/text-generation-webui-barktts

A simple extension that uses Bark Text-to-Speech for audio output

Primary LanguagePythonOtherNOASSERTION

text-generation-webui-barktts

A simple extension for the text-generation-webui by oobabooga that uses Bark for audio output.

⚠️Important Info⚠️

This repo is not actively maintained (at least for a while). If you want a version that works and fixes some issues with my code, have a look at RandoInternetPreson's Fork

How to install

Assuming you already have the webui set up:

  1. Activate the conda environment with the cmd_xxx.bat or using conda activate textgen
  2. Enter the text-generation-webui/extensions/ directory and clone this repository
cd text-generation-webui/extensions/
git clone https://github.com/minemo/text-generation-webui-barktts bark_tts/
  1. install the requirements
pip install -r extensions/bark_tts/requirements.txt
  1. Add --extensions bark_tts to your startup script
    or
    enable it through the Interface Mode tab in the webui

Tips

The full version of Bark requires around 12Gb of memory to hold everything on GPU at the same time. However, even smaller cards down to ~2Gb work with some additional settings. For this extension, you could open extensions/bark_tts/.env, then set USE_SMALL_MODELS and USE_CPU to true:

# Whether to use small models
USE_SMALL_MODELS=true

# Whether to use CPU
USE_CPU=true