepSpeed/VRAM status. The response is a detailed JSON object.

```APIDOC
Endpoint: /api/currentsettings
  Method: GET
  URL: http://127.0.0.1:7851/api/currentsettings
  Response:
    models_available: object[] (List of available models)
      name: string
      model_name: string
    current_model_loaded: string (Name of the model currently loaded into VRAM)
    deepspeed_available: boolean (True if DeepSpeed was detected on startup)
    deepspeed_status: boolean (True if DeepSpeed is currently activated)
    low_vram_status: boolean (True if Low VRAM is currently enabled)
    finetuned_model: boolean (True if a finetuned model was detected, e.g., XTTSv2 FT)
```

```Bash
curl -X GET "http://127.0.0.1:7851/api/currentsettings"
```

--------------------------------

### Execute AllTalk Startup Scripts

Source: https://github.com/erew123/alltalk_tts/wiki/AllTalk-V2-QuickStart-Guide

These commands are used to launch different components of the AllTalk TTS application. Each script serves a specific purpose, from starting the main application to managing the Python environment or initiating finetuning processes.

```Bash
start_alltalk
```

```Bash
start_environment
```

```Bash
start_finetune
```

```Bash
start_diagnostics
```

--------------------------------

### Download and Install Miniconda

Source: https://github.com/erew123/alltalk_tts/wiki/Install-‐-Manual-Installation-Guide

Download the Miniconda installer for the respective operating system and perform a silent installation. Miniconda is used to manage Python environments and packages.

```cmd
curl -Lk "https://repo.anaconda.com/miniconda/Miniconda3-py311_24.4.0-0-Windows-x86_64.exe" > miniconda_installer.exe
start /wait "" miniconda_installer.exe /InstallationType=JustMe /NoShortcuts=1 /AddToPath=0 /RegisterPython=0 /NoRegistry=1 /S /D=%cd%\conda
```

```bash
curl -LO https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
bash Miniconda3-latest-Linux-x86_64.sh -b -p $PWD/conda
```

--------------------------------

### Increase TTS Subprocess Startup Timeout

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

The 'Warning TTS Subprocess has NOT started up yet' message, especially when followed by a timeout, often indicates that the voice model is taking too long to load into VRAM/RAM or the mini-webserver is slow to start, particularly on older machines. To address this, you can extend the allowed startup time by editing the `script.py` file and increasing the value of `startup_wait_time`.

```Python
startup_wait_time = 120
```

```Python
startup_wait_time = 240
```

--------------------------------

### Run AllTalk Finetuning Script

Source: https://github.com/erew123/alltalk_tts/wiki/Install-‐-Manual-Installation-Guide

Executes the 'finetuning.py' Python script to initiate the finetuning process for AllTalk TTS models. This command is used when performing model training or adaptation.

```bash
python finetuning.py
```

--------------------------------

### Uninstalling DeepSpeed

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Command to uninstall DeepSpeed, often necessary when troubleshooting issues related to incorrect versions or installations that conflict with the current Python environment or text-generation-webui setup.

```Shell
pip uninstall deepspeed
```

--------------------------------

### Navigate to Text-generation-webui and Activate Environment

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Commands to change the current directory to the Text-generation-webui folder and activate its custom Conda environment, which is necessary before installing DeepSpeed.

```bash
cd text-generation-webui
```

```bash
./cmd_linux.sh
```

--------------------------------

### Install Parler Requirements

Source: https://github.com/erew123/alltalk_tts/wiki/Install-‐-Manual-Installation-Guide

Install additional Python dependencies specifically required for the Parler component of the project, listed in 'requirements_parler.txt'.

```cmd
pip install -r system\requirements\requirements_parler.txt
```

```bash
pip install -r system/requirements/requirements_parler.txt
```

--------------------------------

### Detailed Training Initialization Output

Source: https://github.com/erew123/alltalk_tts/wiki/XTTS-Model-Finetuning-Guide-(Advanced-Version)

