RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. Can't use GPU with tacotron2

ptrblck · August 23, 2021, 9:28am

torch.hub.load loads the model onto the CPU so there is no need to push it to the CPU again.

The seek error is raised, since waveglow is an object of the nn.Module type and not a file (which is seek’able).