Skip to content

This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion

License

Notifications You must be signed in to change notification settings

upseem/VITS-fast-fine-tuning

 
 

Repository files navigation

中文文档请点击这里

VITS Fast Fine-tuning

This repo will guide you to add your own character voices, or even your own voice, into existing VITS TTS model to make it able to do the following tasks in less than 1 hour:

  1. Many-to-many voice conversion between any characters you added & preset characters in the model.
  2. English, Japanese & Chinese Text-to-Speech synthesis with the characters you added & preset characters

Welcome to play around with the base models!
Chinese & English & Japanese:Hugging Face Spaces Author: Me

Chinese & Japanese:Hugging Face Spaces Author: SayaSS

Chinese only:(No running huggingface spaces) Author: Wwwwhy230825

Currently Supported Tasks:

  • Clone character voice from 10+ short audios
  • Clone character voice from long audio(s) >= 3 minutes (one audio should contain single speaker only)
  • Clone character voice from videos(s) >= 3 minutes (one video should contain single speaker only)
  • Clone character voice from BILIBILI video links (one video should contain single speaker only)

Currently Supported Characters for TTS & VC:

  • Any character you wish as long as you have their voices! (Note that voice conversion can only be conducted between any two speakers in the model)

Fine-tuning

See LOCAL.md for local training guide.
Alternatively, you can perform fine-tuning on Google Colab

How long does it take?

  1. Install dependencies (3 min)
  2. Choose pretrained model to start. The detailed differences between them are described in Colab Notebook
  3. Upload the voice samples of the characters you wish to add,see DATA.MD for detailed uploading options.
  4. Start fine-tuning. Time taken varies from 20 minutes ~ 2 hours, depending on the number of voices you uploaded.

Inference or Usage (Currently support Windows only)

  1. Remember to download your fine-tuned model!
  2. Download the latest release
  3. Put your model & config file into the folder inference, which are named G_latest.pth and finetune_speaker.json, respectively.
  4. The file structure should be as follows:
inference
├───inference.exe
├───...
├───finetune_speaker.json
└───G_latest.pth
  1. run inference.exe, the browser should pop up automatically.
  2. Note: you must install ffmpeg to enable voice conversion feature.

Use in MoeGoe

  1. Prepare downloaded model & config file, which are named G_latest.pth and moegoe_config.json, respectively.
  2. Follow MoeGoe page instructions to install, configure path, and use.

Looking for help?

If you have any questions, please feel free to open an issue or join our Discord server.

About

This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 99.4%
  • Cython 0.6%