News for hackers. Stuff that matters.

pHequals7

Currently the on device models such as Parakeet and Whisper are great for English, faster than cloud hosted models a little less accurate - if you switch on the post processing, the ASR output goes through a fine tuned Qwen 3.5 model that improves the accuracy, formatting etc - all of the code is open source feel free to inspect and suggest perf improvements as a PR!
let me know if you face any issues - and always looking for more collaborators!
Github: https://github.com/pHequals7/muesli

Looking to add on device CUA and support more models (MSFT Vibevoice, IBM Granite etc)

Show HN: Muesli – If Granola and Wisprflow had an open source on device baby

https://freedspeech.xyz

Hey folks, I am the developer behind muesli - which is your one stop app for all your speech to text needs, be it voice dictation or meeting transcriptions that runs on device on your Apple Neural Engine using CoreML based STT models (Parakeet, Whisper, Cohere transcribe). Everything is open source and we are at 160 stars - au naturale - would love for folks to use it and contribute further to...

( Read More... | 10 comments | 7 points | on HN )
Interesting work from Proximal - love the focus on out of distribution tasks like git to zig..
thankfully with code and coding agents - the tacit/tribal knowledge always lives via the codebase itself unlike atoms based manufacturing processes..
Re:Aspartame is not that bad? on Friday April 24, 2026 @11:38PM (#47898410)
lol pseudoscience as a service ha!
Re:The Future of Everything Is Lies, I Guess: New Jobs on Friday April 24, 2026 @11:10AM (#47891359)
unfortunately true :(
Re:The Future of Everything Is Lies, I Guess: New Jobs on Wednesday April 15, 2026 @12:05PM (#47781083)
we are in the times of irrational exuberance - rationality will set in soon!