All tasks / Models
MOSS-Transcribe-Diarize
Open-weights speech recognition model that transcribes and attributes speakers in one pass.
- OpenMOSS (Fudan University / MOSI)
- Open weights
- Released 19 May 2026
Where it ranks
- ATranscriptionModels · Local · 6.2% on Hugging Face Open ASR Leaderboard (English, short-form average WER) (secondary benchmark)
Facts
- Vendor
- OpenMOSS (Fudan University / MOSI)
- Family
- MOSS-Transcribe-Diarize
- Released
- 19 May 2026
- Weights
- Open: download and run it yourself
- License
- Apache-2.0
- Parameters
- 0.91B
- GPU memory to run locally
- ~2 GB (Derived: about 0.91B parameters is roughly 1.8 GB of bf16 weights plus runtime overhead; not an official requirement.)
- Access
- Free (open weights)
- Last verified
- 19 Oct 2026
Benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| Hugging Face Open ASR Leaderboard (English, short-form average WER) | 6.2% | OpenMOSS-Team/MOSS-Transcribe-DiarizeAverage WER over the board's default datasets (English short-form, version 17-10-2026); rank 27 of 56; read from the Space's /config table data. | 17 Oct 2026 | huggingface.co |
Where you can use it
No tracked tool lists this model yet; as open weights it runs in local runtimes.