preprocessing.py

train_audio_path = '../input/tensorflow-speech-recognition-challenge/train/audio/'

all_wave = []
all_label = []
for label in labels:
    print(label)
    waves = [f for f in os.listdir(train_audio_path + '/'+ label) if f.endswith('.wav')]
    for wav in waves:
        samples, sample_rate = librosa.load(train_audio_path + '/' + label + '/' + wav, sr = 16000)
        samples = librosa.resample(samples, sample_rate, 8000)
        if(len(samples)== 8000) : 
            all_wave.append(samples)
            all_label.append(label)