Overview
SileroVADAnalyzer is a Voice Activity Detection (VAD) analyzer that uses the Silero VAD ONNX model to detect speech in audio streams. It provides high-accuracy speech detection with efficient processing using ONNX runtime.
Installation
The Silero VAD analyzer is now included as a core dependency:Constructor Parameters
int
default:"None"
Audio sample rate in Hz. Must be either 8000 or 16000. When
None, the
pipeline’s input sample rate is used. The pipeline’s audio_in_sample_rate
must be 8000 or 16000 even when this is set; any other rate raises
ValueError when the pipeline starts.VADParams
default:"VADParams()"
Voice Activity Detection parameters object
Usage Example
Technical Details
Sample Rate Requirements
The analyzer supports two sample rates:- 8000 Hz (256 samples per frame)
- 16000 Hz (512 samples per frame)
- Uses ONNX runtime for efficient inference
- Keeps the model state for the whole audio stream and never resets it mid-stream
- Runs on CPU by default for consistent performance
- Includes built-in model file
Notes
- High-accuracy speech detection
- Efficient ONNX-based processing
- Thread-safe for pipeline processing
- Built-in model file included
- CPU-optimized inference
- Supports 8kHz and 16kHz audio