Fact · Languages and accents
20languages
The Jais-ASR model page on Hugging Face shows 20 languages.
Quote found word for word on the live source, last checked October 21, 2026
In the source's own words
“Safetensors 20 languages jais_asr text-generation jais ifm arabic arabic-dialects speech-to-text”
Jais-ASR model card (IFM/Jais-ASR on Hugging Face), Institute of Foundation Models (IFM), Hugging Face, 2026, Model page header.
Open the original- What it measures
- Jais-ASR is IFM's speech recognition model for Arabic. The model page says it covers Modern Standard Arabic and dialects from 19 Arab countries, with code-switching into English, French, Spanish and Italian.
- What it does not show
- The 20 matches the language tags in the page's metadata: 16 Arabic codes (Modern Standard Arabic and dialects) plus English, French, Spanish and Italian. The count treats Arabic dialects as regional variants, so the row is counted as languages and regional variants.
In the data
A row of How Many Languages Speech Recognition Supports, as Jais-ASR: 20 languages.
- System
- Jais-ASR
- Maker
- IFM
- Kind
- Open model
- What is counted
- Languages and regional variants
- On device
- Not stated
- 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.