vocos

import torch from vocos import Vocos # Instantiate Vocos model from Hugging Face Hub (Mel-spectrogram variant) vocos_model = Vocos.from_pretrained("charactr/vocos-mel-24khz") # Create a dummy Mel-spectrogram tensor (Batch, Channels, Time) # In a real application, this would come from a feature extraction step on actual audio. # Example: 1 batch, 100 mel bands, 256 time frames mel_spectrogram = torch.randn(1, 100, 256) # Move model and input to GPU if available if torch.cuda.is_available(): vocos_model = vocos_model.to('cuda') mel_spectrogram = mel_spectrogram.to('cuda') # Decode the Mel-spectrogram to an audio waveform audio_waveform = vocos_model.decode(mel_spectrogram) print(f"Generated audio waveform shape: {audio_waveform.shape}") print(f"Generated audio on device: {audio_waveform.device}") # To save the audio, you would typically use torchaudio.save: # import torchaudio # torchaudio.save("generated_audio.wav", audio_waveform.cpu(), sample_rate=24000)