Fact · Languages and accents
28languages
OpenWhisper's README says its Nemotron 3.5 ASR 0.6B streaming model supports 28 languages, plus automatic detection.
Quote found word for word on the live source, last checked October 22, 2026
In the source's own words
“Model Mode Languages in OpenWhisper ... Nemotron 3.5 ASR 0.6B Streaming 28 languages, plus automatic detection”
OpenWhisper README on GitHub, OpenWhisper, GitHub, richardwu/openwhisper repository, n.d., Models table, Languages in OpenWhisper column.
Open the original- What it measures
- The Models table lists this model as streaming, so it shows live text previews while you speak. The model file is 496 MB.
- What it does not show
- This is the number of languages the app offers for this model, as the maker states it. The README's 'plus automatic detection' is not part of the number.
In the data
A row of How Many Languages Speech Recognition Supports, as OpenWhisper: Nemotron 3.5 ASR: 28 languages.
- System
- OpenWhisper (Nemotron 3.5 ASR)
- Maker
- OpenWhisper
- Kind
- Dictation app
- What is counted
- Languages
- As of
- 2026-10
- Note
- The number is stated in the quote
Source
Used to calculate
- In the languages supported by speech recognition systems dataset, the 120 published figures for “Dictation app” have a median of 50 languages, ranging from 1 to 1,600.
- 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.