OpenTalker / SadTalker

[CVPR 2023] SadTalker:Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
https://sadtalker.github.io/
Other
11.12k stars 2.08k forks source link

TypeError: 'ModelManager' object is not subscriptable #899

Open cxiaowen opened 1 month ago

cxiaowen commented 1 month ago

python app_sadtalker.py /home/xmg/anaconda3/envs/sadtalker/lib/python3.10/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: libtorch_cuda_cu.so: cannot open shared object file: No such file or directory warn(f"Failed to load image Python extension: {e}") Traceback (most recent call last): File "/media/xmg/KINGSTON_4T/QY/SadTalker-main/app_sadtalker.py", line 107, in demo = sadtalker_demo() File "/media/xmg/KINGSTON_4T/QY/SadTalker-main/app_sadtalker.py", line 49, in sadtalker_demo tts_talker = TTSTalker() File "/media/xmg/KINGSTON_4T/QY/SadTalker-main/src/utils/text2speech.py", line 8, in init model_name = TTS().list_models()[0] TypeError: 'ModelManager' object is not subscriptable 这个是什么原因