espnet.asr.pytorch_backend.asr_init.get_partial_state_dict

source

espnet.asr.pytorch_backend.asr_init.get_partial_state_dict(model_state_dict, modules)

Create state dict with specified modules matching input model modules.

• Parameters:
  • model_state_dict (Dict) – Pre-trained model state dict.
  • modules (Dict) – Specified module(s) to transfer.
• Returns: State dict with specified modules weights.
• Return type: new_state_dict (Dict)