metadata

license: cc-by-4.0
language:
  - en
library_name: vocos
tags:
  - music

Warning: This model is in beta and not ready for production use. It is undertrained and sounds terrible. A new version will be released soon!

Vocos Music 24kHz (beta)

A model similar to Vocos Mel 24kHz but trained on music.

This model was trained on music, it may not perform well on speech.

It may be used as a drop-in replacement for Vocos in tasks that require music.

Limitations

This model is trained on music, it may not perform well on speech or other audio tasks.