RuntimeError: PytorchStreamReader failed reading file data/39: invalid header or archive is corrupted

Traceback (most recent call last):
File "E:\PyProjects\git_projects\MockingBird\toolbox\__init__.py", line 122, in
func = lambda: self.synthesize() or self.vocode()
File "E:\PyProjects\git_projects\MockingBird\toolbox\__init__.py", line 236, in synthesize
specs = self.synthesizer.synthesize_spectrograms(texts, embeds)
File "E:\PyProjects\git_projects\MockingBird\synthesizer\inference.py", line 87, in synthesize_spectrograms
self.load()
File "E:\PyProjects\git_projects\MockingBird\synthesizer\inference.py", line 65, in load
self._model.load(self.model_fpath)
File "E:\PyProjects\git_projects\MockingBird\synthesizer\models\tacotron.py", line 496, in load
checkpoint = torch.load(str(path), map_location=device)
File "D:\ProgramData\pyvenv\ml\lib\site-packages\torch\serialization.py", line 607, in load
return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
File "D:\ProgramData\pyvenv\ml\lib\site-packages\torch\serialization.py", line 882, in _load
result = unpickler.load()
File "D:\ProgramData\pyvenv\ml\lib\site-packages\torch\serialization.py", line 857, in persistent_load
load_tensor(data_type, size, key, _maybe_decode_ascii(location))
File "D:\ProgramData\pyvenv\ml\lib\site-packages\torch\serialization.py", line 845, in load_tensor
storage = zip_file.get_storage_from_record(name, size, dtype).storage()
RuntimeError: PytorchStreamReader failed reading file data/39: invalid header or archive is corrupted

Start with toolbox/__init__.py at synthesize, then follow synthesizer/inference.py:65 and synthesizer/models/tacotron.py:496 to reproduce the failure during torch.load. Inspect the model path and loading traceback, and consider the issue complete only when the reported checkpoint loads without the PytorchStreamReader error.

Written by the indexing model from the issue text.