Can't deep copy DAC model

[txya900619]

When I try to deep copy the model, I get this error message RuntimeError('Only Tensors created explicitly by the user (graph leaves) support the deepcopy protocol at the moment. If you were attempting to deepcopy a module, this may be because of a torch.nn.utils.weight_norm usage, see https://github.com/pytorch/pytorch/pull/103001').

It looks like the function torch.nn.utils.weight_norm has been deprecated since torch 2.1 and can be replaced by torch.nn.utils.parametrize.remove_parametrizations.
I tried to replace it as suggested and it works.