What does model.py do? Support for MPS
I tried to run # Run example (large model) python model.py --text="Hello world!" --path weights/ --model large but it seems nothing happens. No output, no sound. Was only able to generate and output audio by writing my own code.
Also, how does one enable support for MPS? The audio generation currently happens completely on CPU, and when I modify the code to include 'model.to("mps")' I get :
File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/torch/nn/functional.py", line 2266, in embedding
return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Placeholder storage has not been allocated on MPS device!