Fact · Languages and accents
30languages
The speech.cpp model catalog lists 30 languages for the recognition model qwen3-asr-0.6b.
Quote found word for word on the live source, last checked October 22, 2026
In the source's own words
“Name Task Languages ... qwen3-asr-0.6b recognition 30 languages”
speech.cpp: docs/models.md (model catalog, tasks and languages), nyosegawa, GitHub, nyosegawa/speech.cpp, 2026, Model table in docs/models.md, row qwen3-asr-0.6b.
Open the original- What it measures
- speech.cpp is a speech program written in C++. Its model table gives each model's task and languages, and lists qwen3-asr-0.6b for recognition.
- What it does not show
- A declared language count. The table does not report accuracy for each language, and the smaller 0.6B model may differ in accuracy from the 1.7B model.
In the data
A row of How Many Languages Speech Recognition Supports, as speech.cpp qwen3-asr-0.6b: 30 languages.
- System
- speech.cpp: qwen3-asr-0.6b
- Maker
- nyosegawa
- Kind
- Open model
- What is counted
- Languages
- On device
- Yes
- As of
- 2026-10
Source
Used to calculate
- In the languages supported by speech recognition systems dataset, the 69 published figures for “Open model” have a median of 25 languages, ranging from 1 to 1,672.
- The languages supported by speech recognition systems dataset holds 266 data points, each a published figure traced to its source.
- The languages supported by speech recognition systems dataset draws on 221 distinct sources.