Owsm CTC v4 1B
ESPnet · released Jan 16, 2025 · espnet/owsm_ctc_v4_1B
Speech to textTranscribes a recording into words
- Type
- Open weightsCreative Commons Attribution 4.0
- Languages
- 75
- Size
- 1B
Context measured in tokens
Our take
Written Aug 2, 2026Owsm CTC v4 is a one-billion-parameter speech-to-text model from the ESPnet project that turns audio into written words across 75 languages. It is extremely fast on benchmark hardware and accurate on clean recordings, though its error rate rises sharply on accented speech and meetings.
Choose this for batch transcription of clean, prepared audio where throughput matters most — financial calls and read-aloud speech are its strong suits. It also suits multilingual projects needing 75 languages, provided you can verify quality in English. Skip it if you need hosted inference, are transcribing accented speakers or recorded meetings, or require benchmarked accuracy in languages other than English.
The case for it
- Processes an hour of audio in roughly five seconds on the benchmark hardware we track.
- Strong on clean, structured audio: about one word in fifty wrong on read-aloud speech, and similar on financial calls.
- 75 languages supported, far more than most transcription models.
- Creative Commons Attribution 4.0 licence allows commercial use with attribution.
The case against it
- Accuracy collapses on challenging audio: more than six times the error rate on accented speech compared with clean read speech, and nearly five times higher on recorded meetings than on financial calls.
- No hosted inference options in our catalogue; you must self-host.
- Release date is unverified in our data.
How good is it?
TranscriptionTurning speech into text2 of 5Open ASR WER · 57th of 74
93.3%
Misses roughly one word in 15, averaged over nine English test sets.
765×31st of 62
an hour of audio in 5 seconds, on the board's own hardware. Your machine will differ.
75
Stated by the leaderboard; we do not hold the list itself.
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 v4 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_v4_1B
- Modality record
- audio->text
- Catalogue slug
- espnet-owsm-ctc-v4-1b