search

uberduck-ai / uberduck-ml-dev

ML models for Uberduck
Apache License 2.0
377 stars 61 forks source link

how to train my voice for tts then voice to voice ? #145

Closed Pimax1 closed 1 year ago

Pimax1 commented 1 year ago

Hi guys, its a bit hard for me to figure out what are the steps to follow to achieve something great.

I would like to train a voice first for tts and then for voice to voice in order to match other singers samples.

how to process ? what do you use for the voice to voice RADTTS ?

thank you very much

sjkoelle commented 1 year ago

Hi. Right now our production voice-to-voice inference code is in this branch

https://github.com/uberduck-ai/uberduck-ml-dev/pull/142

which we will merge soon.

Unfortunately, we don't have training code in there at the moment - you're best bet is to take it from here https://colab.research.google.com/github/justinjohn0306/so-vits-svc/blob/4.0/Sovits4_training_inference.ipynb#scrollTo=pCqf3W0d6ify

Radtts is for text-to-speech not voice-to-voice right now. We are working on a radtts fine tuning notebook, but it may be easier to use https://colab.research.google.com/drive/1jF-Otw2_ssEcus4ISaIZu3QDmtifUvyY

Does that help?

Pimax1 commented 1 year ago

thank you so much, i will check :)