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

Option to set a custom random seed #10

Closed
wants to merge 6 commits into from

Conversation

DrMWeigand
Copy link

Integrated the possibility to set a random seed for which I found a function on some issue in the original suno repo. Although this still does not solve consistency issues when using longer text input, it is still nice to obtain very similar results for the same random seed.

@C0untFloyd
Copy link
Owner

You're talking about this this aren't you? I'm unsure if this really helps consistency as much as we would like. I'd like to wait if the PR is accepted by the Suno guys and further explanations/discussions. Thanks for the hint though 👍

@DrMWeigand
Copy link
Author

Exactly, that is what I meant. Indeed, it doesn't help to keep the same voice at inputs of greater length. However, it enables to reproduce previous results relatively well.

@C0untFloyd
Copy link
Owner

I implemented this with pytorch_seed (very easy that way) and it really is quite an advancement. I also store the used speaker/seed as ID3 Metadata in the resulting WAV, so it's a lot easier to share results.

@C0untFloyd C0untFloyd closed this May 8, 2023
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

Successfully merging this pull request may close these issues.

2 participants