Edge0 / Audio8-ASR-0.1B
Audio324M29.6K89Updated Jul 15, 2026
Downloads
29.6K
Likes
89
Last updated
Jul 15, 2026
License
cc-by-nc-4.0
Audio8-ASR-0.1B is a compact autoregressive ASR model whose language-model component has only 0.1B parameters. It supports multilingual speech recognition for languages including Chinese, English, French, German, Japanese, Korean, and Cantonese. We position it as one of the sm…
Tasks & library
- automatic speech recognition
- transformers
Tags
- transformers
- arkasr
- text-generation
- speech
- audio
- multilingual
Technical specifications
Parameters324M
Librarytransformers
Languages7 languages
Licensecc-by-nc-4.0