https://github.com/vtuber-plan/vcvits

Non Parallel Voice Conversion based on VITS
https://github.com/vtuber-plan/vcvits

speech-synthesis svc vits

Last synced: 5 days ago
JSON representation

Non Parallel Voice Conversion based on VITS

• Host: GitHub
• URL: https://github.com/vtuber-plan/vcvits
• Owner: vtuber-plan
• License: mit
• Created: 2022-10-05T16:16:39.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2023-03-31T18:07:37.000Z (over 1 year ago)
• Last Synced: 2024-11-18T08:55:47.555Z (25 days ago)
• Topics: speech-synthesis, svc, vits
• Language: Python
• Homepage:
• Size: 8.52 MB
• Stars: 23
• Watchers: 6
• Forks: 3
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# VCVITS: VITS-based Voice conversion Model

This is a repository for a voice conversion model based on [VITS](https://github.com/jaywalnut310/vits).

## Pre-requisites

0. Python >= 3.8

0. Clone this repository

0. Install python requirements. Please refer [requirements.txt](requirements.txt)

0. Download FairSeq Hubert pretrained models：[Download](https://github.com/facebookresearch/fairseq/blob/main/examples/hubert/README.md)

0. Download datasets

## Parameters

## Training

### File List Generation

First generate the file list text file from the dataset folder.

One folder for audio files of each speaker in the dataset folder.

Run `filelist.py` to get `filelist.txt`

Then split the training and validation dataset, run `split.py`.

### Config Settings

## Inference

pass