Re:Show HN: Muesli – If Granola and Wisprflow had an open so...
by rpdaiml on Monday May 04, 2026 @03:56PM
(#48014097)
How are you handling the on device speech pipeline, especially around model size, latency, and accuracy tradeoffs on consumer hardware?
[ Parent
| on HN ]
Re:Show HN: Muesli – If Granola and Wisprflow had an open so...
by pHequals7 on Monday May 04, 2026 @11:58PM
(#48017888)
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!