s0me-0ne/parakeet-tdt-0.6b-v3-onnx
By s0me-0ne · ↓ 3 · ♥ 2 · Updated 2025-08-18
What's in this repo
This page lists the files in s0me-0ne/parakeet-tdt-0.6b-v3-onnx, including decoder_joint-model.int8.onnx, decoder_joint-model.onnx, encoder-model.int8.onnx and more.
- 5 ONNX models (.onnx files)
- 10 files, including 5 .onnx, 1 .md, 1 .json, 1 .data, 1 .txt
- Last updated 2025-08-18
ONNX files
| File | Size | Download |
|---|---|---|
| decoder_joint-model.int8.onnx | — | Download |
| decoder_joint-model.onnx | — | Download |
| encoder-model.int8.onnx | — | Download |
| encoder-model.onnx | — | Download |
| nemo128.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
NVIDIA Parakeet TDT 0.6B V3 (Multilingual) model converted to ONNX format for magic-voice.
Install onnx-asr
pip install onnx-asr[cpu,hub]
Load Parakeet TDT model and recognize wav file
import onnx_asr
model = onnx_asr.load_model("nemo-parakeet-tdt-0.6b-v3")
print(model.recognize("test.wav"))
Code for models export
import nemo.collections.asr as nemo_asr
from pathlib import Path
model = nemo_asr.models.ASRModel.from_pretrained("nvidia/parakeet-tdt-0.6b-v3")
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")
Model info
Created: 2025-08-18
Updated: 2025-08-18
View on Hugging FaceFiles (10)
Related models
More from s0me-0ne
No other models by this author.