util.py 文件源码

def create_spectrogram_from_audio(data):
    global setting
    spectrogram = librosa.stft(data, n_fft=Config.n_fft, hop_length=Config.hop_length).transpose()

    # divide the real and imaginary components of each element 
    # concatenate the matrix with the real components and the matrix with imaginary components
    # (DataCorruptionError when saving complex numbers in TFRecords)

    # concatenated = np.concatenate([np.real(spectrogram), np.imag(spectrogram)], axis=1)
    return spectrogram # [num_time_frames, num_freq_bins]