← Friday, October 9, 2026InferenceTool

Whistle runs speech recognition on-device in a 16.9 MB model

cactuscompute.com 5 min read Editor score 7/10

Whistle is a 16.9 MB speech model that runs on CPU without dependencies, with transcription, word timestamps and speech embeddings across seven languages. Its compact local runtime is relevant to teams deploying speech features on constrained devices.

What: Whistle is a 16.9 MB speech-recognition model for mobile and embedded devices that runs on a CPU with no dependencies.
How: Its front end creates log-mel frames for an eight-block encoder; a decoder cross-attends to encoder features for transcription.
Why it matters: On-device processing keeps audio local, while compact CPU deployment fits constrained products such as wearables, robots, and microcontrollers.

Whistle processes audio through its front end and encoder, which supplies features to the decoder. Sketched from the article's own text.

Read on cactuscompute.com → Hacker News · 144 comments

Discussion

Discussion is not switched on yet. Use Note above to keep your own thoughts on this story.

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.