utils.py

print('Hello Kaare')

print(__name__)

import os
from PIL import Image
import librosa
import numpy as np

# Define a function that splits an audio file, 
# extracts spectrograms and saves them in a working directory
def get_spectrograms(filepath, primary_label, output_dir, SAMPLE_RATE, SIGNAL_LENGTH, SPEC_SHAPE, FMIN, FMAX):
    
    # Open the file with librosa (limited to the first 15 seconds)
    sig, rate = librosa.load(filepath, sr=SAMPLE_RATE, offset=None, duration=15)
    
    # Split signal into five second chunks
    sig_splits = []
    for i in range(0, len(sig), int(SIGNAL_LENGTH * SAMPLE_RATE)):
        split = sig[i:i + int(SIGNAL_LENGTH * SAMPLE_RATE)]

        # End of signal?
        if len(split) < int(SIGNAL_LENGTH * SAMPLE_RATE):
            break
        
        sig_splits.append(split)
        
    # Extract mel spectrograms for each audio chunk
    s_cnt = 0
    saved_samples = []
    for chunk in sig_splits:
        
        hop_length = int(SIGNAL_LENGTH * SAMPLE_RATE / (SPEC_SHAPE[1] - 1))
        mel_spec = librosa.feature.melspectrogram(y=chunk, 
                                                  sr=SAMPLE_RATE, 
                                                  n_fft=1024, 
                                                  hop_length=hop_length, 
                                                  n_mels=SPEC_SHAPE[0], 
                                                  fmin=FMIN, 
                                                  fmax=FMAX)
    
        mel_spec = librosa.power_to_db(mel_spec, ref=np.max) 
        
        # Normalize
        mel_spec -= mel_spec.min()
        mel_spec /= mel_spec.max()
        
        # Save as image file
        save_dir = os.path.join(output_dir, primary_label)
        if not os.path.exists(save_dir):
            os.makedirs(save_dir)
        save_path = os.path.join(save_dir, filepath.rsplit(os.sep, 1)[-1].rsplit('.', 1)[0] + 
                                 '_' + str(s_cnt) + '.png')
        im = Image.fromarray(mel_spec * 255.0).convert("L")
        im.save(save_path)
        
        saved_samples.append(save_path)
        s_cnt += 1
        
    return saved_samples