bosonai / higgs-audio-v3-stt
Audio2.7B3.1K43Updated Jun 12, 2026
Downloads
3.1K
Likes
43
Last updated
Jun 12, 2026
License
apache-2.0
A speech-to-text model combining a Whisper-Large-v3 encoder with a Qwen3 decoder (2.68B total parameters).
Tasks & library
- automatic speech recognition
Tags
- higgs_audio_3
- hf-asr-leaderboard
- whisper
- qwen
- custom_code
- en
Technical specifications
Parameters2.7B
LibraryNot available
Languagesen
Licenseapache-2.0