how to convert to torchscript using script method. using trace method cause the model cannot handle the dynamic input.

[AnanasPizzaMigliore]

No description provided.

[Dordor333]

I encountered an issue when trying to convert my model to TorchScript using:
torch_jit = model.to_torchscript(file_path='torchscript_model_new_1_epoch.pt', method='trace', example_inputs=dummy_input)

ocr_model_load = torch.jit.load('torchscript_model_new_1_epoch.pt').eval()
Specifically, the output from the traced model does not match the output from the original model. Additionally, the model loaded from TorchScript seems to have some irrelevant characters added to the output, which further complicates the results.

Could you please help me understand why this might be happening and how to resolve it?