Models / OpenMOSS/ MOSS Transcribe Diarize

MOSS Transcribe Diarize

OpenMOSS · released May 19, 2026 · OpenMOSS-Team/MOSS-Transcribe-Diarize

Speech to textTranscribes a recording into words

Input: audio. Output: text.InputOutput
Type
Open weightsApache License 2.0
Languages
2
Size
0.9B

Context measured in tokens

Our take

Written Aug 2, 2026

MOSS Transcribe Diarize is a sub-1-billion-parameter speech-to-text model from OpenMOSS that identifies who is speaking while it transcribes. It processes audio extremely fast under a permissive Apache licence, but you must run it yourself and it only supports English and Chinese.

Who should pick it

Pick this when you need speaker diarization built into transcription, or when permissive open-source licensing matters for compliance. Use it for throughput-heavy pipelines where speed beats perfection — it processes an hour of audio in roughly nine seconds. Skip it if you need commercial hosting, languages beyond English and Chinese, or consistently high accuracy on messy audio like meetings and accented speech.

The case for it

  • Extremely fast: processes one hour of audio in approximately nine seconds at 382.37 times real time.
  • Permissive Apache 2.0 licence allows commercial use, modification and redistribution.
  • Strong on clean prepared speech, with low error rates on read-aloud audio and financial calls.
  • Handles European-accented speech notably better than general accented speech.

The case against it

  • Accuracy degrades sharply in challenging conditions: error rate climbs roughly fivefold on recorded meetings and general accented speech versus clean speech.
  • No commercial hosting available in our data; you must self-host.
  • Only two languages listed, and every accuracy figure we hold is English-only — nothing measured for Chinese or any other language.
00

How good is it?

TranscriptionTurning speech into text4 of 5Open ASR WER · 20th of 74

Words it gets right

94.8%

Misses roughly one word in 19, averaged over nine English test sets.

How fast it listens

382×44th of 62

an hour of audio in 9 seconds, on the board's own hardware. Your machine will differ.

Languages

2

Listed on the model card. The accuracy above is English only.

Where it struggles
Read aloudaudiobooks, clean recording1.7%
Podcasts and videoeveryday internet audio7.7%
Accented speechspeakers from many countries9%
Meetingsa room, several people, far microphone8.3%

Percentage of words wrong on each set, lower better. Bars are scaled to this model's own worst case, not to the board.

Which languages

English · Chinese

The figures above come from the Open ASR Leaderboard, an independent public test that runs every model on the same recordings. It is the only measurement of transcription quality we know of, so there are no other scores to show.

Also scored, on boards we give no mark for
Financial calls 5th of 74Accented speech 15th of 74Podcasts and video 19th of 74Recorded meetings 21st of 74European-accented speech 32nd of 74Clean read speech 49th of 74Harder read speech 54th of 74

These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.

Every published score for this model9 scoresEvery figure we hold, from 9 boards, with who ran it and a link to the source — including the boards no rating above is built on.
382.4independentsource ↗
5.2independentsource ↗
9independentsource ↗
1.7independentsource ↗
8.3independentsource ↗
7.7independentsource ↗
1.7independentsource ↗
4.1independentsource ↗
01

Can you run it yourself?

Fits in memory
weights load entirely on the card
Spills to system RAM
some weights offload; much slower
Too large
will not load even with offload
est
size is calculated; the verdict could change by 10%

Comfortable fit

A card many people ownFits in memory

GeForce RTX 4090 · 24 GB

Weights at Q4_K_M0.6 / 24 GBest
Spare memory20.8 GB spare
Usable context131Kwhat the spare memory holds; no published limit on record
Decode speed1478 tok/sest

Room to spare. 20.8 GB spare means a 10% error in the size would not change the answer.

One step upFits in memory

Apple M1 Pro (16-core GPU) · 32 GB

Weights at Q4_K_M0.6 / 32 GBest
Spare memory22 GB spare
Usable context131Kwhat the spare memory holds; no published limit on record
Decode speed257 tok/sest

Room to spare. 22 GB spare means a 10% error in the size would not change the answer.

On a MacFits in memory

Apple M2 (8-core GPU, 8GB unified) · 8 GB

Weights at Q4_K_M0.6 / 8 GBest
Spare memory4 GB spare
Usable context33Kwhat the spare memory holds; no published limit on record
Decode speed128 tok/sest

Room to spare. 4 GB spare means a 10% error in the size would not change the answer.

Your hardware
Checking your profile…

Memory use by level

Against a 24 GB card.

Q4_K_M
recommended
0.6 GBest
Fits in memory
Q5_K_M
0.7 GBest
Fits in memory
Q8_0
1 GBest
Fits in memory

All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.

Check against your own machine → · All 71 devices, with every size →

02

When we formed this view

Dates behind this page

Aug 2, 2026BenchmarkScored 9 on Accented speechleaderboard
Aug 2, 2026BenchmarkScored 1.7 on Financial callsleaderboard
Aug 2, 2026BenchmarkScored 8.3 on Recorded meetingsleaderboard
Aug 2, 2026BenchmarkScored 3.6 on European-accented speechleaderboard
Aug 2, 2026BenchmarkScored 7.7 on Podcasts and videoleaderboard
Aug 2, 2026BenchmarkScored 1.7 on Clean read speechleaderboard
Aug 2, 2026BenchmarkScored 4.1 on Harder read speechleaderboard
Aug 1, 2026ListedListed on LLMapfirst indexed by our pipeline
Aug 1, 2026BenchmarkScored 382.4 on Open ASR RTFxleaderboard
Aug 1, 2026BenchmarkScored 5.2 on Open ASR WERleaderboard

Prices last checked 6h ago

What we do not know about this model yet

  • We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
  • Nothing we hold says whether an endpoint streams, so we do not show it either way.
03

Licence and identifiers

What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.

Licence

Apache License 2.0

permissiveCommercial use allowed

Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.

Identifiers

Architecture
Dense
Modality record
audio->text
Catalogue slug
openmoss-team-moss-transcribe-diarize

Machine-readable model card (omc.json) →

Something wrong on this page? Tell us