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

COLA == Training Instability? #51

Open
zaptrem opened this issue May 5, 2024 · 0 comments
Open

COLA == Training Instability? #51

zaptrem opened this issue May 5, 2024 · 0 comments

Comments

@zaptrem
Copy link

zaptrem commented May 5, 2024

I'm training a Vocos decoder for my DAC autoencoder. When I set hop length = 256 and n_fft = 1024 in the iSTFT head the discriminators quickly win within 1000 steps. However, this doesn't happen when I set n_fft = 512, 768, or 1026. Do you know why this is happening and whether using 1026 would affect quality? I don't completely understand the COLA property.

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

1 participant