def au_proc(filename, max_shape):
result = np.zeros((num_of_augs + 1, max_shape))
X, sample_rate = librosa.load(filename)
melspec = librosa.feature.melspectrogram(y=X,
sr=sample_rate,
n_mels=256,
hop_length=128,
fmax=8000)
shape = melspec.shape[0] * melspec.shape[1]
for i in range(num_of_augs):
warped_masked_spectrogram = spec_augment_tensorflow.spec_augment(
mel_spectrogram=melspec)
warped_masked_spectrogram = warped_masked_spectrogram.reshape(shape)
for j in range(shape):
result[i + 1][j] = warped_masked_spectrogram[j]
melspec = melspec.reshape(shape)
for j in range(shape):
result[0][j] = melspec[j]
return result
sr=sample_rate,
n_mels=256,
hop_length=128,
fmax=8000)
l = melspec.shape[
0] #TODO: rename the variables 'l' and 'll' , make it as much informative as it's possible
ll = melspec.shape[1]
k = k + 1
for j in range(l):
for jj in range(ll):
x_train[k][j][jj] = melspec[j][jj]
for pp in range(
10
): # TODO: make the number of iterations global constant so we can change it easily
warped_masked_spectrogram = spec_augment_tensorflow.spec_augment(
mel_spectrogram=melspec)
#print(warped_masked_spectrogram)
#spec_augment_tensorflow.visualization_spectrogram(melspec, 'before')
#spec_augment_tensorflow.visualization_spectrogram(warped_masked_spectrogram, 'after')
k = k + 1
for j in range(l):
for jj in range(ll):
x_train[k][j][jj] = warped_masked_spectrogram[j][jj]
librosa.display.specshow(librosa.power_to_db(melspec, ref=np.max))
pylab.savefig(save_path, bbox_inches=None, pad_inches=0)
pylab.close()
x_train = x_train.reshape(1, 3300, 91000)
print(len(x_train))