whatmodel.sh / stt / MOSS-Transcribe-Diarize 0.9B

MOSS-Transcribe-Diarize 0.9B

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

MOSS-Transcribe-Diarize 0.9B is an open-weights speech-to-text model from OpenMOSS, released July 2026. Its published size is 0.909B parameters. Licence: apache-2.0.

Catalogue identity notes

OpenMOSS-Team/MOSS-Transcribe-Diarize ('MOSS-Transcribe-Diarize 0.9B is an end-to-end audio understanding model for long-form multi-speaker transcription, diarization, timestamps'; card news '2026-07-09: Released MOSS-Transcribe-Diarize 0.9B'). transcribe.cpp port pins upstream d7231bb (2026-07-09); later commits change README, serving docs and a FlashAttention declaration, not weights per their titles. Repo created 2026-05-19.

Model information sources

Release date ↗ · Parameter count ↗

Hugging Face safetensors metadata total 908,513,280 (current main 704aa4a); transcribe.cpp catalog counts 908,529,760 for the converted port.

53.6±3.5#82 of 162 speech-to-text modelsfrom 3 benchmark results across 1 source

Score within the Open ASR English short-form WER (March 2026) comparison set only.

$ how it compares

The speech-to-text models ranked either side of MOSS-Transcribe-Diarize 0.9B, out of 176 with a score.

#modelscorewhereRAMreleased
91Canary-180M-Flash NVIDIA54±3local~1.4GB2025-03
92Omnilingual ASR CTC 3B Meta54±2local~7.9GB2025-11
93MOSS-Transcribe-Diarize 0.9B OpenMOSS54±4local~1GB2026-07
94GPT-4o Transcribe OpenAI53±1api $0.0060/audio min2025-03
95LiteWhisper large-v3-turbo-acc Efficient-Speech (LiteASR)53±4local~2.1GB2025-02

see all speech-to-text models · find the ones that fit your machine

$ what it's good at

other tests3 not in a task · 95% of its score
testresultvs the others in its rundifficultycountswhy
LibriSpeech test-clean WER2.1% ✎▁···▁▁▂·▄▄██ beats 24/56avg 2.3%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 54%blunt
FLEURS English test WER5.1% ✎▁··▁▁▁▁▁▁▃█▁ beats 23/56avg 5.8%▇▇▇▇▇▇▇▇▇ 21%blunt
FLEURS Mandarin test error rate9.2% ✎▂▂··▂▄▂▂·▆██ beats 10/17avg 12%▇▇▇▇▇▇▇▇ 20%typical

$ where to run it

Other ways to run it

  1. Run it as published · needs ~0.99 GB · from github.com/handy-computer
    git clone https://github.com/handy-computer/transcribe.cpp.git && cd transcribe.cpp && cmake -B build && cmake --build build && hf download handy-computer/MOSS-Transcribe-Diarize-gguf MOSS-Transcribe-Diarize-Q8_0.gguf --local-dir models/moss-transcribe-diarize && build/bin/transcribe-cli --diarize -m models/moss-transcribe-diarize/MOSS-Transcribe-Diarize-Q8_0.gguf audio.wav

Official weights and documentation: huggingface.co/OpenMOSS-Team ↗

$ how the score was worked out · transcribe.cpp model catalog… 95%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports3▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 95%MIT
prior · pull toward the middle▇ 5%
weighted average= 53.6

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json