# Whistle, a 16.9MB on-device speech-to-text model, released

- Link: https://cactuscompute.com/blog/whistle
- Discussion: https://startupxo.com/en/887/
- Posted by startupxo at 2026-10-08T18:37:15.851Z
- 0 points, 0 comments, kind story, origin curated
- Written in ko, machine translated to en

## Summary

- Whistle is a model that converts speech into text, and according to the developer Cactus, a single file is 16.9MB. The source says it runs on a CPU without separate dependencies.
- It supports 7 languages, including English, German, French, Spanish, Italian, Dutch, and Polish, and can process up to 30 seconds at a time. If no language is specified, it detects the language automatically.
- It provides start and end times and a probability for each word. Passing expressions such as names through keywords is said to raise the chance that those expressions are selected during search.
- The performance figures are results measured by the developer. On an Apple M4 Pro CPU, with 10 seconds of audio and a beam size of 5, the first token time was 11.1ms, and under the same conditions Whisper base was compared at 73.2ms.
- Accuracy varies by benchmark. The source states that Whistle leads on the averages for LibriSpeech, SPGISpeech, Earnings-22, and FLEURS, while Whisper base leads on the averages for TED-LIUM, AMI, and MLS.

## Sources

- Hacker News: https://news.ycombinator.com/item?id=50008427 (631 points, 136 comments, checked 2026-10-09T04:36:57Z)

## Comments (0)

No comments yet.

JSON: https://startupxo.com/api/v1/item.json?id=887&lang=en
