torchfcpe

import torch import torchaudio from torchfcpe import FCPE import os # --- Configuration --- sampling_rate = 44100 # Default sample rate for FCPE hop_length = 512 # Default hop length device = os.environ.get('FCPE_DEVICE', 'cuda' if torch.cuda.is_available() else 'cpu') print(f"Using device: {device}") # --- 1. Initialize the FCPE model --- model = FCPE( sampling_rate=sampling_rate, hop_length=hop_length, device=device ) # --- 2. Create dummy audio data (or load real audio) --- # For a real scenario, replace with torchaudio.load('your_audio.wav') # This creates a 5-second mono sine wave at 440 Hz num_samples = sampling_rate * 5 # 5 seconds of audio t = torch.linspace(0, 5, num_samples, device=device) frequency = 440.0 # Hz # Generate a simple sine wave. FCPE expects mono audio. # Shape: (batch_size, num_samples) audio = torch.sin(2 * torch.pi * frequency * t).unsqueeze(0) # --- 3. Preprocess audio for the model --- # Ensure audio is on the correct device (already done for dummy data) # Ensure audio is 2D (batch_size, num_samples) if audio.dim() == 1: audio = audio.unsqueeze(0) # If audio were stereo (e.g., shape (2, N)), convert to mono: if audio.shape[0] > 1: # Assuming batch_size is 1, check channel dim audio = torch.mean(audio, dim=0, keepdim=True) print(f"Input audio shape: {audio.shape}") # --- 4. Perform pitch estimation --- with torch.no_grad(): f0, uv = model(audio) # f0: fundamental frequency (Hz), uv: unvoiced/voiced decision (boolean-like) print(f"Estimated F0 shape: {f0.shape}") print(f"Estimated UV shape: {uv.shape}") print(f"First 10 F0 values: {f0[0, :10].cpu().numpy()}") print(f"First 10 UV values: {uv[0, :10].cpu().numpy()}")