HF Model & Benchmark Matrix

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

parakeet-ctc-0.6b

nvidia/parakeet-ctc-0.6b

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
nvidia/parakeet-ctc-0.6b
provider
nvidia
license
cc-by-4.0
language
en
context
—
library
nemo
vRAM (GB)
—
size on disk
—
downloads
16,874
likes
26
created
—
last modified
2025-09-25T16:13:20+00:00 (2025)
huggingface
https://huggingface.co/nvidia/parakeet-ctc-0.6b
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-asr16.3low| 1.22.0 | SentencePiece Unigram | 1024 | 16.30 | 14.14 | 10.35 | 1.87 | 3.76 | 4.11 | 3.78 | 7.00 | 10.57 |
WER Earnings-22speech-asr14.14low| 1.22.0 | SentencePiece Unigram | 1024 | 16.30 | 14.14 | 10.35 | 1.87 | 3.76 | 4.11 | 3.78 | 7.00 | 10.57 |
WER GigaSpeechspeech-asr10.35low| 1.22.0 | SentencePiece Unigram | 1024 | 16.30 | 14.14 | 10.35 | 1.87 | 3.76 | 4.11 | 3.78 | 7.00 | 10.57 |
WER Common Voicespeech-asr7.0low| 1.22.0 | SentencePiece Unigram | 1024 | 16.30 | 14.14 | 10.35 | 1.87 | 3.76 | 4.11 | 3.78 | 7.00 | 10.57 |
WER TED-LIUMspeech-asr4.11low| 1.22.0 | SentencePiece Unigram | 1024 | 16.30 | 14.14 | 10.35 | 1.87 | 3.76 | 4.11 | 3.78 | 7.00 | 10.57 |
WER VoxPopulispeech-asr3.78low| 1.22.0 | SentencePiece Unigram | 1024 | 16.30 | 14.14 | 10.35 | 1.87 | 3.76 | 4.11 | 3.78 | 7.00 | 10.57 |
WER SPGISpeechspeech-asr3.76low| 1.22.0 | SentencePiece Unigram | 1024 | 16.30 | 14.14 | 10.35 | 1.87 | 3.76 | 4.11 | 3.78 | 7.00 | 10.57 |

Discussions (0)

none scraped.

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