search

facebookresearch / encodec

State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.
MIT License
3.44k stars 306 forks source link

Could this be used for a better quality audiolm #53

Open y-71 opened 1 year ago

y-71 commented 1 year ago

❓ Questions

within the soundstream paper, the google team used the residual vector quantization model to generate music.

I was wondering since the architecture is very similiar if you guys have thought about using it to generate music.

I've tried openai's jukebox and the output is fairly noisy.

Kudos on this great work!

listener17 commented 1 year ago

@y-71 check AudioGen paper.

andryr commented 1 year ago

You might want to check this as well https://github.com/zhvng/open-musiclm

y-71 commented 1 year ago

audiolm added the encodec weights to audiolm