TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Open source implementation of Google's MusicLM in PyTorch

118 pointsby bevenkyover 2 years ago

8 comments

albertzeyerover 2 years ago
This guy (Phil Wang, <a href="https:&#x2F;&#x2F;github.com&#x2F;lucidrains">https:&#x2F;&#x2F;github.com&#x2F;lucidrains</a>) seems to have the hobby to just implement all models and papers he finds interesting. See his GitHub page. He has 228 repos, and most of them are some implementation of some machine learning paper. Some of those repos are quite popular.
评论 #34593870 未加载
评论 #34594793 未加载
评论 #34594193 未加载
alexmolasover 2 years ago
I don&#x27;t understand how this got so many upvotes. It takes only one minute to read the code and realize that the model is not yet completely implemented. Sometimes I have the feeling that people upvote posts without even reading them...<p>Of course, it&#x27;s good work, and knowing lucidrains trajectory it&#x27;s probably going to be implemented in the following days&#x2F;weeks. But I wonder how many people have at least opened the link before upvoting it.
hall0weenover 2 years ago
This question is a tangent to your work. Having never used music LMs, and only being cursorily aware of them - how do you keep up with the sota in your field?
kavalgover 2 years ago
Google&#x27;s MusicLM sounds plausible, but quite dull and even sometimes irritating to my musician&#x27;s ear.
评论 #34593854 未加载
Lucasoatoover 2 years ago
Does anyone know if these models can output also Midi instead of plain audio?
评论 #34593213 未加载
评论 #34592982 未加载
评论 #34593014 未加载
alephxyzover 2 years ago
Seems to be an early WIP.
评论 #34591142 未加载
henearkrover 2 years ago
Nice work!<p>Won&#x27;t the model training be a lot of cost to bear, though?
bevenkyover 2 years ago
Implementation of MusicLM, Google&#x27;s new SOTA model for music generation using attention networks, in Pytorch.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;lucidrains&#x2F;musiclm-pytorch&#x2F;blob&#x2F;main&#x2F;musiclm.png">https:&#x2F;&#x2F;github.com&#x2F;lucidrains&#x2F;musiclm-pytorch&#x2F;blob&#x2F;main&#x2F;musi...</a>
评论 #34593235 未加载