s3tokenizer

import s3tokenizer import os # Ensure PyTorch is available and CUDA is configured if using GPU # For demonstration, we'll try to use CUDA if available, otherwise CPU. # In a real scenario, you might want to explicitly set device or handle errors. # Assuming a dummy audio file for demonstration. # In a real use case, replace with your .wav file path. # You might need to create a dummy WAV file or download one from the S3Tokenizer repo assets. # For example, by downloading from: https://github.com/xingchensong/S3Tokenizer/blob/main/s3tokenizer/assets/BAC009S0764W0121.wav # Create a dummy .wav file if it doesn't exist for a runnable example dummy_wav_path = "dummy_audio.wav" if not os.path.exists(dummy_wav_path): try: import torchaudio import torch sample_rate = 16000 duration_seconds = 5 waveform = torch.randn(1, sample_rate * duration_seconds) torchaudio.save(dummy_wav_path, waveform, sample_rate) print(f"Created dummy audio file: {dummy_wav_path}") except ImportError: print("torchaudio or torch not found. Cannot create dummy audio. Please provide a real .wav file.") exit() # Load the tokenizer model, preferring CUDA if available device = "cuda" if torch.cuda.is_available() else "cpu" tokenizer = s3tokenizer.load_model("speech_tokenizer_v1").to(device) print(f"Tokenizer model loaded on device: {device}") # Load an audio file # Replace `dummy_wav_path` with your actual audio file path if not using the dummy if os.path.exists(dummy_wav_path): audio = s3tokenizer.load_audio(dummy_wav_path) audio = audio.to(device) audio_len = torch.tensor([audio.shape[1]], device=device) # Quantize the audio to get speech codes speech_codes, speech_codes_lens = tokenizer.quantize(audio, audio_len) print(f"Shape of extracted speech codes: {speech_codes.shape}") print(f"Length of speech codes: {speech_codes_lens.item()}") else: print(f"Error: Audio file not found at {dummy_wav_path}.")