pyvad

import numpy as np from pyvad import vad, trim # Simulate audio data (e.g., 1 second of speech, 1 second of silence) fs = 16000 # Sample rate in Hz (WebRTC VAD supported rate) duration_speech = 1.0 # seconds duration_silence = 1.0 # seconds # Generate a simple sine wave for 'speech' t = np.linspace(0, duration_speech, int(fs * duration_speech), endpoint=False) speech_data = 0.5 * np.sin(2 * np.pi * 440 * t) # 440 Hz sine wave # Generate silence silence_data = np.zeros(int(fs * duration_silence)) # Combine speech and silence audio_data = np.concatenate((silence_data, speech_data, silence_data)).astype(np.float32) print(f"Audio data shape: {audio_data.shape}, Sample rate: {fs} Hz") # Perform Voice Activity Detection vact = vad(audio_data, fs) print(f"Voice activity array shape: {vact.shape}") # vact will contain 1s for voiced segments, 0s for unvoiced # Trim silence from the audio trimmed_audio, (start_idx, end_idx) = trim(audio_data, fs) print(f"Trimmed audio shape: {trimmed_audio.shape}") print(f"Original audio length: {len(audio_data) / fs:.2f}s") print(f"Trimmed audio from {start_idx/fs:.2f}s to {end_idx/fs:.2f}s, total {len(trimmed_audio)/fs:.2f}s")