Parakeet-TDT-0.6B-v3
Multilingual automatic speech recognition (ASR) model supporting English and 25 European languages with Token‑and‑Duration Transducer (TDT) architecture.
Parakeet‑TDT‑0.6B‑v3 is a 600M‑parameter ASR model by NVIDIA using TDT architecture with a FastConformer encoder and 2‑layer LSTM predictor, split into Encoder, Decoder, and Joint components for efficient on‑device inference across English and 25 European languages.
Not supported
This model is currently not supported on any IoT chipset.
To see performance metrics for this model on other chipsets, click the button below.
View for other chipsetsTechnical Details
Input resolution:128 mel bins x variable time (16kHz mono audio)
Model checkpoint:nvidia/parakeet-tdt-0.6b-v3
Model size (decoder) (float):47 MB
Model size (encoder) (float):2270 MB
Model size (joint) (float):20 MB
Number of parameters (decoder):12.2M
Number of parameters (encoder):609.5M
Number of parameters (joint):5.3M
Supported languages:English + 25 European languages
TDT durations:5 (0,1,2,3,4 frames)
Total parameters:627.0M
Vocabulary size:8193 (8192 BPE + 1 blank)
WER (LibriSpeech test-clean):1.93%
WER (LibriSpeech test-other):3.59%
Applicable Scenarios
- Voice Assistants
- Transcription Services
- Accessibility
- Smart Home
- Real-time Transcription
License
Model:CC-BY-4.0
Tags
- foundation
- real-time
Supported IoT Devices
- Dragonwing Q-8750
Supported IoT Chipsets
- Qualcomm® Dragonwing™ Q-8750
Related Models
See all models
Looking for more? See models created by industry leaders.
Discover Model Makers