Canary 1b
NVIDIA · nvidia/canary-1b
Speech to textTranscribes a recording into words
- Type
- Open weightsCreative Commons Attribution-NonCommercial 4.0
- Languages
- 4
- Size
- 1B
Context measured in tokens
Our take
Written Aug 2, 2026Canary 1b is NVIDIA's tiny downloadable speech-to-text model that turns audio into written words. It is extremely fast and accurate on clean studio recordings, but its error rate rises nearly tenfold on accented speech or meeting audio, and its licence blocks commercial use.
Pick this for offline batch transcription of clean English audio where speed is the priority, or for research and non-commercial experimentation on small-footprint speech recognition. Consider it if you need German, Spanish, or French support, though accuracy in those languages is unverified in our data. Skip it if you need commercial deployment, hosted inference, or reliable accuracy on messy real-world recordings.
The case for it
- Extremely fast: processes an hour of audio in about five seconds on benchmark hardware.
- Strong on clean read-aloud English, with a word error rate roughly one-tenth of what it manages on accented speech or meeting audio.
- Unusually small for a speech model at 1B parameters, making it feasible for constrained hardware.
- Downloadable weights with redistribution rights under a Creative Commons licence.
The case against it
- Accuracy collapses in messy real-world audio: recorded meetings and accented speech are roughly nine to ten times worse than clean studio conditions.
- Non-commercial licence prohibits commercial deployment; no hosted offers exist, so you must self-host.
- Every accuracy figure we hold is English; German, Spanish, and French are unmeasured in our data.
How good is it?
TranscriptionTurning speech into text3 of 5Open ASR WER · 40th of 74
94.2%
Misses roughly one word in 17, averaged over nine English test sets.
766×30th of 62
an hour of audio in 5 seconds, on the board's own hardware. Your machine will differ.
4
Listed on the model card. The accuracy above is English only.
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 · German · Spanish · French
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 Canary 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-NonCommercial 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-NonCommercial 4.0
Weights are downloadable but commercial use is prohibited. Research and personal use only.
Identifiers
- Hugging Face
- nvidia/canary-1b
- Modality record
- audio->text
- Catalogue slug
- nvidia-canary-1b