New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add new state of the art voice seperation models (UVR) #400

Open

montvid opened this issue Nov 17, 2024 · 1 comment

Assignees

Labels

Milestone

montvid commented Nov 17, 2024

Thanks for showing that in order to do exact transcription one needs to use a voice seperation model (UVR) and a silence cutting model (VAD) and only afterwards transcribe with Whisper.
Found a list of recent state of the art voice seperation models here:
https://github.com/ZFTurbo/Music-Source-Separation-Training?tab=readme-ov-file#vocal-models
Experimenting with this one now:
https://github.com/KimberleyJensen/Mel-Band-Roformer-Vocal-Model

montvid added the enhancement label

montvid assigned jhj0517

Owner

jhj0517 commented Nov 17, 2024

Thanks for noticing, I'll definitely take a look at it when I have time!

jhj0517 added this to the bgm-separation milestone

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment