torchcrepe

import torch import torchcrepe import numpy as np # Mock torchcrepe.load.audio for a runnable example without external files class MockLoadAudio: def audio(self, *args, **kwargs): # Generate a dummy 16kHz sine wave audio (1 second) sr = 16000 duration = 1.0 frequency = 440.0 # Hz t = np.linspace(0., duration, int(sr * duration), endpoint=False) audio_np = 0.5 * np.sin(2 * np.pi * frequency * t).astype(np.float32) return torch.from_numpy(audio_np).unsqueeze(0), sr # unsqueeze for batch dimension torchcrepe.load = MockLoadAudio() # Load dummy audio audio, sr = torchcrepe.load.audio('dummy.wav', sr=16000) # Here we'll use a 5 millisecond hop length hop_length = int(sr / 200.) # Provide a sensible frequency range for your domain (upper limit is 2006 Hz) # This would be a reasonable range for speech fmin = 50 fmax = 550 # Select a model capacity--one of "tiny" or "full" model = 'tiny' # Choose a device to use for inference device = 'cuda:0' if torch.cuda.is_available() else 'cpu' # Pick a batch size that doesn't cause memory errors on your gpu batch_size = 2048 # Note: Batching here refers to internal frame processing, not input audio files # Compute pitch pitch = torchcrepe.predict( audio, sr, hop_length, fmin, fmax, model, batch_size=batch_size, device=device, return_periodicity=False # Set to True to get a confidence score ) print(f"Predicted pitch shape: {pitch.shape}") if pitch.shape[-1] > 0: print(f"First few pitch values: {pitch[0, :5].tolist()}")