kan-bayashi/ParallelWaveGAN

Questions on SVS

Opened this issue · 4 comments

Deleted user commented

Hi, im highly interested singing voice synthesis, i saw that there are pretrained models for svs but i dont understand how to specify what the model should sing eg is it possible to have it sing a text?

ftshijt commented

Thanks for your interest on singing voice synthesis. This pre-trained model in this repo is for the vocoder training (i.e., converting acoustic features into waveform) instead of acoustic modeling. If you are interested in acoustic modeling (e.g., score2wav, score2feat), please feel free to check either ESPnet or Muskits, where we do offer acoustic modeling training with vocoders provided from this repo.

Deleted user commented

Hi thank you for your time and the information provided, ill make sure to check it out. :)

lhc991025 commented

Thanks for your interest on singing voice synthesis. This pre-trained model in this repo is for the vocoder training (i.e., converting acoustic features into waveform) instead of acoustic modeling. If you are interested in acoustic modeling (e.g., score2wav, score2feat), please feel free to check either ESPnet or Muskits, where we do offer acoustic modeling training with vocoders provided from this repo.

I want to train a vocoder with my own data. How do I do that?

ftshijt commented

You can follow any of the existing recipe, but replacing the wav.scp with your own data.