Open y-71 opened 1 year ago
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!
@y-71 check AudioGen paper.
You might want to check this as well https://github.com/zhvng/open-musiclm
audiolm added the encodec weights to audiolm
❓ 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!