stt_ar_fastconformer_hybrid_large_pcd_v1.0

Home/Models/nvidia/stt_ar_fastconformer_hybrid_large_pcd_v1.0

nvidia/stt_ar_fastconformer_hybrid_large_pcd_v1.0

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: nvidia/stt_ar_fastconformer_hybrid_large_pcd_v1.0
provider: nvidia
license: cc-by-4.0
language: ar
context: —
library: nemo
vRAM (GB): —
size on disk: —
downloads: 1,812
likes: 42
created: —
last modified: 2025-10-21T15:45:43+00:00 (2025)
huggingface: https://huggingface.co/nvidia/stt_ar_fastconformer_hybrid_large_pcd_v1.0
tags: nemospeech-recognitionASRArabicConformerTransducerCTCNeMohf-asr-leaderboardspeechaudioautomatic-speech-recognitionardataset:mozilla-foundation/common_voice_17_0dataset:google/fleursdataset:MASCdataset:tarteel-ai/everyayaharxiv:2305.05084license:cc-by-4.0model-indexregion:us

benchmark	category	score	context	conf	evidence
WER Common Voice	speech-asr	17.0		medium	`Common Voice 17.0`
WER	speech-asr	16.67		low	`\| 2.0.0 \| SentencePiece Unigram \| 1024 \| 16.67 \| 1679 \| 25.60 \| 1535 \| 12.94 \| 1392 \| 6.55 \| 1004 \|`

none scraped.