Canary 1b Flash
NVIDIA · released Mar 7, 2025 · nvidia/canary-1b-flash
Speech to textTranscribes a recording into words
- Type
- Open weightsCreative Commons Attribution 4.0
- Languages
- 4
- Size
- 0.8B
Context measured in tokens
Our take
Written Sep 4, 2026Canary 1b Flash is a compact speech-to-text model from NVIDIA that turns audio into written words. It is built for speed and handles everyday internet audio and meeting recordings more accurately than most alternatives, though it falls behind on heavily accented speech.
Pick this for fast transcription at scale — it processes an hour of audio in about two seconds on benchmark hardware. Use it for meeting-room recordings and podcast or video transcription where it scores better than most models, or for edge deployment under a permissive attribution licence. Skip it if you need heavily accented speech recognition, hosted inference without self-hosting, or verified accuracy in German, Spanish or French.
The case for it
- Extremely fast: 2,126 times real time on the benchmark hardware used.
- Better than most on podcasts and video, at 8.19% word error rate against a field median of 8.2%.
- Among the more accurate options for meeting-room recordings, at 10.58% word error rate against a median of 10.6%.
- Creative Commons Attribution 4.0 licence allows commercial use with credit.
The case against it
- Worse than most on heavily accented speech: 12.03% word error rate, 1.23 percentage points above the median.
- No hosted inference options currently listed; you must run it yourself.
- Every accuracy figure is English; nothing we hold verifies German, Spanish or French.
How good is it?
TranscriptionTurning speech into text3.5 of 5Open ASR WER · 31st of 76
95.1%
Misses roughly one word in 21, averaged over nine English test sets.
2,129×25th of 74
an hour of audio in 2 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. 21.1 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. 22.3 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. 4.3 GB spare means a 10% error in the size would not change the answer.
These cards answer whether Canary 1b Flash 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 Flash
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
- nvidia/canary-1b-flash
- Architecture
- Dense
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- nvidia-canary-1b-flash