TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Demucs Music Source Separation

4 点作者 tomduncalf将近 3 年前

1 comment

tomduncalf将近 3 年前
This is an AI&#x2F;ML system by Meta which can separate recorded music into four “stems” - drums, bass, vocals and other. It’s not the first one (Deezer open sourced Spleeter a few years back which is now widely used) but I think the results from Demucs are super impressive - it sounds much “crisper” than previous systems. Kind of blows my mind that this is possible!<p>On my M1 Max it runs at 5-10x real-time if you pass a “-j 10” argument (and makes it real hot, lol) so it’s fast enough to be usable. You can also try it out online e.g. here: <a href="https:&#x2F;&#x2F;huggingface.co&#x2F;spaces&#x2F;akhaliq&#x2F;demucs" rel="nofollow">https:&#x2F;&#x2F;huggingface.co&#x2F;spaces&#x2F;akhaliq&#x2F;demucs</a><p>I thought I’d share this as in the Kate Bush thread someone was talking about being able to get acapellas for tracks.