Whistle: Speech to Text in 16.9 MB
An open speech recognition model that runs on the same CPU engine as Needle. It transcribes seven languages, reaches the first token in 11 ms, and loads beside Needle so one binary turns a clip straight into tool calls.
Quick read
Whistle is an open speech recognition model for various devices. Users can transcribe audio in multiple languages quickly and efficiently.
- Transcribe audio in seven languages
- Get word timestamps with probabilities
- Embed audio without decoding a transcript
Reactions
No reactions yet. Record a short about this link and it shows up here, in Reels and in the community feed.
Is cactuscompute.com your site? Sign in to verify it and get a Verified badge, full stats and a link-back badge.
More Tech & AI finds
- WallHop - Replacement for 12ft.iowallhop.io
- Carrier-Explode: Decoding carrier settingscarrierexplode.com
- Beam: Reflection's 501B Open-Weight Modelreflection.ai
- Bot traffic from Yandexradar.cloudflare.com
- The Lightbulb Computerlightbulbcomputer.com
- Shipping JPEG XL in Chromedeveloper.chrome.com
Where people went next
Nobody has added a next stop yet. Be the first.