runtime error

Exit code: 1. Reason: e allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. state_dict_raw = torch.load(model_path, map_location="cpu")['state_dict'] 2025-03-13 03:26:42.888 | ERROR | outetts.wav_tokenizer.audio_codec:__init__:35 - invalid load key, 'E'. Traceback (most recent call last): File "/usr/local/lib/python3.10/site-packages/outetts/wav_tokenizer/audio_codec.py", line 33, in __init__ self.wavtokenizer = WavTokenizer.from_pretrained0802(self.config_path, self.model_path) File "/usr/local/lib/python3.10/site-packages/outetts/wav_tokenizer/decoder/pretrained.py", line 101, in from_pretrained0802 state_dict_raw = torch.load(model_path, map_location="cpu")['state_dict'] File "/usr/local/lib/python3.10/site-packages/torch/serialization.py", line 1384, in load return _legacy_load( File "/usr/local/lib/python3.10/site-packages/torch/serialization.py", line 1628, in _legacy_load magic_number = pickle_module.load(f, **pickle_load_args) _pickle.UnpicklingError: invalid load key, 'E'. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/user/app/app.py", line 11, in <module> interface = outetts.InterfaceHF(model_version="0.2", cfg=model_config) File "/usr/local/lib/python3.10/site-packages/outetts/interface.py", line 76, in InterfaceHF return interface_class(cfg) File "/usr/local/lib/python3.10/site-packages/outetts/version/v1/interface.py", line 114, in __init__ self.audio_codec = AudioCodec(self.device, config.wavtokenizer_model_path) File "/usr/local/lib/python3.10/site-packages/outetts/wav_tokenizer/audio_codec.py", line 36, in __init__ raise ImportError(f"Failed to load WavTokenizer model.") ImportError: Failed to load WavTokenizer model.

Container logs: