Edge0 / ARK-ASR-3B
Audio4.1B1.8K113Updated Jun 27, 2026
Downloads
1.8K
Likes
113
Last updated
Jun 27, 2026
License
apache-2.0
TL;DR ARK-ASR-3B is a multilingual automatic speech recognition model. It achieves current state-of-the-art results on the Hugging Face Open ASR Leaderboard English short-form benchmark, with an average WER of 5.04% and RTFx of 490.98 across AMI, Earnings22, GigaSpeech, Libri…
Tasks & library
- automatic speech recognition
- transformers
Tags
- transformers
- arkasr
- text-generation
- speech
- audio
- pytorch
Technical specifications
Parameters4.1B
Librarytransformers
Languages19 languages
Licenseapache-2.0