vits2 icon indicating copy to clipboard operation
vits2 copied to clipboard

espeak phoneme tokenization - failed experiment?

Open Teravus opened this issue 1 year ago • 0 comments

Hey there

I trained a model to 42,000 steps on master. And, it sounds like the voice that I trained it on but.. the phonemes sound like eSpeak-EN-US.

Just wondering if I should give it more time.. or go back a revision with the vocab as a static text that doesn't use espeak.

Teravus avatar Jan 17 '24 03:01 Teravus