Owsm CTC v3.2 ft 1B
ESPnet · released Sep 24, 2024 · espnet/owsm_ctc_v3.2_ft_1B
Speech to textTranscribes a recording into words
- Type
- Open weightsCreative Commons Attribution 4.0
- Size
- 1B
Context measured in tokens
Our take
Written Sep 5, 2026Owsm CTC v3.2 ft 1B is a one-billion-parameter speech-to-text model from ESPnet that transcribes audio faster than almost anything we track. Its speed comes at an accuracy cost: it sits below the median on every recording type measured.
Pick this when raw transcription speed matters above all else — it processes an hour of audio in roughly five seconds. Use it for offline batch processing of clean, read-aloud audio where a 2.2% word error rate is acceptable, or for research under a permissive attribution licence. Skip it if you need accuracy on podcasts, accented speech or meetings, where its error rate rises well above the median.
The case for it
- Extremely fast: 692 times real time on the leaderboard harness.
- Creative Commons Attribution 4.0 licence allows commercial use with attribution.
- One billion parameters with no mixture-of-experts complexity, making it easy to deploy at the edge.
The case against it
- Below the median on every measured condition: read-aloud, podcasts, accented speech and meetings all trail the pack.
- No language coverage information held; every accuracy figure here is English only.
How good is it?
An open speech-to-text model for turning recordings into written text, though it trails most models on meeting, podcast and read-aloud audio.
- transcribing recordings of meetings in a roomRecorded meetings · 76th of 92
- transcribing podcasts and video audioPodcasts and video · 78th of 92
- transcribing clear recordings of people reading aloudClean read speech · 80th of 92
TranscriptionTurning speech into text
692×42nd of 74
an hour of audio in 5 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 v3.2 ft 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.
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_v3.2_ft_1B
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- espnet-owsm-ctc-v3-2-ft-1b