Owsm CTC v3.1 1B
ESPnet · released Feb 23, 2024 · espnet/owsm_ctc_v3.1_1B
Speech to textTranscribes a recording into words
- Type
- Open weightsCreative Commons Attribution 4.0
- Size
- 1.1B
Context measured in tokens
Our take
Written Sep 11, 2026Owsm CTC v3.1 is a 1.1-billion-parameter speech-to-text model from ESPnet with a Creative Commons licence. It processes audio at extreme speed — roughly an hour in four seconds on benchmark hardware — but its accuracy sits below the middle of the field on every English condition measured.
Pick this for batch transcription jobs where speed matters far more than accuracy and a human will review the output. Use it for research or prototyping with a fully open, attribution-licensed backbone, or for offline processing on very constrained hardware where larger models will not fit. Skip it if you need competitive accuracy on any audio condition, measured support beyond English, or a hosted provider to run it for you.
The case for it
- Processes audio at 816× real time on the benchmark harness — an hour of audio in roughly four seconds.
- Creative Commons Attribution 4.0 licence allows commercial use with credit and no API lock-in.
- 1.1 billion parameters, small enough to deploy where memory is severely constrained.
The case against it
- Below-median accuracy on every measured English condition: clean read speech, podcasts and video, and recorded meetings all score worse than most of 78 models.
- No measured language support beyond English; no language list held.
- No commercial hosting available; you must run it yourself.
How good is it?
An open speech-to-text model for turning recordings into written text, though podcast and read-aloud audio come out less clean than most.
- transcribing podcasts and video audioPodcasts and video · 79th of 92
- transcribing clear recordings of people reading aloudClean read speech · 72nd of 92
TranscriptionTurning speech into text
816×36th of 74
an hour of audio in 4 seconds, on the board's own hardware. Your machine will differ.
Percentage of words wrong on each set, lower better. Bars are scaled to this model's own worst case; the placing beneath each rate is against every model measured on that set.
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.
Each of these is the same transcription job on a different kind of recording, so together they say where it holds up and where it slips — not how closely it follows an instruction.
Every published score for this model7 scoresEvery figure we hold, from 7 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 20.9 GB spare means a 10% error in the size would not change the answer.
Apple M1 Pro (16-core GPU) · 32 GB
Room to spare. 22.1 GB spare means a 10% error in the size would not change the answer.
Apple M2 (8-core GPU, 8GB unified) · 8 GB
Room to spare. 4.1 GB spare means a 10% error in the size would not change the answer.
These cards answer whether Owsm CTC v3.1 1B loads, not how fast it transcribes. Throughput figures for a transcription model come from its text decoder, so treat this as a fit answer rather than a speed one.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first. This is a fit answer: whether it loads, not how fast it transcribes.
Models people weigh against Owsm CTC v3.1 1B
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
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.
Licence and identifiers
What the licence allowsCreative Commons Attribution 4.0, 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
Creative Commons Attribution 4.0
Permissive content license: any use with attribution. Common for datasets and some model weights.
Identifiers
- Hugging Face
- espnet/owsm_ctc_v3.1_1B
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- espnet-owsm-ctc-v3-1-1b