auspicious3000/SpeechSplit

Is it very slow for the Wavenet vocoder to synthesize a voice

hhhuazi opened this issue · 5 comments

hhhuazi commented

Hello, I use demo.ippynb synthesizes voice from mel, it takes 5 minutes to synthesize a voice. Isn't this too slow? Can I use HifiGAN's pre training model directly？Thank you for your answer！

auspicious3000 commented

yes, that's the purpose

hhhuazi commented

Thank you for your answer! I found the pre training model of hifiGAN in github and added it, but the synthesized voice has no content, such as noise. Why? Do I need to use the VCTK dataset to train the HiFiGAN vocoder again? Does the dataset need to be divided?

auspicious3000 commented

Yes. But you can also use the hifigan model under autovc or autopst.

hhhuazi commented

Are there any precautions for retraining vocoder?

auspicious3000 commented

It should be straightforward.