Canary 1b v2
NVIDIA · released Aug 4, 2025 · nvidia/canary-1b-v2
Speech to textTranscribes a recording into words
- Type
- Open weightsCreative Commons Attribution 4.0
- Languages
- 25
- Size
- 1B
Context measured in tokens
Our take
Written Aug 2, 2026Canary 1b v2 is a small downloadable speech-to-text model from NVIDIA that turns audio into written text. It is extremely fast and accurate on clean read-aloud audio, but its accuracy drops sharply in noisy or conversational settings.
Pick this for high-throughput transcription of clean, scripted audio where a 1.76% word error rate is acceptable. Use it for batch processing at extreme speed, or for multilingual pipelines across 25 languages where you can verify quality yourself. Skip it if you need to transcribe meetings, accented speech, or podcasts and video, where its error rate rises several-fold; or if you need a hosted service rather than self-hosting.
The case for it
- Extremely fast: processes one hour of audio in approximately two seconds on benchmark hardware.
- Excellent on clean read-aloud audio, with a word error rate roughly a quarter of its own overall average.
- Strong on financial calls specifically, with a word error rate well under its own average.
- Permissive Creative Commons Attribution 4.0 licence allows commercial use with attribution.
The case against it
- Accuracy collapses in recorded meetings, with a word error rate more than seven times worse than its clean read-aloud score.
- Podcast and video quality is mediocre, with a word error rate more than five times worse than clean read-aloud.
- No commercial hosting available; users must self-host.
How good is it?
TranscriptionTurning speech into text2.5 of 5Open ASR WER · 51st of 74
93.6%
Misses roughly one word in 16, averaged over nine English test sets.
1,821×21st of 62
an hour of audio in 2 seconds, on the board's own hardware. Your machine will differ.
25
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 ↓ ↑
Bulgarian · Croatian · Czech · Danish · Dutch · English · Estonian · Finnish · French · German · Greek · Hungarian · Italian · Latvian · Lithuanian · Maltese · Polish · Portuguese · Romanian · Slovak · Slovenian · Spanish · Swedish · Russian · Ukrainian
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 v2
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
- nvidia/canary-1b-v2
- Modality record
- audio->text
- Catalogue slug
- nvidia-canary-1b-v2