Parakeet Tdt 0.6b V2 Onnx

🚀 NVIDIA Parakeet TDT 0.6B V2 (En)

The NVIDIA Parakeet TDT 0.6B V2 model is converted to ONNX format for onnx - asr, enabling efficient automatic speech recognition.

🚀 Quick Start

This guide will show you how to install the onnx - asr library and use the converted NVIDIA Parakeet TDT 0.6B V2 model for speech recognition.

📦 Installation

To install the onnx - asr library, run the following command:

pip install onnx-asr[cpu,hub]

💻 Usage Examples

Basic Usage

The following code demonstrates how to load the Parakeet TDT model and recognize a WAV file:

import onnx_asr
model = onnx_asr.load_model("nemo-parakeet-tdt-0.6b-v2")
print(model.recognize("test.wav"))

Advanced Usage

The following code shows how to export the model to ONNX format:

import nemo.collections.asr as nemo_asr
from pathlib import Path

model = nemo_asr.models.ASRModel.from_pretrained("nvidia/parakeet-tdt-0.6b-v2")

onnx_dir = Path("nemo-onnx")
onnx_dir.mkdir(exist_ok=True)
model.export(str(Path(onnx_dir, "model.onnx")))

with Path(onnx_dir, "vocab.txt").open("wt") as f:
    for i, token in enumerate([*model.tokenizer.vocab, "<blk>"]):
        f.write(f"{token} {i}\n")

📄 License

This project is licensed under the CC - BY 4.0 license.

📚 Documentation

Model Information