Hacker Newsnew | past | comments | ask | show | jobs | submit | hm64's commentslogin

Coqui is great, but in practice, I found Piper easier to set up, train, and deploy as an ONNX file. Big thanks to the Sherpa development team for their helpful resources: https://k2-fsa.github.io/sherpa/onnx/tts/piper.html and to the Rhasspy team for their training guide: https://github.com/rhasspy/piper/blob/master/TRAINING.md.

I also found DEMUCS + Whisper + pydub to be a super helpful combo for creating quality datasets.


> judiciary is independent from government

Correction: The judiciary is independent from the legislative branch of the government, but it functions alongside the executive and legislative branches as part of the Indian government. While the separation of powers is fundamental, it’s important to acknowledge that the existence of this structure doesn’t automatically guarantee impartiality or independence in practice.


My favorite bit is when you connect it to core war. I was just thinking about core war in context of my PL class today. Core war renaissance!


A large number of handwriting synthesis demos are derivations of/inspired by Alex Graves's paper "Generating Sequences With Recurrent Neural Networks". Alex's code is available under GPL-3.0 here, https://sourceforge.net/projects/rnnl/. One could also port the techniques described in the paper, https://arxiv.org/abs/1308.0850 using any modern machine learning framework.


What a coincidence, this is from my University. I just submitted a request to collect it from the library :)


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: