Modelpublic

TigreGotico/frame-vad-marblenet-onnx

sourceHugging Faceotherupdated 3mo agoView on Hugging Face

0likes

Model Card

frame-vad-marblenet (ONNX, repackaged for vadonnx)

ONNX voice activity detection model packaged for use with `vadonnx`.

—Upstream source: https://huggingface.co/nvidia/framevadmultilingualmarblenetv2.0 (NVIDIA Open Model License)
—License: NVIDIA Open Model License
—Sample rate: 16000 Hz
—Frame size: 320 samples
—Stateful: False

This repository redistributes the model in ONNX form together with a signature.json describing its input/output wiring. All rights and the original license belong to the upstream authors.

Usage

python

from vadonnx import load_vad
vad = load_vad("frame")
segments = vad.get_speech_segments(audio, sample_rate=16000)