Skip to content
This repository has been archived by the owner on Jun 20, 2023. It is now read-only.

Google collab for testing SoftVC VITS Singing Voice Conversion for AI capable of changing the singer within music files.

Notifications You must be signed in to change notification settings

MahdeenSky/SoftVC-VITS-MusicSingerChanger

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 

Repository files navigation

SoftVC-VITS-MusicSingerChangerCollab

Google collab for testing SoftVC VITS Singing Voice Conversion for AI capable of changing the singer within music files.

The singing voice conversion model uses SoftVC content encoder to extract source audio speech features, then the vectors are directly fed into VITS instead of converting to a text based intermediate; thus the pitch and intonations are conserved. Additionally, the vocoder is changed to NSF HiFiGAN to solve the problem of sound interruption.

Open In Collab

Open In Colab

Example of music made through SoftVC-VITS

Kanye West - Billie Jeans (AI Cover)

Credits

https://github.com/svc-develop-team/so-vits-svc

https://www.youtube.com/@PluggingAI

https://huggingface.co/therealvul

About

Google collab for testing SoftVC VITS Singing Voice Conversion for AI capable of changing the singer within music files.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published