Mansar Youness
Mansar Youness
Hello All your audio files should have the same length, so you need to truncate them or pad them. Best
Its in the repo : https://github.com/CVxTz/audio_classification/blob/master/code/keras_cnn_mel.py def load_audio_file(file_path, input_length=input_length): data = librosa.core.load(file_path, sr=16000)[0] #, sr=16000 if len(data)>input_length: max_offset = len(data)-input_length offset = np.random.randint(max_offset) data = data[offset:(input_length+offset)] # HERE: Truncating else:...
Maybe its a difference in librosa version since I uploaded the code Maybe you can change the input shape from " inp = Input(shape=(63, 320, 1))" to " inp =...
Did this solve your issue ?
Hello ! The train files need to be in ../input/audio_train/ not in ./input/audio_train/ :)
Hello, You have some convergence issue in your network. Maybe the data is badly shaped or the learning rate is too high or too low. I can't really help you...