Fact · Languages and accents
19languages
AutoArk's open-audio-opd repository lists 19 languages for its ARK-ASR-0.6B speech recognition checkpoint, from Chinese and English to Lithuanian.
Quote found word for word on the live source, last checked October 21, 2026
In the source's own words
“Task Autoregressive ASR Languages Chinese, English, German, Japanese, French, Korean, Spanish, Polish, Italian, Romanian, Hungarian, Czech, Dutch, Finnish, Croatian, Slovak, Slovene, Estonian, Lithuanian”
open-audio-opd: Audio OPD training and ARK-ASR inference (README), AutoArk, GitHub, AutoArk repository, 2026, Model Release table.
Open the original- What it measures
- The Model Release table of the repository's README lists the checkpoint AutoArk-AI/ARK-ASR-0.6B with its task and its languages. The table is the only model release it lists.
- What it does not show
- The list names languages, not regional variants, and the README does not say how the model was tested on each language or how well it performs on each.
In the data
A row of How Many Languages Speech Recognition Supports, as ARK-ASR-0.6B (AutoArk): 19 languages.
- System
- ARK-ASR-0.6B
- Maker
- AutoArk
- Kind
- Open model
- What is counted
- Languages
- As of
- 2026-10
- Note
- Counted the 19 language names in the quoted list.
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.