third-intelligence/Haas-ja-v1.0
just landed · new, unvettedmodel
New, unvetted: created or first seen in the last few days, not from a trusted org and not past the signal threshold yet.
Haas-ja-v1.0 is a Japanese speech recognition model built to be both fast and accurate. License: apache-2.0. Vendor-reported: "It is competitive with commercial APIs: on par with GPT-Transcribe (6.07%), while MAI-Transcribe 2, Scribe v2 and Gemini 3.1 Pro remain more accurate."
- Vendor-reported: It is competitive with commercial APIs: on par with GPT-Transcribe (6.07%), while MAI-Transcribe 2, Scribe v2 and Gemini 3.1 Pro remain more accurate.
- Org
- third-intelligence
- Released
- 2026-10-08
- Status
- just landed · new, unvetted
- License
- apache-2.0 (permissive)
- Task
- automatic-speech-recognition · audio
- Signal
- 11 HF likes · 136 downloads
Links
First published here 2026-10-08 · updated 2026-10-30 · markdown · JSON