runtime error

Downloaded hubert base model file successfully. File saved to ./hubert_base.pt. Downloaded rmvpe model file successfully. File saved to ./rmvpe.pt. ------------------------------- RVC v2 Easy GUI (Local Edition) ------------------------------- 2024-01-02 20:53:21 | INFO | fairseq.tasks.text_to_speech | Please install tensorboardX: pip install tensorboardX 2024-01-02 20:53:24 | INFO | matplotlib.font_manager | generated new fontManager No supported Nvidia GPU found, use CPU instead CUDA is not available. Make sure you have an NVIDIA GPU and CUDA installed. Preloading RMVPE model... Traceback (most recent call last): File "/home/user/app/app.py", line 225, in <module> from vc_infer_pipeline import VC File "/home/user/app/vc_infer_pipeline.py", line 24, in <module> model_rmvpe = RMVPE("rmvpe.pt", is_half=config.is_half, device=config.device) File "/home/user/app/rmvpe.py", line 334, in __init__ ckpt = torch.load(model_path, map_location="cpu") File "/home/user/.local/lib/python3.10/site-packages/torch/serialization.py", line 1028, in load return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args) File "/home/user/.local/lib/python3.10/site-packages/torch/serialization.py", line 1246, in _legacy_load magic_number = pickle_module.load(f, **pickle_load_args) _pickle.UnpicklingError: invalid load key, '<'.

Container logs: