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。

Show HN: The Horde – Music Groovebox and Remixer

24 点作者 raver1975超过 4 年前

1 comment

lioeters超过 4 年前
That&#x27;s impressive! The video got my attention immediately:<p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=FjkpVbbDtMY" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=FjkpVbbDtMY</a><p>&gt; Grab a track from spotify, split into stem files, and then chop it up.<p>I&#x27;m guessing the &quot;AI&quot; plays a role in determining the tempo, vocal&#x2F;instrument layers, where to chop up the beats.<p>The first few minutes of the video demonstrates how practical the application is, to drag a file&#x2F;URL(?) in and start looping, mixing and matching.<p>It reminds me a bit of Ableton, with their automatic detection and marking of &quot;beats&quot; (amplitude peaks?).<p>I&#x27;d be curious to learn more about the technical aspects. For example, the readme says both Java and Python are required - but I didn&#x27;t see any Python code in there. I suppose it&#x27;s bundling an external library, probably for machine learning. I do see Java functions for training models - I wonder what datasets were used, what musical asepcts the pattern recognition works on.<p>The feature set is extensive, with synthesizers (like TB-303&#x2F;808&#x2F;909), sampler, live sessions, record&#x2F;export - I can see it&#x27;s a long-term project built up over years. Nice work!