stt_it_fastconformer_hybrid_large_pc

Home/Models/nvidia/stt_it_fastconformer_hybrid_large_pc

nvidia/stt_it_fastconformer_hybrid_large_pc

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: nvidia/stt_it_fastconformer_hybrid_large_pc
provider: nvidia
license: cc-by-4.0
language: it
context: —
library: nemo
vRAM (GB): —
size on disk: —
downloads: 277
likes: 2
created: —
last modified: 2025-02-18T13:23:51+00:00 (2025)
huggingface: https://huggingface.co/nvidia/stt_it_fastconformer_hybrid_large_pc
tags: nemoautomatic-speech-recognitionspeechaudioTransducerFastConformerCTCTransformerpytorchNeMohf-asr-leaderboarditdataset:facebook/voxpopulidataset:facebook/multilingual_librispeechdataset:mozilla-foundation/common_voice_12_0arxiv:2305.05084license:cc-by-4.0model-indexregion:us

benchmark	category	score	conf	evidence
WER VoxPopuli	speech-asr	13.02	low	`\| 1.20.0 \| SentencePiece BPE \| 512 \| 5.19% \| 5.64% \| 13.01% \| 11.39% \| 13.02% \| 16.22% \|`
WER MLS	speech-asr	13.01	low	`\| 1.20.0 \| SentencePiece BPE \| 512 \| 5.19% \| 5.64% \| 13.01% \| 11.39% \| 13.02% \| 16.22% \|`
WER Common Voice	speech-asr	12.0	medium	`Common Voice 12.0`

none scraped.