descript-audio-codec

import dac import torch from audiotools import AudioSignal import os # Instantiate the DAC model. Model weights are automatically downloaded and cached. # You can specify model_type='16khz', '24khz', or '44khz'. Default is '44khz'. device = "cuda" if torch.cuda.is_available() else "cpu" model = dac.DAC.load(model_type="44khz").to(device) # Prepare dummy audio for encoding (e.g., 5 seconds of stereo 44.1kHz noise) sample_rate = model.sample_rate # 44100 duration = 5 # seconds channels = 2 # stereo audio_tensor = torch.randn(channels, sample_rate * duration, device=device) audio_signal = AudioSignal(audio_tensor, sample_rate) # Encode the audio to discrete codes and get the reconstructed audio with torch.no_grad(): # codes: quantized latent representations (discrete tokens) # latents: continuous latent representations # audio_out: reconstructed audio (audiotools.AudioSignal) codes, latents, audio_out = model.encode(audio_signal, return_audio=True) print(f"Original audio shape: {audio_signal.shape}") print(f"Encoded codes shape (batch, num_quantizers, sequence_length): {codes.shape}") print(f"Decoded audio shape: {audio_out.shape}") # In a real application, you might save `codes` for storage/transmission # or `audio_out` to a file. # Example (requires audiotools): # audio_out.write("reconstructed_audio.wav") # Example: torch.save(codes, "compressed_audio_codes.pt")