Hacker News14h ago610 points135 commentslive
Whistle: Speech to Text in 16.9 MB
Whistle is a 16.9 MB speech recognition model that runs on CPU with no dependencies, transcribes 7 languages in 11ms, and integrates with Needle for device-side tool calls.
Read the full story atcactuscompute.comWhy this is in the Signal
LAXIMA AI Signal curates the highest-velocity stories across Hacker News, GitHub trending, and new Hugging Face / Replicate model releases — quality-filtered, deduplicated, and refreshed every four hours. This item surfaced from Hacker News with 610 points (by gmays). We link straight to the original source above — see the full live feed.
More AI Signal briefs
- HNTheranos.world
- HNWhat should we tell our students?
- HNADHD as a circadian rhythm disorder: evidence and implications for chronotherapy (2025)
- HN4-hour battery storage is cheaper to install than gas turbines all across globe
- HNOpenAI annualised revenues $20B less than previously signalled
- HNOpenAI Withdraws 3 Math Papers
- HNI gave Opus 5.5 one prompt and six hours to visualize Invisible Cities
- HNShow HN: I've been paying for a rural Tanzanian's education for 10 years