resemblyzer

import numpy as np import soundfile as sf import os from resemblyzer import VoiceEncoder, preprocess_wav # Note: Resemblyzer (v0.1.4) was developed with PyTorch <= 1.4.0. # Installing a compatible PyTorch version (e.g., pip install torch==1.4.0) # is crucial for avoiding runtime errors, especially on GPU. # Create a dummy WAV file for demonstration if it doesn't exist test_wav_path = "resemblyzer_test_audio.wav" if not os.path.exists(test_wav_path): # Generate a dummy 5-second 16kHz sine wave duration = 5 # seconds sample_rate = 16000 # Hz frequency = 440 # Hz (A4 note) t = np.linspace(0, duration, int(sample_rate * duration), endpoint=False) dummy_audio = 0.5 * np.sin(2 * np.pi * frequency * t) sf.write(test_wav_path, dummy_audio.astype(np.float32), sample_rate) print(f"Created dummy audio file: {test_wav_path}") # Load the pre-trained encoder (downloads if not cached) print("Loading VoiceEncoder... (first run may download model)") encoder = VoiceEncoder.from_pretrained() # Load and preprocess the dummy audio wav, sr = sf.read(test_wav_path) # Resemblyzer expects 16kHz audio. If your audio is different, # you would need to resample it, e.g., using librosa. # For this dummy, we ensured it's 16kHz. if sr != 16000: print(f"Warning: Audio sample rate is {sr}Hz, but Resemblyzer expects 16kHz. Resampling would be needed.") # Example resampling (requires librosa): # import librosa # wav = librosa.resample(wav, orig_sr=sr, target_sr=16000) clean_wav = preprocess_wav(wav) # Encode the voice embedding print("Encoding voice...") embed = encoder.embed_utterance(clean_wav) print(f"Generated embedding with shape: {embed.shape}") print(f"First 5 elements of embedding: {embed[:5]}") # Clean up dummy file if os.path.exists(test_wav_path): os.remove(test_wav_path) print(f"Removed dummy audio file: {test_wav_path}")