Original Summary

TLDR: I’m building Earshot - the sound detection app that can detect (ideally) any sound described by text.<p>The neural model under the hood is a CLAP-style model (CLIP for audio): basically during the training you force the model make inner text and audio representations to match. And then you can use such model as 0-shot audio classifier. For POC I used LAION’s clap-htsat model but it turned out to be quite &quot;heavy&quot; so I’ve trained a smaller one by myself.<p>As for text encoder I used model from the EfficientAT family; for audio I used jhu-clsp&#x2F;ettin-encoder-32m. The training was performed on my mighty 2x1080 Ti home server. The trained weights can be found on my HF: <a href="https:&#x2F;&#x2F;huggingface.co&#x2F;mirth&#x2F;earshot-clap-mn10-ettin32" rel="nofollow">https:&#x2F;&#x2F;huggingface.co&#x2F;mirth&#x2F;earshot-clap-mn10-ettin32</a><p>I would appreciate it if you could test this application (especially if you could report if an app missed the sound).<p>A couple of disclaimers:<p>1. The sound never leaves you device.<p>2. It can miss the sound so it’s not a replacement for your monitoring system (but an extra pair of ears).<p>3. I’m aware that similar functionality is presented in the Apple HomePod but there is a minor difference: to add very custom sound for detection on HomePod you need first to record it (to train inner HomePod model I presume). In my case you can just describe the sound in the text format.<p>Happy to answer any questions!

  • 情报分类：工作与职业机会
  • 分类依据：内容涉及招聘、求职或职业发展
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/10/15 23:18:18