Text-to-Speech
Safetensors
inf5
custom_code

solve the model loading error!

#13
by rajavemula - opened

NotImplementedError: Cannot copy out of meta tensor; no data! Please use torch.nn.Module.to_empty() instead of torch.nn.Module.to() when moving module from meta to a different device.

(This error indicates a problem during the model loading process where the model's parameters are being initialized in a "meta" state (structure without data), and the standard methods for moving the model to the GPU (.to(device)) are unable to handle this state.)

is there any solution?

I make some changes in model.py file but still not able to make it work , i hope they fix this issue asap

pip install transformers==4.49.0 pydub soundfile safetensors huggingface_hub , run this

Sign up or log in to comment