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

Duration of generated audio #4

Open

sakshamsingh1 opened this issue Oct 30, 2024 · 0 comments

sakshamsingh1 commented Oct 30, 2024 •

edited

Loading

Hi,
Thanks for open-sourcing your wonderful work.

Compared to most visual-to-audio models that generate and evaluate on 10-second samples, the REWAS model produces audio with a duration of 5 seconds. I was wondering if you could explain why the duration is 5 seconds.
Additionally, I’m interested in extending the audio duration to 10 seconds. Would adjusting the shape of the initial noise latent be sufficient to achieve this, or would I need to generate two 5-second segments and combine them?

Thanks

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