same shape for audio dataset .wav files-CodePudding

So, I'm creating an ANN neural network type that can classify if the one that is talking is me or not, the problem is that I can train it because of the shape of my data.

X data is

(262144,)

y data is

(261768,)

How can I make my .wav audio files data the same shape?

Here is my full code

    from sklearn.model_selection import train_test_split
    from sklearn.preprocessing import StandardScaler
    import tensorflow as tf
    import numpy as np
    from scipy.io import wavfile
    from pathlib import Path
    import os

    ### DATASET 
    pathlist = Path(os.path.abspath('Voiceclassification/Data/me/')).rglob('*.wav')

    # My voice data
    for path in pathlist:
        filename = str(path)

        # convert audio to numpy array and then 2D to 1D np Array
        samplerate, data = wavfile.read(filename)
        #print(f"sample rate: {samplerate}")
        data = data.flatten()
        #print(f"data: {data}")

    pathlist2 = Path(os.path.abspath('Voiceclassification/Data/other/')).rglob('*.wav')

    # other voice data
    for path2 in pathlist2:
        filename2 = str(path2)

        samplerate2, data2 = wavfile.read(filename2)
        data2 = data2.flatten()
        #print(data2)


    ### ADAPTING THE DATA FOR THE MODEL
    X = data # My voice
    y = data2 # Other data
    #print(X.shape)
    #print(y.shape)

    ### Trainig the model
    x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=0)

    # Performing future scaling
    sc = StandardScaler()

    x_train = sc.fit_transform(x_train)
    x_test = sc.transform(x_test)

    ### Creating the ANN
    ann = tf.keras.models.Sequential()

    # First hidden layer of the ann
    ann.add(tf.keras.layers.Dense(units=6, activation="relu"))
    # Second one
    ann.add(tf.keras.layers.Dense(units=6, activation="relu"))
    # Output layer
    ann.add(tf.keras.layers.Dense(units=6, activation="sigmoid"))

    # Compile our neural network
    ann.compile(optimizer="adam",
                loss="binary_crossentropy",
                metrics=['accuracy'])

    # Fit ANN
    ann.fit(x_train, y_train, batch_size=32, epochs=100)
    ann.save('train_model.model')

Any idea, in total I have 18 .wav files for each X or y

CodePudding user response：

You can use scipy.io for wav files, rewrite the file with only 5 seconds long, I create this little code that will help you

def trim_wav( originalWavPath, newWavPath , start, new ):
   sampleRate, waveData = wavfile.read( originalWavPath )
   startSample = int( start * sampleRate )
   endSample = int( new * sampleRate )
   wavfile.write( newWavPath, sampleRate, waveData[startSample:endSample])

wp = "path of the wav file"
trim_wav(wp, wp.replace(".wav", ".wav"), 0,5)

This will crop your audio files and get rid of the millisecond that are not changing the shape of your data