OpenTalker / video-retalking

[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild
https://opentalker.github.io/video-retalking/
Apache License 2.0
6.66k stars 978 forks source link

checkpoints can not open and RuntimeError: unexpected EOF, expected 73963 more bytes. The file might be corrupted error running on autodl #137

Open shlay158 opened 1 year ago

shlay158 commented 1 year ago

hello, i got 2 errors to running this project with autodl.

  1. checkpoints can not be opened or renamed
  2. got RuntimeError: unexpected EOF, expected 73963 more bytes. The file might be corrupted error running on autodl when running "python inference.py --face examples/face/1.mp4 --audio examples/audio/1.wav --outfile results/1_1.mp4" anybody can do help?
xin-duan commented 1 year ago

@shlay158, I hit similar error which is caused by incomplete or failure of downloading some necessarcy checkpoints models, check your log and manually download required models and rerun for example, my error is like below which means you need to check if s3fd-619a316812.pth has been downloaded successfully, you can see s3fd-619a316812.pth has not been downloaded completely so folollowing check failed: Output------------------------------------------------------------------------ [Step 1] Landmarks Extraction in Video. Downloading: "https://www.adrianbulat.com/downloads/python-fan/s3fd-619a316812.pth" to C:\Users\dx/.cache\torch\hub\checkpoints\s3fd-619a316812.pth 32%|████████████████████████▍ | 27.2M/85.7M [00:03<00:08, 7.43MB/s] Traceback (most recent call last): File "C:\AI\video-retalking\inference.py", line 345, in main() File "C:\AI\video-retalking\inference.py", line 81, in main kp_extractor = KeypointExtractor() File "C:\AI\video-retalking\third_part\face3d\extract_kp_videos.py", line 16, in init self.detector = face_alignment.FaceAlignment(face_alignment.LandmarksType.TWO_D) # duanxin change _2D to TWO_D File "C:\AI\system\miniconda3\lib\site-packages\face_alignment\api.py", line 80, in init self.face_detector = face_detector_module.FaceDetector(device=device, verbose=verbose, face_detector_kwargs) File "C:\AI\system\miniconda3\lib\site-packages\face_alignment\detection\sfd\sfd_detector.py", line 24, in init model_weights = load_url(models_urls['s3fd']) File "C:\AI\system\miniconda3\lib\site-packages\torch\hub.py", line 750, in load_state_dict_from_url return torch.load(cached_file, map_location=map_location) File "C:\AI\system\miniconda3\lib\site-packages\torch\serialization.py", line 815, in load return _legacy_load(opened_file, map_location, pickle_module, pickle_load_args) File "C:\AI\system\miniconda3\lib\site-packages\torch\serialization.py", line 1051, in _legacy_load typed_storage._untyped_storage._set_from_file( RuntimeError: unexpected EOF, expected 2659590 more bytes. The file might be corrupted.

Hope this help you.