HF Model & Benchmark Matrix

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

stt_en_fastconformer_ctc_large

nvidia/stt_en_fastconformer_ctc_large

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
nvidia/stt_en_fastconformer_ctc_large
provider
nvidia
license
cc-by-4.0
language
en
context
—
library
nemo
vRAM (GB)
—
size on disk
—
downloads
2,615
likes
20
created
—
last modified
2025-02-18T11:54:49+00:00 (2025)
huggingface
https://huggingface.co/nvidia/stt_en_fastconformer_ctc_large
tags
nemoautomatic-speech-recognitionspeechaudioCTCFastConformerTransformerpytorchNeMohf-asr-leaderboardendataset:librispeech_asrdataset:fisher_corpusdataset:Switchboard-1dataset:WSJ-0dataset:WSJ-1dataset:National-Singapore-Corpus-Part-1dataset:National-Singapore-Corpus-Part-6dataset:vctkdataset:voxpopulidataset:europarldataset:multilingual_librispeechdataset:mozilla-foundation/common_voice_8_0dataset:MLCommons/peoples_speech

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
WER MLSspeech-asr6.4low| 1.18.0 | SentencePiece Unigram | 1024 | 4.2 | 2.1 | 1.6 | 2.5 | 6.3 | 6.4 | 8.3 | NeMo ASRSET 3.0 |

Discussions (0)

none scraped.

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