whatmodel.sh / stt / STT En Conformer-CTC Large

STT En Conformer-CTC Large

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

STT En Conformer-CTC Large is an open-weights speech-to-text model from NVIDIA, released April 2022. Its published size is 0.12B parameters. Licence: cc-by-4.0.

Catalogue identity notes

Exact checkpoint nvidia/stt_en_conformer_ctc_large (NeMo). Params: card (~120M). released: HF repo creation month.

50.5±3.7#95 of 162 speech-to-text modelsfrom 2 benchmark results across 1 source* thinly tested, treat the rank as provisional

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 STT En Conformer-CTC Large, out of 176 with a score, then more from NVIDIA.

#modelscorewhereRAMreleased
104Omnilingual ASR CTC 1B Meta51±2local~2.9GB2025-11
105Whisper large-v2 OpenAI51±2local~4.2GB2022-12
106STT En Conformer-CTC Large NVIDIA51±4local~1.1GB2022-04
107Omnilingual ASR LLM 300M v2 Meta51±3local~4.4GB2025-12
108Moonshine Streaming Medium Useful Sensors (Moonshine AI)50±3local~1.8GB2026-01
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

long-form transcription▁▁▄▁·▃▂█▄▁▁▁ #20 of 27 * · 47% of its score · 1 test

Trails Whisper large (v1) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Open ASR English long-form WER11.1% ✎▁▁▅▁·▃▅█▆▁▂▂ beats 8/30avg 12%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 47%typical
other tests1 not in a task · 47% of its score
testresultvs the others in its rundifficultycountswhy
Open ASR English short-form WER (March 2026)8.3% ✎▁▁▁▃··▁▁▂██▆ beats 29/86avg 8.2%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 47%blunt

$ where to run it

Other ways to run it

  1. Run it as published · needs ~1.08 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/stt_en_conformer_ctc_large').transcribe(['audio.wav']))"

Official weights and documentation: huggingface.co/nvidia ↗

$ how the score was worked out · Open ASR Leaderboard 95%

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
Open ASR Leaderboard2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 95%Apache-2.0
prior · pull toward the middle▇▇ 5%
weighted average= 50.5

$ 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