def __init__()

in models/src/parallel_wavegan/layers/pqmf.py [0:0]

• 36 lines of code
• 4 McCabe index (conditional complexity)

    def __init__(self, subbands=4, taps=62, cutoff_ratio=0.142, beta=9.0):
        """Initilize PQMF module.

        The cutoff_ratio and beta parameters are optimized for #subbands = 4.
        See dicussion in https://github.com/kan-bayashi/ParallelWaveGAN/issues/195.

        Args:
            subbands (int): The number of subbands.
            taps (int): The number of filter taps.
            cutoff_ratio (float): Cut-off frequency ratio.
            beta (float): Beta coefficient for kaiser window.

        """
        super(PQMF, self).__init__()

        # build analysis & synthesis filter coefficients
        h_proto = design_prototype_filter(taps, cutoff_ratio, beta)
        h_analysis = np.zeros((subbands, len(h_proto)))
        h_synthesis = np.zeros((subbands, len(h_proto)))
        for k in range(subbands):
            h_analysis[k] = (
                2
                * h_proto
                * np.cos(
                    (2 * k + 1)
                    * (np.pi / (2 * subbands))
                    * (np.arange(taps + 1) - (taps / 2))
                    + (-1) ** k * np.pi / 4
                )
            )
            h_synthesis[k] = (
                2
                * h_proto
                * np.cos(
                    (2 * k + 1)
                    * (np.pi / (2 * subbands))
                    * (np.arange(taps + 1) - (taps / 2))
                    - (-1) ** k * np.pi / 4
                )
            )

        # convert to tensor
        analysis_filter = torch.from_numpy(h_analysis).float().unsqueeze(1)
        synthesis_filter = torch.from_numpy(h_synthesis).float().unsqueeze(0)

        # register coefficients as beffer
        self.register_buffer("analysis_filter", analysis_filter)
        self.register_buffer("synthesis_filter", synthesis_filter)

        # filter for downsampling & upsampling
        updown_filter = torch.zeros((subbands, subbands, subbands)).float()
        for k in range(subbands):
            updown_filter[k, k, 0] = 1.0
        self.register_buffer("updown_filter", updown_filter)
        self.subbands = subbands

        # keep padding info
        self.pad_fn = torch.nn.ConstantPad1d(taps // 2, 0.0)