PlachtaVITS Voice Conversion
This repo will guide you to add your voice into an existing VITS TTS model to make it a high-quality voice converter to all existing character voices in the model.
Welcome to play around with the base model, a Trilingual Anime VITS!
Currently Supported Tasks:
- Convert user's voice to characters listed here
- Chinese, English, Japanese TTS with user's voice
- Chinese, English, Japanese TTS with custom characters!
Currently Supported Characters for TTS & VC:
- Umamusume Pretty Derby (Used as base model pretraining)
- Sanoba Witch (Used as base model pretraining)
- Genshin Impact (Used as base model pretraining)
- Any character you wish as long as you have their voices!
Fine-tuning
It's recommended to perform fine-tuning on Google Colab because the original VITS has some dependencies that are difficult to configure.
How long does it take?
- Install dependencies (2 min)
- Record at least 20 your own voice (5~10 min)
- Upload your character voices, which should be a
.zipfile, it's file structure should be like:
Your-zip-file.zip
├───Character_name_1
├ ├───xxx.wav
├ ├───...
├ ├───yyy.mp3
├ └───zzz.wav
├───Character_name_2
├ ├───xxx.wav
├ ├───...
├ ├───yyy.mp3
├ └───zzz.wav
├───...
├
└───Character_name_n
├───xxx.wav
├───...
├───yyy.mp3
└───zzz.wav
Note that the format & name of the audio files does not matter as long as they are audio files.
You can either choose to perform step 2, 3, or both, depending on your needs.
4. Fine-tune (30 min)
After everything is done, download the fine-tuned model & model config
Inference or Usage (Currently support Windows only)
- Remember to download your fine-tuned model!
- Download the latest release
- Put your model & config file into the folder
inference, make sure to rename the model toG_latest.pthand config file tofinetune_speaker.json - The file structure should be as follows:
inference
├───inference.exe
├───...
├───finetune_speaker.json
└───G_latest.json
- run
inference.exe, the browser should pop up automatically.