parakeet-rnnt-1.1b

Home/Models/nvidia/parakeet-rnnt-1.1b

nvidia/parakeet-rnnt-1.1b

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: nvidia/parakeet-rnnt-1.1b
provider: nvidia
license: cc-by-4.0
language: en
context: —
library: nemo
vRAM (GB): —
size on disk: —
downloads: 6,561
likes: 179
created: —
last modified: 2026-07-06T13:52:55+00:00 (2026)
huggingface: https://huggingface.co/nvidia/parakeet-rnnt-1.1b
tags: nemosafetensorsparakeet_rnntfeature-extractionautomatic-speech-recognitionspeechaudioTransducerFastConformerConformerpytorchNeMohf-asr-leaderboardtransformersendataset:librispeech_asrdataset:fisher_corpusdataset:Switchboard-1dataset:WSJ-0dataset:WSJ-1dataset:National-Singapore-Corpus-Part-1dataset:National-Singapore-Corpus-Part-6dataset:vctkdataset:voxpopuli

benchmark	category	score	conf	evidence
WER AMI	speech-asr	17.1	low	`\| 1.22.0 \| SentencePiece Unigram \| 1024 \| 17.10 \| 14.11 \| 9.96 \| 1.46 \| 2.47 \| 3.11 \| 3.92 \| 5.39 \| 5.79 \|`
WER Earnings-22	speech-asr	14.11	low	`\| 1.22.0 \| SentencePiece Unigram \| 1024 \| 17.10 \| 14.11 \| 9.96 \| 1.46 \| 2.47 \| 3.11 \| 3.92 \| 5.39 \| 5.79 \|`
WER GigaSpeech	speech-asr	9.96	low	`\| 1.22.0 \| SentencePiece Unigram \| 1024 \| 17.10 \| 14.11 \| 9.96 \| 1.46 \| 2.47 \| 3.11 \| 3.92 \| 5.39 \| 5.79 \|`
WER Common Voice	speech-asr	5.39	low	`\| 1.22.0 \| SentencePiece Unigram \| 1024 \| 17.10 \| 14.11 \| 9.96 \| 1.46 \| 2.47 \| 3.11 \| 3.92 \| 5.39 \| 5.79 \|`
WER VoxPopuli	speech-asr	3.92	low	`\| 1.22.0 \| SentencePiece Unigram \| 1024 \| 17.10 \| 14.11 \| 9.96 \| 1.46 \| 2.47 \| 3.11 \| 3.92 \| 5.39 \| 5.79 \|`
WER TED-LIUM	speech-asr	3.11	low	`\| 1.22.0 \| SentencePiece Unigram \| 1024 \| 17.10 \| 14.11 \| 9.96 \| 1.46 \| 2.47 \| 3.11 \| 3.92 \| 5.39 \| 5.79 \|`
WER SPGISpeech	speech-asr	2.47	low	`\| 1.22.0 \| SentencePiece Unigram \| 1024 \| 17.10 \| 14.11 \| 9.96 \| 1.46 \| 2.47 \| 3.11 \| 3.92 \| 5.39 \| 5.79 \|`

none scraped.