{"id":887,"kind":"story","title":"Whistle, a 16.9MB on-device speech-to-text model, released","url":"https://cactuscompute.com/blog/whistle","host":"cactuscompute.com","by":"startupxo","score":0,"comments":0,"time":"2026-10-08T18:37:15.851Z","origin":"curated","language":{"source":"ko","reading":"en","translated":true},"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."],"discussion":"https://startupxo.com/en/887/","markdown":"https://startupxo.com/en/887.md","api":"https://startupxo.com/api/v1/item.json?id=887&lang=en","text":null,"edited":null,"sources":[{"site":"hn","name":"Hacker News","url":"https://news.ycombinator.com/item?id=50008427","score":631,"comments":136,"observed_at":"2026-10-09T04:36:57Z"}],"thread":[]}