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)

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..

lol pseudoscience as a service ha!

we are in the times of irrational exuberance - rationality will set in soon!

The market can stay irrational longer than you or I can stay solvent.

unfortunately true :(