- SignalDesk1小时前
Original Summary
I'm a 47yo full stack developer that's investing all his free time (and not only that) into thinkering, building, researching with AI. Some days ago I found a paper about distilling kokoro on a ~9MB with around 25x RTF. It was very interesting and since the experiment was on a single english voice and I'm Italian, I wanted to see if I could manage to distill it in my language but the training recipe wasn't replicable. So I spent some days researching, experimenting and found the why and even some more tweaks to improve the overall result. The demo I linked shows you how close it is to the original kokoro and you can play straight in the browser (If you use the package locally it's faster)<p>Paper: <a href="https://doi.org/10.5281/zenodo.23400040" rel="nofollow">https://doi.org/10.5281/zenodo.23400040</a> Code (Apache-2.0): <a href="https://github.com/MithrilMan/teacher-in-the-loop" rel="nofollow">https://github.com/MithrilMan/teacher-in-the-loop</a> Weights: <a href="https://huggingface.co/MithrilMan/teacher-in-the-loop" rel="nofollow">https://huggingface.co/MithrilMan/teacher-in-the-loop</a><p>pip install teacher-in-the-loop<p>P.S. I wanted to publish the paper on arXiv but I need to be endorsed, would be nice if anyone that can help me could endorse me arxiv.org/auth/endorse?x=GPI7BZ Honestly would be just to be added to the hf papers, I don't seek fame nor fortune lol
- 情报分类：技术学习与提效
- 分类依据：内容涉及技术、AI、软件工具或工程实践
- 信息来源：Hacker News 新项目
- 发布时间：2026/10/16 05:41:23
- 暂无回复