Function moving_average

data_gen/tts/data_gen_utils.py:75–79

(array, width)

    # Smooth the voice detection with a moving average
    def moving_average(array, width):
        array_padded = np.concatenate((np.zeros((width - 1) // 2), array, np.zeros(width // 2)))
        ret = np.cumsum(array_padded, dtype=float)
        ret[width:] = ret[width:] - ret[:-width]
        return ret[width - 1:] / width

    audio_mask = moving_average(voice_flags, vad_moving_average_width)
    audio_mask = np.round(audio_mask).astype(np.bool)