Hacker News new | ask | show | jobs
by bevenky 1240 days ago
Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch.

https://github.com/lucidrains/musiclm-pytorch/blob/main/musi...
1 comments
swyx 1240 days ago
pardon my ignorance - what exactly is involved in reimplementing these models?

i assume there's only a superficial description of the architecture, and no weights to load in, so you'll have to train everything from scratch? do we even have their dataset?

link
f_devd 1239 days ago
Generally it's without weights, but MusicLM is also a WIP. More mature implementations have descriptions on how to train them and follow ups on small scale/crowd-sourced experiments & research[1].

[1]: https://github.com/lucidrains/denoising-diffusion-pytorch

link