Handling variable length audio for extract_data.py

[signalarun]

My audio is of varied length and I am obtaining the following error. Should the duration be calculated dynamically ?

ValueError                                Traceback (most recent call last)
<ipython-input-4-b10fa00927a8> in <module>()
----> 1 save_mfcc(DATASET_PATH, JSON_PATH, num_segments=2)

5 frames
<__array_function__ internals> in pad(*args, **kwargs)

/usr/local/lib/python3.6/dist-packages/numpy/lib/arraypad.py in pad(array, pad_width, mode, **kwargs)
    819                 raise ValueError(
    820                     "can't extend empty axis {} using modes other than "
--> 821                     "'constant' or 'empty'".format(axis)
    822                 )
    823         # passed, don't need to do anything more as _pad_simple already

ValueError: can't extend empty axis 0 using modes other than 'constant' or 'empty'
 

[silahsor]

Hi,
I am working on this codes and topics but ı could not do that region.ı dont understand what should ı write that spaces? Could you help me please?

add an axis to input sets

X_train = X_train[..., np.newaxis]
X_validation = X_validation[..., np.newaxis]
X_test = X_test[..., np.newaxis]

[signalarun]

For CNN you have to do this