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

Checkpoints not found #21

Open
naitian opened this issue Apr 7, 2024 · 1 comment
Open

Checkpoints not found #21

naitian opened this issue Apr 7, 2024 · 1 comment

Comments

@naitian
Copy link

naitian commented Apr 7, 2024

From the documentation, I use pyfoal.DEFAULT_CHECKPOINT, but it looks like this path (assets/checkpoints) doesn't exist. Are we supposed to train the model ourselves? Are there pre-trained weights available for download somewhere?

Thanks!

@maxrmorrison
Copy link
Owner

I do not currently have pre-trained weights. My concern with releasing pre-trained weights is—while the rough idea of RADTTS is provided in this repo—it is not the official version, and contains some differences. Until those are mended, I've been keeping the bar for using that a bit higher. Also, P2FA and my improvements over my baseline RADTTS (in config/) both outperform each other on different metrics included in pyfoal. So it's not yet clear that RADTTS is strictly improving over much older methods.

TLDR; training works, P2FA works, but no RADTTS checkpoint until I've verified that implementation is correct relative to the original paper.

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