openunmix

import torch import numpy as np from openunmix.separate import separate_audio # Simulate stereo audio data (e.g., 10 seconds at 44.1 kHz) sr = 44100 duration = 10 # seconds num_frames = sr * duration # Create a dummy audio tensor: (channels, samples) # In a real scenario, load an audio file using torchaudio.load() or similar. audio_data_np = np.random.randn(2, num_frames).astype(np.float32) audio_tensor = torch.from_numpy(audio_data_np) # Separate the audio into stems # By default, 'umxl' model is used from v1.2.1 onwards estimates = separate_audio(audio_tensor, rate=sr) # 'estimates' is a dictionary with keys like 'vocals', 'drums', 'bass', 'other' # Each value is a torch.Tensor representing the separated stem. print("Separated stems and their shapes:") for stem_name, stem_tensor in estimates.items(): print(f" {stem_name}: {stem_tensor.shape}") # Example: access vocals vocals = estimates['vocals'] # print(f"Vocals stem shape: {vocals.shape}")