stt_en_conformer_ctc_small

Home/Models/nvidia/stt_en_conformer_ctc_small

nvidia/stt_en_conformer_ctc_small

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: nvidia/stt_en_conformer_ctc_small
provider: nvidia
license: cc-by-4.0
language: en
context: —
library: nemo
vRAM (GB): —
size on disk: —
downloads: 863
likes: 7
created: —
last modified: 2025-02-27T13:05:37+00:00 (2025)
huggingface: https://huggingface.co/nvidia/stt_en_conformer_ctc_small
tags: nemoautomatic-speech-recognitionspeechaudioCTCConformerTransformerpytorchNeMohf-asr-leaderboardRivaendataset:librispeech_asrdataset:fisher_corpusdataset:Switchboard-1dataset:WSJ-0dataset:WSJ-1dataset:National-Singapore-Corpus-Part-1dataset:National-Singapore-Corpus-Part-6dataset:vctkdataset:VoxPopulidataset:Europarl-ASRdataset:Multilingual-LibriSpeechdataset:mozilla-foundation/common_voice_7_0

benchmark	category	score	context	conf	evidence
WER MLS	speech-asr	11.3		low	`\| 1.6.0 \| SentencePiece Unigram \| 128 \| 8.1 \| 3.7 \| 3.3 \| 4.8 \| 6.9 \| 11.3 \| 10.1 \| 15.7 \| NeMo ASRSET 2.0 \|`

none scraped.