https://github.com/log1stics/voice-generator-webui
A multi-speaker, multilingual speech generation tool
https://github.com/log1stics/voice-generator-webui
Last synced: about 1 month ago
JSON representation
A multi-speaker, multilingual speech generation tool
- Host: GitHub
- URL: https://github.com/log1stics/voice-generator-webui
- Owner: log1stics
- License: mit
- Created: 2023-04-16T12:09:31.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2023-10-13T08:50:53.000Z (over 1 year ago)
- Last Synced: 2024-08-03T01:25:04.265Z (10 months ago)
- Language: Jupyter Notebook
- Homepage:
- Size: 1.78 MB
- Stars: 150
- Watchers: 7
- Forks: 21
- Open Issues: 12
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-ChatGPT-repositories - voice-generator-webui - A multi-speaker, multilingual speech generation tool (Chatbots)
README
# Voice Generator web UI
A Multi-speaker, multilingual speech generation tool.
日本語は[こちら](docs/ja/README.md)
[](https://colab.research.google.com/github/log1stics/voice-generator-webui/blob/main/colab.ipynb)
## Features
- Speech synthesis for 209 speakers (109 English / 100 Japanese)
- [Script generation using LLM](docs/how_llm.md)
- Accent and phoneme editing functions
- Voice conversion by RVC
- Batch voice conversion by RVC
## Installation and Running
- [Python](https://www.python.org/downloads/windows/) (tested on 3.10.6)
- PyTorch for CUDA
Check if the CUDA version of PyTorch is already installed with `pip show torch`.
It is OK if `cu` is included in the Version as follows.
```shell
Version: 2.0.0+cu118
```
If not, install the CUDA version of PyTorch.
```
pip uninstall torch
pip install torch --index-url https://download.pytorch.org/whl/cu118
```
### Windows
- [espeak](docs/dependencies.md#espeak)
- [Build Tools for Visual Studio](docs/dependencies.md#build-tools-for-visual-studio) (Not necessary if Japanese is not generated)
1. download the zip or
`git clone https://github.com/log1stics/voice-generator-webui`
2. run `setup.bat` or `setup.bat en`
`setup.bat en` avoids installation of pyopenjtalk used for Japanese generation
Run the webui.py file in PowerShell or at the command prompt
```
python webui.py
```
### Linux
Run the webui.py file at a PowerShell or command prompt
```shell
apt-get install espeak # For English Text To Speak
git clone https://github.com/log1stics/voice-generator-webui
chmod +x setup.sh
```
```
setup.sh
```
```shell
# if you do not use Japanese Text To Speak
# you can avoid install pyopenjtalk
setup.sh en
```
## Add RVC model
For example, if you want to handle an RVC trained model named EXAMPLE_MODEL.pth, place it as follows
```bash
vc/
└── models/
└── EXAMPLE_MODEL/
├── EXAMPLE_MODEL.pth # file name should be the same as the directory name
├── added.index # not necessary (name is fixed to added.index)
└── total_fea.npy # not necessary (name is fixed to added.index)
```
## Contributing
Here's how to add code to this repo: [Contributing](docs/add_vits.md)
## Credits
- [VITS](https://github.com/jaywalnut310/vits)
- [Retrieval-based-Voice-Conversion-WebUI](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI)
- [pyopenjtalk](https://github.com/r9y9/pyopenjtalk)
### Dataset
- [JVS](https://sites.google.com/site/shinnosuketakamichi/research-topics/jvs_corpus)
- [VCTK](https://datashare.ed.ac.uk/handle/10283/2950)