Jacob

@OpenAI your support for open source is incredible. Thank you for giving me another 6 months of Codex as an open-source contributor. Really appreciate it!

PocketTTS now speaks Hebrew 🎉 LoRA fine-tune on IPA phonemes, supports any espeak language. 100% in-browser instant streaming, no GPU. Higher quality than Kokoro, faster than Piper. Built on @kyutai_labs Try it: huggingface.co/spaces/thewh1…

chore check parses the chorefile without running anything and flags every command that won't exist on someone else's machine — with the builtin to swap in. Works for coding agents too: they write curl | tar by reflex, chore check catches it, they fix it themselves from the hint.

Makefiles and npm scripts break the first time someone clones on Windows, so I built chore: a task runner with its own portable shell baked in. Builtins for download, extract, archive, copy, sha256. chore check flags non-portable commands. github.com/getchore/chore 🧵

I wanted this for years, so I finally built it. Like ngrok, but peer-to-peer. punch 3000 Share a local app through a plain browser URL. No server in the middle, no account, no config. The link connects straight to your machine over WebRTC, end-to-end encrypted. punchpage.pages.dev Open source: github.com/thewh1teagle/punc…

Another win for open source! Just got accepted into Anthropic's Claude for Open Source program. Thanks @AnthropicAI for supporting open source maintainers ❤️

I'm fully ready

This led to a follow-up project with a bigger idea: ReNikud. What if Hebrew pronunciation could be learned directly from audio, without manual nikud labels? We run Hebrew ASR + IPA ASR on 1,700 hours of speech, keep only transcripts that agree, and train on 1.5M pseudo-labeled sentences with everyday spoken Hebrew including slang, loanwords, and colloquial forms. 🧵

Does it work? Listen for yourself. הוא רצה את זה, "he wanted it" (ratsa) vs. היא רצה מהר, "she ran fast" (ratsa, different stress). Same letters. Phonikud handles cases that trip up commercial systems, trained with as little as 2 hours of data. 🧵

Phonikud extends a Hebrew diacritizer with lightweight adapters that predict new enhanced marks indicating lexical stress and vocal Shva. The enhanced Nikud then maps directly to full IPA phonemes. Small enough for real-time TTS on edge devices like a Raspberry Pi. 🧵

Hebrew is written without vowels. ספר can be "book" (sefer), "barber" (sapar), or "he counted" (safar). Deep learning diacritizers handle this by restoring vowel marks (nikud). But nikud doesn't mark lexical stress (בוקר: "boker" morning vs. "boker" cowboy) or vocal Shva (בלונדון "belondon" vs. בלונדיני "blondini"). For TTS, that's not enough. 🧵

Our Hebrew G2P, Phonikud, was accepted to Interspeech! 🎉 In Hebrew, בירה can be "beer" ('bira) or "capital" (bi'ra). Same vowel marks, different stress. Even fully vocalized Hebrew underspecifies pronunciation. 🧵