Confirms the successful loading of model files and provides a comprehensive overview of the training parameters, including optimizer and gradient accumulation settings.

```console
[MODEL] ✓ All required files found for model: xttsv2_2.0.3
[MODEL] Training Configuration:
- Language: en
- Epochs: 4
- Batch Size: 4
- Gradient Accumulation: 1
- Learning Rate: 5e-06
- Learning Rate Scheduler: CosineAnnealingWarmRestarts
- Optimizer: AdamW
```

--------------------------------

### Clone AllTalk Repository for Text-generation-webui

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Navigate to the Text-generation-webui extensions directory and clone the AllTalk TTS repository using Git. This method is recommended for automatic updates.

```Shell
cd \text-generation-webui\extensions\
git clone https://github.com/erew123/alltalk_tts
```

--------------------------------

### Disable Coqui TTS Trainer Telemetry

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Instructions to manually disable anonymous training telemetry for Coqui's TTS trainer scripts before starting finetuning. This ensures that no anonymous training data is sent, allowing for offline operation.

```Batch
set TRAINER_TELEMETRY=0
```

```Bash
export TRAINER_TELEMETRY=0
```

--------------------------------

### Install Parler Requirements

Source: https://github.com/erew123/alltalk_tts/wiki/Install-‐-Manual-Installation-Guide

Installs Python dependencies specifically required for the Parler component of AllTalk TTS. These dependencies are listed in the 'system/requirements/requirements_parler.txt' file.

```bash
pip install -r system/requirements/requirements_parler.txt
```

--------------------------------

### Resolve PyTorch Version Mismatch with DeepSpeed

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

This error indicates that the installed DeepSpeed version was compiled for a different version of Python, PyTorch, or CUDA than what is currently in use. To fix this, you must uninstall the existing DeepSpeed from your Python environment using `pip` and then install the correct version compatible with your current setup.

```Log
raise RuntimeError("PyTorch version mismatch! DeepSpeed ops were compiled and installed 
RuntimeError: PyTorch version mismatch! DeepSpeed ops were compiled and installed with a different version than what is being used at runtime. Please re-install DeepSpeed or switch torch versions. Install torch version=2.1, Runtime torch version=2.2
```

```Python
pip uninstall deepspeed
```

--------------------------------

### Clone AllTalk TTS GitHub Repository

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Command to clone the AllTalk TTS source code from its GitHub repository into the current directory and then navigate into the newly created project folder.

```Shell
git clone https://github.com/erew123/alltalk_tts
cd alltalk_tts
```

--------------------------------

### Download and Install Miniconda on macOS

Source: https://github.com/erew123/alltalk_tts/wiki/Install-‐-Manual-Installation-Guide

Downloads the Miniconda installer for macOS (x86_64) from the official Anaconda repository. It then executes the installer in batch mode, installing Miniconda into a 'conda' directory within the current working directory, which is suitable for isolated environments.

```bash
curl -LO https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-x86_64.sh
bash Miniconda3-latest-MacOSX-x86_64.sh -b -p $PWD/conda
```

--------------------------------

### Navigate to AllTalk TTS Project Directory

Source: https://github.com/erew123/alltalk_tts/blob/main/README.md

Changes the current working directory to the 'alltalk_tts' project folder. This step is essential before executing any project-specific scripts or commands.

```Bash
cd alltalk_tts
```

--------------------------------

### Update AllTalk TTS Standalone Application

Source: https://github.com/erew123/alltalk_tts/blob/main/system/admin.html

This guide provides commands to update the standalone AllTalk TTS application. It covers navigating to the application directory, activating its dedicated Python environment, pulling the latest code from the repository, and installing updated Python dependencies specific to the standalone setup.

```bash
cd alltalk_tts
```

```batch
cd alltalk_tts
```

```batch
start_environment.bat
```

```bash
./start_environment.sh
```

```bash
git pull
```

```batch
pip install -r system\requirements\requirements_standalone.txt
```

```bash
pip install -r system/requirements/requirements_standalone.txt
```