nenad1002/nemotron-onnx-quantized
By nenad1002 · ↓ 0 · ♥ 0 · Updated 2026-03-02
What's in this repo
This page lists the files in nenad1002/nemotron-onnx-quantized, including decoder.int8.onnx, encoder.int8.onnx, joiner.int8.onnx.
- 3 ONNX models (.onnx files)
- 13 files, including 3 .onnx, 3 .json, 3 .wav, 2 .txt, 1 .md
- Last updated 2026-03-02
ONNX files
| File | Size | Download |
|---|---|---|
| decoder.int8.onnx | — | Download |
| encoder.int8.onnx | — | Download |
| joiner.int8.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
Introduction
This model is from https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b
Files (13)
.gitattributes
README.md
decoder.int8.onnx
ONNX
encoder.int8.onnx
ONNX
genai_config.json
joiner.int8.onnx
ONNX
test_wavs/0.wav
test_wavs/1.wav
test_wavs/8k.wav
test_wavs/trans.txt
tokenizer.json
tokenizer_config.json
tokens.txt
Related models
More from nenad1002
More models
No task type declared.