how to solve this bug?

[lzkzls]

Traceback (most recent call last):
File "preprocess.py", line 59, in
main()
File "preprocess.py", line 42, in main
tacotron2 = get_Tacotron2()
File "/home/workspace/fastspeech/FastSpeech-master/utils.py", line 69, in get_Tacotron2
model.load_state_dict(torch.load(checkpoint_path)['state_dict'])
File "/usr/local/lib/python3.6/site-packages/torch/serialization.py", line 387, in load
return _load(f, map_location, pickle_module, **pickle_load_args)
File "/usr/local/lib/python3.6/site-packages/torch/serialization.py", line 564, in _load
magic_number = pickle_module.load(f, **pickle_load_args)
_pickle.UnpicklingError: invalid load key, '\x0a'.

[xcmyz]

Did you use the same tacotron2 pretrained model as referred in this repo?

[lzkzls]

Thank you! It has been solved. I did not use the correct Tacotron2 model.

[Ankita-020696]

Thank you! It has been solved. I did not use the correct Tacotron2 model.

@lzkzls I am getting same error, can you please help me to solve it?

[Ankita-020696]

@lzkzls I am getting same error, can you please help me me to fix it?

Thanks