nvidia / automatic-speech-recognition updated 1 month ago

parakeet-tdt-0.6b-v2

Name: parakeet-tdt-0.6b-v2
Author: nvidia

> 🎉 NEW: Multilingual Parakeet TDT 0.6B V3 is now available! > 🌍 25 European Languages 🚀 Enhanced Performance 🔗 Try it here: nvidia/parakeet-tdt-0.6b-v3

Params

—

Context

—

Downloads 30d

719 K

Likes

1,532

Commercial use: allowed cc-by-4.0 Not gated 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

772 K719 K

Jul 28Jul 31Aug 3Aug 6

Specifications

Licence: cc-by-4.0
First seen on the Hub: 2025-04-15
Training datasets: nvidia/Granary, nvidia/nemo-asr-set-3.0
GigaSpeech (reported): 9.74
Vox Populi (reported): 5.95
tedlium-v3 (reported): 3.38
Earnings-22 (reported): 11.15
SPGI Speech (reported): 2.17
AMI (Meetings test) (reported): 11.16
LibriSpeech (clean) (reported): 1.69
LibriSpeech (other) (reported): 3.19
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Derivative parakeet-tdt-0.6b-v2 mlx-community 1.9 M

Compare with

speaker-diarization-3.1 8.9 M whisper-large-v3-turbo 8.7 M whisperkit-coreml 8.3 M whisper-large-v3 5.5 M speaker-diarization-community-1 5.3 M whisper-base 4.8 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB