Skip to content

Any suggestions of how to use with Speech LLMs #5

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

Open
mush42 opened this issue Nov 2, 2024 · 1 comment
Open

Any suggestions of how to use with Speech LLMs #5

mush42 opened this issue Nov 2, 2024 · 1 comment

Comments

@mush42
Copy link

mush42 commented Nov 2, 2024

Hello

Thanks for making the code available.

Any recommendations regarding using this codec with audio LLMs?

Best
Musharraf

@yzGuu830
Copy link
Owner

Hi @mush42, similar to mainstream codecs like SoundStream and EnCodec, ESC can also function as an acoustic tokenizer, generating codes from multiple streams. I suggest drawing inspiration from recent audio generative models (AudioLM, VALL-E, MusicGen) to effectively model the multi-level discrete codes.

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