metadata
language:
- en
license: mit
library_name: pytorch
tags:
- so-vits-svc
- voice-cloning
- audio-to-audio
Model Card for dog/kanye
This model will take in any voice and try to clone it in the style of Kanye West. It was trained using the so-vits-svc-fork repo.
To train your own, you can check out this Colab notebook: 