transforms.py 文件源码

def __call__(self, tensor):
        """

        Args:
            tensor (Tensor): Tensor of audio of size (samples x channels)

        Returns:
            tensor (Tensor): n_mels x hops x channels (BxLxC), where n_mels is
                the number of mel bins, hops is the number of hops, and channels
                is unchanged.

        """
        if librosa is None:
            print("librosa not installed, cannot create spectrograms")
            return tensor
        L = []
        for i in range(tensor.size(1)):
            nparr = tensor[:, i].numpy()  # (samples, )
            sgram = librosa.feature.melspectrogram(
                nparr, **self.kwargs)  # (n_mels, hops)
            L.append(sgram)
        L = np.stack(L, 2)  # (n_mels, hops, channels)
        tensor = torch.from_numpy(L).type_as(tensor)

        return tensor