音频提取mag,mel,f0,energy

# Audio
num_mels = 80
# num_freq = 1024
n_fft = 2048
sr = 22050
# frame_length_ms = 50.
# frame_shift_ms = 12.5
preemphasis = 0.97
frame_shift = 0.0125 # seconds
frame_length = 0.05 # seconds
hop_length = int(sr*frame_shift) # samples.
win_length = int(sr*frame_length) # samples.
n_mels = 80 # Number of Mel banks to generate
power = 1.2 # Exponent for amplifying the predicted magnitude
min_level_db = -100
ref_level_db = 20
hidden_size = 256
embedding_size = 512
max_db = 100
ref_db = 20


def get_spectrograms(fpath):
    '''Parse the wave file in `fpath` and
    Returns normalized melspectrogram and linear spectrogram.
    Args:
      fpath: A string. The full path of a sound file.
    Returns:
      mel: A 2d array of shape (T, n_mels) and dtype of float32.
      mag: A 2d array of shape (T, 1+n_fft/2) and dtype of float32.
    '''
    # Loading sound file
    y, sr = librosa.load(fpath, sr=hp.sr)

    # Trimming
    y, _ = librosa.effects.trim(y)

    # Preemphasis
    y = np.append(y[0], y[1:] - hp.preemphasis * y[:-1])

    # stft
    linear = librosa.stft(y=y,
                          n_fft=hp.n_fft,
                          hop_length=hp.hop_length,
                          win_length=hp.win_length)

    # magnitude spectrogram
    mag = np.abs(linear)  # (1+n_fft//2, T)

    # mel spectrogram
    mel_basis = librosa.filters.mel(hp.sr, hp.n_fft, hp.n_mels)  # (n_mels, 1+n_fft//2)
    mel = np.dot(mel_basis, mag)  # (n_mels, t)

    # to decibel
    mel = 20 * np.log10(np.maximum(1e-5, mel))
    mag = 20 * np.log10(np.maximum(1e-5, mag))

    # normalize
    mel = np.clip((mel - hp.ref_db + hp.max_db) / hp.max_db, 1e-8, 1)
    mag = np.clip((mag - hp.ref_db + hp.max_db) / hp.max_db, 1e-8, 1)

    # Transpose
    mel = mel.T.astype(np.float32)  # (T, n_mels)
    mag = mag.T.astype(np.float32)  # (T, 1+n_fft//2)

    f0, _ = pw.dio(y.astype(np.float64), hp.sr, frame_period=hp.hop_length / hp.sr * 1000)

    energy = np.linalg.norm(mag, ord=None, axis=None, keepdims=False)

    return mel, mag, f0, energy