Cannot run on docker

[manchuwook]

Made a fork of the repo, cloned to my Windows 11 desktop, ran docker compose up -d and got this error when adding a picture, wav, and ran generate.

2024-07-04 01:30:47 app-1  | 
2024-07-04 01:30:47 app-1  | ==========
2024-07-04 01:30:47 app-1  | == CUDA ==
2024-07-04 01:30:47 app-1  | ==========
2024-07-04 01:30:47 app-1  | 
2024-07-04 01:30:47 app-1  | CUDA Version 12.2.0
2024-07-04 01:30:47 app-1  | 
2024-07-04 01:30:47 app-1  | Container image Copyright (c) 2016-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
2024-07-04 01:30:47 app-1  | 
2024-07-04 01:30:47 app-1  | This container image and its contents are governed by the NVIDIA Deep Learning Container License.
2024-07-04 01:30:47 app-1  | By pulling and using the container, you accept the terms and conditions of this license:
2024-07-04 01:30:47 app-1  | https://developer.nvidia.com/ngc/nvidia-deep-learning-container-license
2024-07-04 01:30:47 app-1  | 
2024-07-04 01:30:47 app-1  | A copy of this license is made available in this container at /NGC-DL-CONTAINER-LICENSE for your convenience.
2024-07-04 01:30:47 app-1  | 
2024-07-04 01:31:31 app-1  | /usr/local/lib/python3.10/dist-packages/gradio/processing_utils.py:588: UserWarning: Trying to convert audio automatically from int32 to 16-bit int format.
2024-07-04 01:31:31 app-1  |   warnings.warn(warning.format(data.dtype))
2024-07-04 01:31:32 app-1  | The cache for model files in Transformers v4.22.0 has been updated. Migrating your old cache. This is a one-time only operation. You can interrupt this and resume the migration later on by calling `transformers.utils.move_cache()`.
2024-07-04 01:31:32 app-1  | 
0it [00:00, ?it/s]
0it [00:00, ?it/s]
2024-07-04 01:31:35 app-1  | Traceback (most recent call last):
2024-07-04 01:31:35 app-1  |   File "/app/scripts/inference.py", line 424, in <module>
2024-07-04 01:31:35 app-1  |     inference_process(
2024-07-04 01:31:35 app-1  |   File "/app/scripts/inference.py", line 181, in inference_process
2024-07-04 01:31:35 app-1  |     with ImageProcessor(img_size, face_analysis_model_path) as image_processor:
2024-07-04 01:31:35 app-1  |   File "/app/hallo/datasets/image_processor.py", line 97, in __init__
2024-07-04 01:31:35 app-1  |     self.face_analysis = FaceAnalysis(
2024-07-04 01:31:35 app-1  |   File "/usr/local/lib/python3.10/dist-packages/insightface/app/face_analysis.py", line 31, in __init__
2024-07-04 01:31:35 app-1  |     model = model_zoo.get_model(onnx_file, **kwargs)
2024-07-04 01:31:35 app-1  |   File "/usr/local/lib/python3.10/dist-packages/insightface/model_zoo/model_zoo.py", line 96, in get_model
2024-07-04 01:31:35 app-1  |     model = router.get_model(providers=providers, provider_options=provider_options)
2024-07-04 01:31:35 app-1  |   File "/usr/local/lib/python3.10/dist-packages/insightface/model_zoo/model_zoo.py", line 40, in get_model
2024-07-04 01:31:35 app-1  |     session = PickableInferenceSession(self.onnx_file, **kwargs)
2024-07-04 01:31:35 app-1  |   File "/usr/local/lib/python3.10/dist-packages/insightface/model_zoo/model_zoo.py", line 25, in __init__
2024-07-04 01:31:35 app-1  |     super().__init__(model_path, **kwargs)
2024-07-04 01:31:35 app-1  |   File "/usr/local/lib/python3.10/dist-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 419, in __init__
2024-07-04 01:31:35 app-1  |     self._create_inference_session(providers, provider_options, disabled_optimizers)
2024-07-04 01:31:35 app-1  |   File "/usr/local/lib/python3.10/dist-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 472, in _create_inference_session
2024-07-04 01:31:35 app-1  |     sess = C.InferenceSession(session_options, self._model_path, True, self._read_config_from_model)
2024-07-04 01:31:35 app-1  | onnxruntime.capi.onnxruntime_pybind11_state.InvalidProtobuf: [ONNXRuntimeError] : 7 : INVALID_PROTOBUF : Load model from ./pretrained_models/face_analysis/models/1k3d68.onnx failed:Protobuf parsing failed.