Fact · Languages and accents
7languages
The Whistle model page on Hugging Face shows 7 languages, and its model card names them: English, German, French, Spanish, Italian, Dutch and Polish.
Quote found word for word on the live source, last checked October 20, 2026
In the source's own words
“Automatic Speech Recognition 7 languages cactus-needle whistle speech-recognition speech-to-text”
Cactus-Compute/whistle (model card, Hugging Face), Cactus Compute, Inc., Hugging Face, 2026, Model page header, next to Automatic Speech Recognition.
Open the original- What it measures
- Whistle is an open speech recognition model that Cactus Compute publishes on Hugging Face. The model card's transcription line reads: 16 kHz mono audio of any length, one pass up to 30 seconds and windowed beyond it, in English, German, French, Spanish, Italian, Dutch and Polish. The same card says that all three of Whistle's jobs run on the device.
- What it does not show
- The count covers the languages the maker lists for transcription. The card does not give accuracy per language in this sentence, and it does not say the model recognizes other languages.
In the data
A row of How Many Languages Speech Recognition Supports, as Cactus Whistle: 7 languages.
- System
- Cactus Whistle
- Maker
- Cactus Compute
- Kind
- Open model
- What is counted
- Languages
- On device
- Yes
- As of
- 2026-10
- Note
- The page header reads 7 languages and the model card names seven languages in its transcription sentence. The card says all three of Whistle's jobs run on the device.
Source
Used to calculate
- In the languages supported by speech recognition systems dataset, the 43 published figures for “Open model” have a median of 25 languages, ranging from 1 to 1,600.
- The languages supported by speech recognition systems dataset holds 185 data points, each a published figure traced to its source.
- The languages supported by speech recognition systems dataset draws on 153 distinct sources.