Re:MusicLM: Generating music from text
by andreyk on Friday January 27, 2023 @01:36AM
(#34543283)
FYI, they don't actually train end-to-end, they have three separate models that are each trained via self-supervised learning independently (I think, I haven't read the paper very carefully).
[ Parent
| on HN ]
There are no comments on this comment yet.