added cutting and option to change the number of mels

data/get_spectrograms.py

 # -*- coding: utf-8 -*-
 
+import math
 import os.path
 import torch
 import torchaudio
 import torchaudio.transforms as transforms
 
-def soundToSpectrogram(path, sample_rate = 16000, duration = 30) :
-    r"""Return the Mel Spectrogram of an audio file.
+def soundToSpectrogram(path, sample_rate = 16000, duration = 30, nb_mels = 128) :
+    r"""Return the Mel-spectrograms of consecutive parts of an audio file.
 
     Args :
         path (str): the path to the file.
         sample_rate (int, optional) : the sample rate in Hz to use when getting the spectrogram. Default : 16000 Hz
-        duration (int, optional) : the number of seconds the recording should last. Default : 30s
+        duration (int, optional) : the number of seconds each part should last. Default : 30s
+        nb_mels (int, optional) : the number of frequencies in the resulting spectrograms. Default : 128
     Returns :
         torch.Tensor : Mel frequency spectrogram of size (2, 128, time)"""
 
@@ -25,23 +27,30 @@ def soundToSpectrogram(path, sample_rate = 16000, duration = 30) :
     resample = transforms.Resample(orig_freq = orig_freq, new_freq = sample_rate)
     waveform = resample(waveform)
 
-    # Extract a certain duration
+    # Cut the recording and compute the Mel-spectrogram
     nb_frames = duration * sample_rate
-    waveform = waveform[:, :nb_frames]
-    nb_frames_missing = nb_frames - waveform.size()[1]
-    waveform = torch.cat([waveform, torch.zeros((1, nb_frames_missing))], dim = 1)
-
-    # Compute the Mel-spectrogram
-    melspectrogram = transforms.MelSpectrogram(sample_rate = sample_rate)
-    spectrogram = melspectrogram(waveform)
-
-    return spectrogram
+    spectrograms = []
+    
+    melspectrogram_of = transforms.MelSpectrogram(sample_rate = sample_rate)
+    
+    while waveform.size()[1] > 0 :
+        sample = waveform[:nb_frames]
+        waveform = waveform[nb_frames:]
+        spectrogram = melspectrogram_of(sample)
+        spectorgrams.append(samples)
+        
+    nb_frames_missing = nb_frames - sample.size()[0]
+    if nb_frames_missing > 0 :
+        spectrograms.pop()
+        
+    return spectrograms
 
 
 def getSpectrograms(dir_source, dir_target,
                     sample_rate = 16000,
                     overwrite = False,
                     duration = 30,
+                    nb_mels = 128,
                     to_ignore = set()) :
     r"""Compute the Mel spectrograms of all the sound files and write them to memory.
 
@@ -51,18 +60,23 @@ def getSpectrograms(dir_source, dir_target,
         sample_rate (int, optional) : the sample rate in Hz to use when getting the spectrogram. Default : 16000 Hz
         overwrite (bool, optional) : whether to compute all spectrograms again. Default : False
         duration (int, optional) : the number of seconds the recording should last. Default : 30s
+        nb_mels (int, optional) : the number of frequencies in the resulting spectrograms. Default : 128
         to_ignore (set, optional) : the set of titles of recordings that should not be downloaded."""
 
     for filename in os.listdir(dir_source) :
         title, _ = os.path.splitext(filename)
         path_source = os.path.join(dir_source, filename)
-        path_target = os.path.join(dir_target, title + '.pt')
+        path_target = os.path.join(dir_target, title + '-{part}.pt')
 
         print('Computing the Mel-spectrogram of {filename} ...'.format(filename = filename))
         if (overwrite or not(os.path.isfile(path_target))) and not(title in to_ignore) :
             try :
-                spectrogram = soundToSpectrogram(path_source, sample_rate = sample_rate, duration = duration)
-                torch.save(spectrogram, path_target)
+                spectrograms = soundToSpectrogram(path_source,
+                                                  sample_rate = sample_rate,
+                                                  duration = duration,
+                                                  nb_mels = nb_mels)
+                for i, spectrogram in enumerate(spectrograms) :
+                    torch.save(spectrogram, path_target.format(part = i + 1))
                 print('Success.')
             except Exception as exception :
                 print('Failure : {exception}.'.format(exception = exception))