whatmodel.sh / stt / Canary-180M-Flash

Canary-180M-Flash

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Canary-180M-Flash is an open-weights speech-to-text model from NVIDIA, released March 2025. Its published size is 0.182B parameters. Licence: cc-by-4.0.

Catalogue identity notes

Exact checkpoint nvidia/canary-180m-flash (NeMo). Params: card (182M). released: HF repo creation month.

53.7±3.2#80 of 162 speech-to-text modelsfrom 3 benchmark results across 2 sources

Score within the Open ASR English short-form WER (March 2026) comparison set only.

$ how it compares

The speech-to-text models ranked either side of Canary-180M-Flash, out of 176 with a score, then more from NVIDIA.

#modelscorewhereRAMreleased
89Breeze ASR 25 MediaTek Research54±4local~1.7GB2025-06
90Parakeet CTC 0.6B NVIDIA54±3local~3.4GB2024-01
91Canary-180M-Flash NVIDIA54±3local~1.4GB2025-03
92Omnilingual ASR CTC 3B Meta54±2local~7.9GB2025-11
93MOSS-Transcribe-Diarize 0.9B OpenMOSS54±4local~1GB2026-07
more from NVIDIA
28Canary-Qwen-2.5B NVIDIA61±2local~6.6GB2025-07
35Parakeet TDT 0.6B v2 NVIDIA60±1local~1.9GB2025-05
37Parakeet Unified EN 0.6B NVIDIA60±4local~0.7GB2026-04

see all speech-to-text models · find the ones that fit your machine

$ what it's good at

other tests3 not in a task · 96% of its score
testresultvs the others in its rundifficultycountswhy
LibriSpeech test-clean WER1.9% ✎▁···▁▁▂·▄▄██ beats 28/56avg 2.3%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 44%blunt
Open ASR English short-form WER (March 2026)7.1% ✎▁▁▁▃··▁▁▂██▆ beats 58/86avg 8.2%▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 35%blunt
FLEURS English test WER6.0% ✎▁··▁▁▁▁▁▁▃█▁ beats 18/56avg 5.8%▇▇▇▇▇▇▇ 18%blunt

$ where to run it

Other ways to run it

  1. Run it as published · needs ~1.37 GB, NVIDIA only · from huggingface.co/nvidia (official)
    uvx --with 'nemo_toolkit[asr]' python -c "import nemo.collections.asr as a; print(a.models.ASRModel.from_pretrained('nvidia/canary-180m-flash').transcribe(['audio.wav']))"

Official weights and documentation: huggingface.co/nvidia ↗

$ how the score was worked out · transcribe.cpp model catalog… 62%, Open ASR Leaderboard 35%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 62%MIT
Open ASR Leaderboard1▇▇▇▇▇▇▇▇▇▇ 35%Apache-2.0
prior · pull toward the middle▇ 4%
weighted average= 53.7

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json