VQ-GAN vs. RVQ (soundstream) #55
WinterStraw
started this conversation in
Ideas
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Would people consider using RVQ as a replacement for VQ? It is similar to the structure of audioLM. For example, let the llama model predict shallow RVQ first, then deep RVQ based on shallow RVQ. Finally, passed RVQ to the vocoder to generate the audio.
Beta Was this translation helpful? Give feedback.
All reactions