Function log_mel_spectrogram

audio.py:157–204

Compute the log-Mel spectrogram of Parameters ---------- audio: Union[str, np.ndarray, torch.Tensor], shape = (*) The path to audio or either a NumPy array or Tensor containing the audio waveform in 16 kHz n_mels: int The number of Mel-frequency filters, only 8

(
    audio: Union[str, np.ndarray, torch.Tensor],
    n_mels: int = N_MELS,
    padding: int = 0,
    device: Optional[Union[str, torch.device]] = None,
)

def log_mel_spectrogram(
    audio: Union[str, np.ndarray, torch.Tensor],
    n_mels: int = N_MELS,
    padding: int = 0,
    device: Optional[Union[str, torch.device]] = None,
):
    """
    Compute the log-Mel spectrogram of

    Parameters
    ----------
    audio: Union[str, np.ndarray, torch.Tensor], shape = (*)
        The path to audio or either a NumPy array or Tensor containing the audio waveform in 16 kHz

    n_mels: int
        The number of Mel-frequency filters, only 80 is supported

    padding: int
        Number of zero samples to pad to the right

    device: Optional[Union[str, torch.device]]
        If given, the audio tensor is moved to this device before STFT

    Returns
    -------
    torch.Tensor, shape = (80, n_frames)
        A Tensor that contains the Mel spectrogram
    """
    if not torch.is_tensor(audio):
        if isinstance(audio, str):
            audio = load_audio(audio)
        audio = torch.from_numpy(audio)

    if device is not None:
        audio = audio.to(device)
    if padding > 0:
        audio = F.pad(audio, (0, padding))
    window = torch.hann_window(N_FFT).to(audio.device)
    stft = torch.stft(audio, N_FFT, HOP_LENGTH, window=window, return_complex=True)
    magnitudes = stft[..., :-1].abs() ** 2

    filters = mel_filters(audio.device, n_mels)
    mel_spec = filters @ magnitudes

    log_spec = torch.clamp(mel_spec, min=1e-10).log10()
    log_spec = torch.maximum(log_spec, log_spec.max() - 8.0)
    log_spec = (log_spec + 4.0) / 4.0
    return log_spec


@dataclass