HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

parakeet-ctc-1.1b

nvidia/parakeet-ctc-1.1b

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
nvidia/parakeet-ctc-1.1b
provider
nvidia
license
cc-by-4.0
language
en
context
—
library
nemo
vRAM (GB)
1,024
size on disk
—
downloads
1,632,235
likes
52
created
—
last modified
2025-09-24T14:54:06+00:00 (2025)
huggingface
https://huggingface.co/nvidia/parakeet-ctc-1.1b
tags
nemosafetensorsparakeet_ctcautomatic-speech-recognitiontransformersspeechaudioFastConformerConformerpytorchNeMohf-asr-leaderboardctcendataset:librispeech_asrdataset:fisher_corpusdataset:Switchboard-1dataset:WSJ-0dataset:WSJ-1dataset:National-Singapore-Corpus-Part-1dataset:National-Singapore-Corpus-Part-6dataset:vctkdataset:voxpopulidataset:europarl

Benchmark scores (7)

benchmarkcategoryscorecontextconfevidence
WER AMIspeech-asr15.62low| 1.22.0 | SentencePiece Unigram | 1024 | 15.62 | 13.69 | 10.27 | 1.83 | 3.54 | 4.20 | 3.54 | 6.53 | 9.02 |
WER Earnings-22speech-asr13.69low| 1.22.0 | SentencePiece Unigram | 1024 | 15.62 | 13.69 | 10.27 | 1.83 | 3.54 | 4.20 | 3.54 | 6.53 | 9.02 |
WER GigaSpeechspeech-asr10.27low| 1.22.0 | SentencePiece Unigram | 1024 | 15.62 | 13.69 | 10.27 | 1.83 | 3.54 | 4.20 | 3.54 | 6.53 | 9.02 |
WER Common Voicespeech-asr6.53low| 1.22.0 | SentencePiece Unigram | 1024 | 15.62 | 13.69 | 10.27 | 1.83 | 3.54 | 4.20 | 3.54 | 6.53 | 9.02 |
WER TED-LIUMspeech-asr4.2low| 1.22.0 | SentencePiece Unigram | 1024 | 15.62 | 13.69 | 10.27 | 1.83 | 3.54 | 4.20 | 3.54 | 6.53 | 9.02 |
WER SPGISpeechspeech-asr3.54low| 1.22.0 | SentencePiece Unigram | 1024 | 15.62 | 13.69 | 10.27 | 1.83 | 3.54 | 4.20 | 3.54 | 6.53 | 9.02 |
WER VoxPopulispeech-asr3.54low| 1.22.0 | SentencePiece Unigram | 1024 | 15.62 | 13.69 | 10.27 | 1.83 | 3.54 | 4.20 | 3.54 | 6.53 | 9.02 |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.