stt_en_fastconformer_transducer_large

Home/Models/nvidia/stt_en_fastconformer_transducer_large

nvidia/stt_en_fastconformer_transducer_large

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: nvidia/stt_en_fastconformer_transducer_large
provider: nvidia
license: cc-by-4.0
language: en
context: —
library: nemo
vRAM (GB): —
size on disk: —
downloads: 149
likes: 10
created: —
last modified: 2025-02-27T13:10:27+00:00 (2025)
huggingface: https://huggingface.co/nvidia/stt_en_fastconformer_transducer_large
tags: nemoautomatic-speech-recognitionspeechaudioTransducerFastConformerTransformerpytorchNeMohf-asr-leaderboardendataset: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_8_0dataset:MLCommons/peoples_speech

benchmark	category	score	context	conf	evidence
WER MLS	speech-asr	5.8		low	`\| 1.18.0 \| SentencePiece Unigram \| 1024 \| 3.8 \| 1.8 \| 1.4 \| 2.4 \| 5.5 \| 5.8 \| 7.5 \| NeMo ASRSET 3.0 \|`

none scraped.