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 Aug 2, 2026Owsm CTC v3.1 is a tiny downloadable speech-to-text model from ESPnet that turns audio into written words at exceptional speed. It carries a permissive attribution-only licence and performs well on clean recordings, though its accuracy falls sharply on messier audio.
Pick this for batch transcription where speed matters most — an hour of audio in roughly four seconds on benchmark hardware. Use it for clean read-aloud or financial calls, or projects needing a licence with no commercial restrictions beyond attribution. Skip it if you are transcribing meetings or accented speech, where errors rise more than sevenfold, or if you need hosted rather than self-hosted inference.
The case for it
- Extremely fast: 816 times real time on benchmark hardware, turning an hour of audio into roughly four seconds of processing.
- Strong on clean, structured audio: 1.9% word error rate on read-aloud speech and 2.64% on financial calls.
- Permissive Creative Commons Attribution 4.0 licence allows commercial use with attribution.
The case against it
- Accuracy collapses on natural, messy audio: 13.35% word error rate in recorded meetings versus 1.9% on clean read-aloud — a gap of more than seven times.
- No hosted access available: zero current offers in our catalogue, so you must self-host.
- Unverified language coverage: all accuracy figures are English only, with no measurements held for other languages.
How good is it?
TranscriptionTurning speech into text1.5 of 5Open ASR WER · 63rd of 74
92.8%
Misses roughly one word in 14, averaged over nine English test sets.
816×27th of 62
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, not to the board.
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.
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.
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
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.
Memory use by level
Against a 24 GB card.
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 →
Models people weigh against Owsm CTC v3.1 1B
When we formed this view
Dates behind this page
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.
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
- Modality record
- audio->text
- Catalogue slug
- espnet-owsm-ctc-v3-1-1b