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

Codec size is huge #4

Open
MonolithFoundation opened this issue Jan 21, 2025 · 2 comments
Open

Codec size is huge #4

MonolithFoundation opened this issue Jan 21, 2025 · 2 comments

Comments

@MonolithFoundation
Copy link

The current codec model huge, about 14GB, this even not count the LLM size.

Any plan to release a smaller size codec?

@zhenye234
Copy link
Owner

The codec model itself is actually not that large; it only uses about 3GB, with parameter size being less than 1B, https://huggingface.co/HKUST-Audio/xcodec2/blob/main/pytorch_model.bin For inference, you only need this. The larger size is because I also provided checkpoint includes all the state, making it suitable for continued training as well. https://huggingface.co/HKUST-Audio/xcodec2/blob/main/ckpt/epoch%3D4-step%3D1400000.ckpt Hope this clears things up!

@MonolithFoundation
Copy link
Author

thank u, is that possible make 3G even smaller but still maintain the ability?

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