Specifications
Size
~120 MB - 400 MB
Architecture
RNN-T / CTC
Latency
Low
Language
English
Developer / Creator
NVIDIA (NeMo team), Sherpa ONNX community
Download Source
Verified Repository Source
Hugging Face Hub / Sherpa ONNX model catalog
Open Model Repository (k2-fsa/sherpa-onnx)Model Overview
NVIDIA's Parakeet is a state-of-the-art speech-to-text model optimized for English. It is quantized to INT8 ONNX format to run in-process through the Sherpa ONNX engine. It provides extremely high accuracy and lightning-fast speed for coding, business, and general English dictation.
Available Model Variants
| Model Name | File Size | RAM Usage | Format/Quant | Languages | Description |
|---|---|---|---|---|---|
| NVIDIA Parakeet | 400 MB | 1.4 GB | INT8 (ONNX) | English | NVIDIA Parakeet TDT 0.6B v3 model. Superior English coding and business accuracy. |