Fact · Speech recognition
74open-source models
As of 27 March 2026, the Open ASR Leaderboard listed 86 speech recognition models, and 74 of them were open-source.
Checked against its source on October 17, 2026
In the source's own words
“Of the 86 models currently listed in the ASR Leaderboard (as of 27 March 2026), 74 are open-source”
Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation, Hugging Face and collaborators, arXiv, 2025, Section 2.4, Current models.
Open the original- What it measures
- The paper's authors counted the models on the leaderboard on that date, from 26 organizations.
- What it does not show
- A dated snapshot. The live leaderboard adds models over time, so the count will have changed since March 2026.