parakeet-tdt-0.6b-v2

Home/Models/nvidia/parakeet-tdt-0.6b-v2

nvidia/parakeet-tdt-0.6b-v2

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: nvidia/parakeet-tdt-0.6b-v2
provider: nvidia
license: cc-by-4.0
language: en
context: —
library: nemo
vRAM (GB): —
size on disk: —
downloads: 763,375
likes: 1,529
created: —
last modified: 2026-06-29T19:00:21+00:00 (2026)
huggingface: https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2
tags: nemoautomatic-speech-recognitionspeechaudioTransducerTDTFastConformerConformerpytorchNeMohf-asr-leaderboardendataset:nvidia/Granarydataset:nvidia/nemo-asr-set-3.0arxiv:2305.05084arxiv:2304.06795arxiv:2406.00899arxiv:2410.01036arxiv:2505.13404license:cc-by-4.0model-indexeval-resultsregion:usdeploy:azure

benchmark	category	score	conf	evidence
WER AMI	speech-asr	11.16	high	`\| parakeet-tdt-0.6b-v2 \| 6.05 \| 11.16 \| 11.15 \| 9.74 \| 1.69 \| 3.19 \| 2.17 \| 3.38 \| 5.95 \| - \|`
WER Earnings-22	speech-asr	11.15	high	`\| parakeet-tdt-0.6b-v2 \| 6.05 \| 11.16 \| 11.15 \| 9.74 \| 1.69 \| 3.19 \| 2.17 \| 3.38 \| 5.95 \| - \|`
WER GigaSpeech	speech-asr	9.74	high	`\| parakeet-tdt-0.6b-v2 \| 6.05 \| 11.16 \| 11.15 \| 9.74 \| 1.69 \| 3.19 \| 2.17 \| 3.38 \| 5.95 \| - \|`
WER	speech-asr	6.05	high	`\| parakeet-tdt-0.6b-v2 \| 6.05 \| 11.16 \| 11.15 \| 9.74 \| 1.69 \| 3.19 \| 2.17 \| 3.38 \| 5.95 \| - \|`
WER VoxPopuli	speech-asr	5.95	high	`\| parakeet-tdt-0.6b-v2 \| 6.05 \| 11.16 \| 11.15 \| 9.74 \| 1.69 \| 3.19 \| 2.17 \| 3.38 \| 5.95 \| - \|`
WER TED-LIUM	speech-asr	3.38	high	`\| parakeet-tdt-0.6b-v2 \| 6.05 \| 11.16 \| 11.15 \| 9.74 \| 1.69 \| 3.19 \| 2.17 \| 3.38 \| 5.95 \| - \|`
WER SPGISpeech	speech-asr	2.17	high	`\| parakeet-tdt-0.6b-v2 \| 6.05 \| 11.16 \| 11.15 \| 9.74 \| 1.69 \| 3.19 \| 2.17 \| 3.38 \| 5.95 \| - \|`

none scraped.