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.

Sign up for GitHub

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

Jump to bottom

use of NoiseBlock and depthwise? #7

Closed

listener17 opened this issue Mar 22, 2024 · 1 comment

listener17 commented Mar 22, 2024

Hi!

Interesting work. But I don't understand the following changes:

I think you're doing "depthwise" for reducing the number the parameters. Correct?
What's the use of NoiseBlock in the decoder?

listener17 closed this as completed

zaptrem mentioned this issue

Architectural questions (SNAC vs Vocos) #13

Open

Owner

hubertsiuzdak commented Apr 19, 2024

Hello!

Depthwise convolutions not only reduced the parameter count, but also helped me optimize the model. After replacing most of the convolutions with DW, I could use higher learning rates without the model collapsing. Surprisingly, the perceived quality was higher!
Injecting noise into the decoder improved my models. I believe it's helpful to introduce some stochasticity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment