i reverse engineered wispr flow, then used deepseek to fine-tune LFM3-1.7B. the result…
This is a AI post classified by AGK Intelligence as Voice AI (a tool drop), kept by the AI Radar because it carries real work, not commentary.
i reverse engineered wispr flow, then used deepseek to fine-tune LFM3-1.7B. the result is on par with the wispr flow models you pay for, and it's free, open source and runs entirely on your mac. key-up latency is 65 ms on my m4 max vs ~520 ms for wispr flow on the same clips. a 6 minute yap session pacing around my office still lands in about a quarter second. > rust backend with a native metal engine: each decode step runs as one fused megakernel > a dflash2 speculative drafter is built into the engine, trained on my local 4 x rtx pro 6000 server > parakeet transcribes, LFM3-1.7B refines. b
Posted by Elliot Arledge (44.9k followers) 1 days ago · 2.3k likes · 98.5k views · view the original post on X. Kept by the AI Radar as Voice AI.
More AI work like this
- 今天测试了 Meta 智能眼镜第一人称运动直播， — @coolish
- Two weeks ago, we opened up Phonon: text-to-speech that runs locally. — @GradiumAI
- 先解决 Screen Studio 的第一个痛点，中文语音识别转写不准。 — @vista8
- Group decisions, character conversations, and hands-free computer control. Three ways… — @AgoraIO
- You can now run local transcription models on your @t3dotcodes environments and use it… — @jullerino
- Last night I said #86 was the best rank Grok Bot ever had. — @spcxGOD
- Speech recognition evalualtion must test where voice agents actually work, which is… — @rohanpaul_ai
- this is my favorite kind of hack. someone took an old Echo Dot and made it run Hermes… — @MichaelGannotti
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.5k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:50 UTC. Full method.