Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Question on use WaveGlow instead of MelGan #10

Open
faranaziz opened this issue Apr 11, 2021 · 1 comment
Open

Question on use WaveGlow instead of MelGan #10

faranaziz opened this issue Apr 11, 2021 · 1 comment

Comments

@faranaziz
Copy link

faranaziz commented Apr 11, 2021

Hello,
Want use WeveGlow since MelGan have a lot of sound metalic. I see config:

audio: # WARNING! This cannot be changed unlees you're planning to train the MelGAN vocoder by yourself.
  n_mel_channels: 80
  filter_length: 1024
  hop_length: 256
  win_length: 1024
  sampling_rate: 22050
  mel_fmin: 70.0
  mel_fmax: 8000.0

What need change to work with pre-trained WavGlow? I try use but I think have problem with MEL normalization since sound very noisy.

I know WavGlow use mel_fmin: 0.0, I modify and retrain but still not work.
Thanks you

@seungwonpark
Copy link
Contributor

The mel-spectrogram calculation code of the WaveGlow and Cotatron differs much. Therefore the sounds will be metalic even when the mel configs are identical.

You might want to try matching the mel-spectrogram code. Since training the WaveGlow from scratch won't be feasible for most users, I would recommend to train Cotatron again.

Plus, you might be interested in our recent paper: https://arxiv.org/abs/2104.00931

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants