Stella VC Based on Soft-VC and VITS

This project is closed...

Contents

• Update
• Introduction
• Models
  • A Certain Magical Index
  • Shiki Natsume
  • Shiki Natsume 2.0
• How to use
• TODO
• Contact
• Acknowledgement
• References

Update

• Sovits 2.0 inference demo is available!

Introduction

Inspired by Rcell, I replaced the word embedding of TextEncoder in VITS with the output of the ContentEncoder used in Soft-VC to achieve any-to-one voice conversion with non-parallel data. Of course, any-to-many voice converison is also doable!

For better voice quality, in Sovits2, I utilize the f0 model used in StarGANv2-VC to get fundamental frequency feature of an input audio and feed it to the vocoder of VITS.

Models

A Certain Magical Index

• Description

• Model: Google drive

• Config: in this repository

• Demo

  • Colab: Sovits (魔法禁书目录)
  • BILIBILI: 基于Sovits的4人声音转换模型

Shiki Natsume

• Description

Single speaker model of Shiki Natsume.

• Model: Google drive

• Config: in this repository

• Demo

  • Colab: Sovits (四季夏目)
  • BILIBILI: 枣子姐变声器

Shiki Natsume 2.0

• Description

Single speaker model of Shiki Natsume, trained with F0 feature.

• Model: Google drive

• Config: in this repository

• Demo

  • Colab: Sovits2 (四季夏目)

How to use

Train

Prepare dataset

Audio should be wav file, with mono channel and a sampling rate of 22050 Hz.

Your dataset should be like:

└───wavs
    ├───dev
    │   ├───LJ001-0001.wav
    │   ├───...
    │   └───LJ050-0278.wav
    └───train
        ├───LJ002-0332.wav
        ├───...
        └───LJ047-0007.wav

Extract speech units

Utilize the content encoder to extract speech units in the audio.

For more information, refer to this repo.

cd hubert
python3 encode.py soft path/to/wavs/directory path/to/soft/directory --extension .wav

Then you need to generate filelists for both your training and validation files. It's recommended that you prepare your filelists beforehand!

Your filelists should look like:

Single speaker:

path/to/wav|path/to/unit
...

Multi-speaker:

path/to/wav|id|path/to/unit
...

Train Sovits

Single speaker:

python train.py -c configs/config.json -m model_name

Multi-speaker:

python train_ms.py -c configs/config.json -m model_name

You may also refer to train.ipynb

Inference

Please refer to inference.ipynb

TOD0

• [x] Add F0 model
• [ ] Add F0 loss

Contact

QQ: 2235306122

BILIBILI: Francis-Komizu

Ackowledgement

Special thanks to Rcell for giving me both inspiration and advice!

References

基于VITS和SoftVC实现任意对一VoiceConversion

Soft-VC

vits

StarGANv2-VC