HF Model & Benchmark Matrix

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

canary-180m-flash

nvidia/canary-180m-flash

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
nvidia/canary-180m-flash
provider
nvidia
license
cc-by-4.0
language
en, de, es, fr
context
—
library
nemo
vRAM (GB)
—
size on disk
—
downloads
1,807
likes
107
created
—
last modified
2025-03-18T23:55:00+00:00 (2025)
huggingface
https://huggingface.co/nvidia/canary-180m-flash
tags
nemoautomatic-speech-recognitionautomatic-speech-translationspeechaudioTransformerFastConformerConformerpytorchNeMohf-asr-leaderboardendeesfrdataset:librispeech_asrdataset:fisher_corpusdataset:Switchboard-1dataset:WSJ-0dataset:WSJ-1dataset:National-Singapore-Corpus-Part-1dataset:National-Singapore-Corpus-Part-6dataset:vctkdataset:voxpopuli

Benchmark scores (6)

benchmarkcategoryscorecontextconfevidence
WERspeech-asr16.92% WERmedium| % WER | 16.92 | 14.01 | 20.01 | 25.04 |
WER AMIspeech-asr14.86low| main | canary-180m-flash | 1233 | 14.86 | 10.51 | 1.87 | 3.83 | 13.33 | 2.26 | 3.98 | 6.35 |
WER Earnings-22speech-asr13.33low| main | canary-180m-flash | 1233 | 14.86 | 10.51 | 1.87 | 3.83 | 13.33 | 2.26 | 3.98 | 6.35 |
WER GigaSpeechspeech-asr10.51low| main | canary-180m-flash | 1233 | 14.86 | 10.51 | 1.87 | 3.83 | 13.33 | 2.26 | 3.98 | 6.35 |
WER VoxPopulispeech-asr6.35low| main | canary-180m-flash | 1233 | 14.86 | 10.51 | 1.87 | 3.83 | 13.33 | 2.26 | 3.98 | 6.35 |
WER TED-LIUMspeech-asr3.98low| main | canary-180m-flash | 1233 | 14.86 | 10.51 | 1.87 | 3.83 | 13.33 | 2.26 | 3.98 | 6.35 |

Discussions (0)

none scraped.

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