File Not Found Error ?

[AlonDan]

After I failed with the local Gradio (it works but can't generate without error)
I've tried via the prompt way.

I followed the instructions and tried the simple example, but I get this error:

(sadtalker) D:\SadTalker>python inference.py --driven_audio /_SOURCE_/1.wav  --source_image /_SOURCE_/1.png
./checkpoints\epoch_20.pth
Traceback (most recent call last):
  File "inference.py", line 158, in <module>
    main(args)
  File "inference.py", line 55, in main
    preprocess_model = CropAndExtract(path_of_lm_croper, path_of_net_recon_model, dir_of_BFM_fitting, device)
  File "D:\SadTalker\src\utils\preprocess.py", line 51, in __init__
    self.kp_extractor = KeypointExtractor(device)
  File "D:\SadTalker\src\face3d\extract_kp_videos.py", line 16, in __init__
    self.detector = face_alignment.FaceAlignment(face_alignment.LandmarksType._2D,
  File "Z:\anaconda3\envs\sadtalker\lib\site-packages\face_alignment\api.py", line 77, in __init__
    self.face_detector = face_detector_module.FaceDetector(device=device, verbose=verbose, **face_detector_kwargs)
  File "Z:\anaconda3\envs\sadtalker\lib\site-packages\face_alignment\detection\sfd\sfd_detector.py", line 26, in __init__
    model_weights = torch.load(path_to_detector)
  File "Z:\anaconda3\envs\sadtalker\lib\site-packages\torch\serialization.py", line 699, in load
    with _open_file_like(f, 'rb') as opened_file:
  File "Z:\anaconda3\envs\sadtalker\lib\site-packages\torch\serialization.py", line 230, in _open_file_like
    return _open_file(name_or_buffer, mode)
  File "Z:\anaconda3\envs\sadtalker\lib\site-packages\torch\serialization.py", line 211, in __init__
    super(_open_file, self).__init__(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: '/root/.cache/torch/hub/checkpoints/s3fd-619a316812.pth'

[Ionaut]

Watching this

[vinthony]

fixed as in #125 if you have any problem you can reopen it.

[AlonDan]

I've downloaded the latest version and tried again,
and I get this error:

./checkpoints\epoch_20.pth
./checkpoints\auido2pose_00140-model.pth
./checkpoints\auido2exp_00300-model.pth
Traceback (most recent call last):
  File "inference.py", line 158, in <module>
    main(args)
  File "inference.py", line 59, in main
    audio_to_coeff = Audio2Coeff(audio2pose_checkpoint, audio2pose_yaml_path,
  File "D:\SadTalker\src\test_audio2coeff.py", line 35, in __init__
    self.audio2pose_model = Audio2Pose(cfg_pose, wav2lip_checkpoint, device=device)
  File "D:\SadTalker\src\audio2pose_models\audio2pose.py", line 15, in __init__
    self.audio_encoder = AudioEncoder(wav2lip_checkpoint, device)
  File "D:\SadTalker\src\audio2pose_models\audio_encoder.py", line 45, in __init__
    wav2lip_state_dict = torch.load(wav2lip_checkpoint, map_location=torch.device(device))['state_dict']
  File "Z:\anaconda3\envs\SadTalker\lib\site-packages\torch\serialization.py", line 713, in load
    return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
  File "Z:\anaconda3\envs\SadTalker\lib\site-packages\torch\serialization.py", line 938, in _legacy_load
    typed_storage._storage._set_from_file(
RuntimeError: unexpected EOF, expected 1630207 more bytes. The file might be corrupted.

[vinthony]

where are you download from？

[AlonDan]

where are you download from？

Based on these from the main page:
https://github.com/Winfredy/SadTalker#download-trained-models

I tried from Google Drive:
https://drive.google.com/drive/folders/1Wd88VDoLhVzYsQ30_qDVluQr_Xm46yHT?usp=sharing

And also from - Scrolling down to "Assets"
https://github.com/Winfredy/SadTalker/releases

I still get the same error,
Size files looks full based on the size mentioned in that list, so I don't think the files are corrupted, I also re-download and re-install on another computer just in case but I get the same exact same error.

How can I pass that error, I really want to try the local Gradio version.
I hope you can help, thanks ahead! 💙

[vinthony]

Sure, I will try to solve it and you can close some other similar issues by you, so we can focus on this one.

[vinthony]

According to the log, your wav2lip.pth file is not as unexpected. So please just try to solely download it and compare with the original file.

[vinthony]

it seems this issue has been solved. closed it.

[Asfandyar-Khan-2022]

I was having the exact same problem. Didn't realise you have to have a checkpoint folder within sad talker and download all the files. Extracted everything and it works now.

[romanr]

Just downloaded and trying clean install, same errors:

*** Error verifying pickled file from /Users/xx/Projects/stable-diffusion-webui/extensions/SadTalker/checkpoints/auido2pose_00140-model.pth
*** The file may be malicious, so the program is not going to read it.
*** You can skip this check with --disable-safe-unpickle commandline argument.
***
    Traceback (most recent call last):
      File "/Users/xx/Projects/stable-diffusion-webui/modules/safe.py", line 137, in load_with_extra
        check_pt(filename, extra_handler)
      File "/Users/xx/Projects/stable-diffusion-webui/modules/safe.py", line 83, in check_pt
        with zipfile.ZipFile(filename) as z:
      File "/opt/homebrew/Cellar/python@3.10/3.10.13/Frameworks/Python.framework/Versions/3.10/lib/python3.10/zipfile.py", line 1251, in __init__
        self.fp = io.open(file, filemode)
    FileNotFoundError: [Errno 2] No such file or directory: '/Users/xx/Projects/stable-diffusion-webui/extensions/SadTalker/checkpoints/auido2pose_00140-model.pth'

---
Traceback (most recent call last):
  File "/Users/xx/Projects/stable-diffusion-webui/extensions/SadTalker/src/test_audio2coeff.py", line 48, in __init__

[notbrianbob]

idk if you guys are having the same error I had. But for me when installing SadTalker, it puts the checkpoints folder in the scripts folder inside SadTalker.

All I did was move the checkpoints folder into the SadTalker main directory rather than in scripts and it fixed the issue.