HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

canary-1b-v2

nvidia/canary-1b-v2

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
nvidia/canary-1b-v2
provider
nvidia
license
cc-by-4.0
language
bg, hr, cs, da, nl, en, et, fi, fr, de, el, hu
context
—
library
nemo
vRAM (GB)
—
size on disk
—
downloads
50,940
likes
404
created
—
last modified
2025-12-03T22:23:42+00:00 (2025)
huggingface
https://huggingface.co/nvidia/canary-1b-v2
tags
nemoautomatic-speech-recognitionautomatic-speech-translationspeechaudioTransformerFastConformerConformerpytorchNeMohf-asr-leaderboardbghrcsdanlenetfifrdeelhuit

Benchmark scores (9)

benchmarkcategoryscorecontextconfevidence
WER AMIspeech-asr16.01low| `Canary-1b-v2` | 749 | 7.15 | 16.01 | 10.82 | 2.18 | 3.56 | 11.79 | 2.28 | 4.29 | 6.25 |
WERspeech-asr13.78low| Earnings-22 | 13.78% |
WER Earnings-22speech-asr13.78Earnings-22medium| Earnings-22 | 13.78% |
WER Earnings-22speech-asr11.79low| `Canary-1b-v2` | 749 | 7.15 | 16.01 | 10.82 | 2.18 | 3.56 | 11.79 | 2.28 | 4.29 | 6.25 |
WER GigaSpeechspeech-asr10.82low| `Canary-1b-v2` | 749 | 7.15 | 16.01 | 10.82 | 2.18 | 3.56 | 11.79 | 2.28 | 4.29 | 6.25 |
WER FLEURSspeech-asr8.4low| **`Canary-1b-v2`** | 8.40% | 8.85% | 7.27% |
WER MLSspeech-asr7.27low| **`Canary-1b-v2`** | 8.40% | 8.85% | 7.27% |
WER VoxPopulispeech-asr6.25low| `Canary-1b-v2` | 749 | 7.15 | 16.01 | 10.82 | 2.18 | 3.56 | 11.79 | 2.28 | 4.29 | 6.25 |
WER TED-LIUMspeech-asr4.29low| `Canary-1b-v2` | 749 | 7.15 | 16.01 | 10.82 | 2.18 | 3.56 | 11.79 | 2.28 | 4.29 | 6.25 |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.