vosk-vc-ru / README.md
nshmyrevgmail's picture
Update README.md
64d2f17 verified
|
raw
history blame
481 Bytes
metadata
license: apache-2.0
language:
  - ru
pipeline_tag: audio-to-audio

About

This is a basic zero-shot voice conversion model trained with VITS + softhubert

See:

https://github.com/alphacep/vosk-tts/tree/master/vc

https://github.com/quickvc/QuickVC-VoiceConversion

Speaker Similarity

Computed with eval.py with Resemblyzer

Original QuickVC (trained on VCTK)       Average: 0.667 Min: 0.477
New model                                Average: 0.836 Min: 0.692