AutoPST the speech content of converted voice with my own trained model changed

the speech content of converted voice with my own trained model changed

Open wang1612 opened this issue 3 years ago • 2 comments

Why did the speech content of the converted voice with my own trained model changed? Do you know the reason?

Dec 16 '21 19:12 wang1612

It might be due to the content loss in the content embedding. Maybe you could try replacing the SEA with a better self-supervised model.

Dec 16 '21 20:12 auspicious3000

@auspicious3000 But I did not use SEA and the same problem occurred. Do you know the reason？

Dec 19 '21 06:12 wang1612