Silero VAD MLX

This model was converted from onnx-community/silero-vad to MLX format.

Usage

from mlx_audio.vad import load

model = load("mlx-community/silero-vad")
timestamps = model.get_speech_timestamps("audio.wav", return_seconds=True)
print(timestamps)

For streaming, pass 512-sample chunks at 16 kHz or 256-sample chunks at 8 kHz:

state = model.initial_state(sample_rate=16000)
probability, state = model.feed(chunk, state, sample_rate=16000)
Downloads last month
33
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support