Whistle: Speech to Text in 16.9 MB
- MB: 5 events in the last 90 days
- Previous: 22 days earlier · WangNet – 1.8 MB, zero-dependency Numberwang adjudication in 11 languages
What happened
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.
Summary assembled by rule from the sources below
Why it's spreading
Sources
Community
- Whistle: Speech to Text in 16.9 MBHacker News