Canary 1b
NVIDIA · released Feb 7, 2024 · 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 · download allowed, licence restricts use
Our take
Written Sep 4, 2026Canary 1b is a compact downloadable speech-to-text model from NVIDIA that turns audio into written words. It is extremely fast and accurate on clean recordings, but its performance drops on harder audio and its licence blocks commercial use.
Pick this for fast batch transcription of clean, read-aloud audio where speed matters, or for non-commercial projects needing a lightweight English recogniser you can run yourself. Skip it if you need commercial deployment, accented-speech accuracy, or hosted inference rather than self-hosting.
The case for it
- Processes an hour of audio in about five seconds on standard hardware.
- Gets roughly one word in eighty wrong on clean read-aloud audio, better than most models tracked.
- Compact at 1B parameters, downloadable under an open licence.
The case against it
- Worse than most on podcasts and video, with a higher error rate than the field middle.
- Struggles with meeting audio and accented speech, where the gap to the best models widens further.
- Non-commercial licence prohibits commercial deployment, and no hosted providers are listed.
How good is it?
An open transcription model for turning clear spoken recordings into written text.
- transcribing clear recordings of people reading aloudClean read speech · 22nd of 92
TranscriptionTurning speech into text3.5 of 5Open ASR WER · 34th of 76
95%
Misses roughly one word in 20, averaged over nine English test sets.
767×39th of 74
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; the placing beneath each rate is against every model measured on that set.
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.
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 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?
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 Canary 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 Canary 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-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
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- nvidia-canary-1b