silero-vad

import torch import torchaudio import numpy as np # Ensure PyTorch is installed and CUDA if available if not torch.cuda.is_available(): print("Warning: CUDA not available, using CPU for VAD.") # Load the Silero VAD model and utilities from torch hub # force_reload=True ensures you get the latest version from the repo # onnx=True if you have onnxruntime installed and want to use ONNX model model, utils = torch.hub.load( repo_or_dir='snakers4/silero-vad', model='silero_vad', force_reload=True, onnx=False # Set to True if onnxruntime is installed and preferred ) # Destructure utilities (get_speech_timestamps, save_audio, read_audio, VADIterator, collect_chunks) = utils # Define the sampling rate required by the model (e.g., 16000 Hz) SAMPLING_RATE = 16000 # Create dummy audio for demonstration (10 seconds, 16kHz) samples = SAMPLING_RATE * 10 dummy_audio = torch.randn(samples, dtype=torch.float32) # Resample dummy audio to the required sampling rate if it's not already # (In a real scenario, you'd read your audio file with torchaudio.load) if SAMPLING_RATE != torchaudio.get_sample_rate(dummy_audio): # This part is illustrative; dummy_audio is already at 16k here # For real audio: audio, sr = torchaudio.load('your_audio.wav') # if sr != SAMPLING_RATE: audio = torchaudio.functional.resample(audio, orig_freq=sr, new_freq=SAMPLING_RATE) pass # Process the audio to get speech timestamps speech_timestamps = get_speech_timestamps(dummy_audio, model, sampling_rate=SAMPLING_RATE) print(f"Speech timestamps detected: {speech_timestamps}") # Example of using VADIterator for real-time processing (requires audio chunks) vad_iterator = VADIterator(model, sampling_rate=SAMPLING_RATE) # Simulate processing small chunks chunk_size = SAMPLING_RATE * 0.5 # 0.5 second chunks for i in range(0, dummy_audio.shape[0], int(chunk_size)): chunk = dummy_audio[i:i + int(chunk_size)] if chunk.shape[0] < chunk_size: # Handle last chunk continue speech_dict = vad_iterator(chunk, return_seconds=True) if speech_dict: print(f"Speech detected in chunk starting at {i/SAMPLING_RATE:.2f}s: {speech_dict}") vad_iterator.reset_states() # Reset internal states after processing