Show HN：Vaghenu，一个考虑音节的梵语诗句到唱诵的 TTS
4 分•作者: init0•3 个月前
一个15年的梦想今天实现了。我攻读博士学位的梦想是创建一个能够完美诵读任何梵语诗句的系统。
现在，我将开源 Vagdhenu，这是一个能够识别韵律的梵语诗句转语音系统。这是世界上第一个能够识别韵律、开源的梵语诵读语音合成系统。我将公开模型权重、训练脚本，甚至是我精心收集的数据——[https://prathosh.in/vagdhenu/](https://prathosh.in/vagdhenu/)
没有大型人工智能实验室。没有庞大的工程团队。没有风险投资规模的预算。只有一个教授的信念，即人类最古老的知识传统之一值得拥有现代、开放的基础设施。
这个名字来源于《奥义书》中的一句话：“Vācaṃ dhenum upāsīta”——就像神话中能满足愿望的母牛一样，Vagdhenu 旨在让世界各地的学生、教师、研究人员和信徒更容易接触到梵语文本。
在这里试用实时演示，并告诉我您的评论——[https://prathosh.in/vagdhenu/](https://prathosh.in/vagdhenu/)
整个系统，从数据收集到模型构建和演示，都由一个人（也就是我）使用我们在 LatentForce 构建的强大工具完成。
我附上了一段系统生成的示例音频文件。
附注：我代表我的朋友发布此信息，他们不在 HN 上。
查看原文
A 15-year-old dream has come true today. I started a PhD with the dream of creating a system that chants any Sanskrit shloka perfectly.<p>And here I am opening sourcing Vaghenu, a meter aware sloka-to-chant, TTS for Sanskrit . This is the world's first vrutta-aware, open-source TTS for Sanskrit Chanting. I am making the model weights, training scripts, and even data (that I meticulously collected) public - <a href="https://prathosh.in/vagdhenu/" rel="nofollow">https://prathosh.in/vagdhenu/</a><p>No large AI lab. No big engineering team. No venture-scale budget. Just a professor's conviction that one of humanity's oldest knowledge traditions deserves modern, open infrastructure.<p>The name comes from the Upanishadic phrase: "Vācaṃ dhenum upāsīta" - Like the mythical wish-fulfilling cow, Vāgdhenu is intended to make Sanskrit texts more accessible to students, teachers, researchers, and devotees everywhere.<p>Test out the live demo here and let me know your comments - <a href="https://prathosh.in/vagdhenu/" rel="nofollow">https://prathosh.in/vagdhenu/</a><p>The entire system, from data collection to model building and demos, is built by a single person (your truly) using the powerful harness that we are building at LatentForce.<p>I have attached a sample audio file generated by the system.<p>P.S: Posting on behalf of my friend, their aren't on HN.