苹果电脑提示GPU异常

[October27]

RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU. 1、请问怎么才能在GPU运行 2、参考如下链接，改成CPU后依然生成失败 https://github.com/OpenTalker/SadTalker/issues/346 3、新的错误提示如下，请问如何解决

(sadtalker) xx@xxdeMacBook-Pro SadTalker % python inference.py --driven_audio /Users/xxa/Documents/aigc/chinese_poem1.wav\ --source_image /Users/xxa/Documents/aigc/男1.png \ --enhancer gfpgan OMP: Info #276: omp_set_nested routine deprecated, please use omp_set_max_active_levels instead. using safetensor as default 3DMM Extraction for source image landmark Det:: 100%|████████████████████████████████████████| 1/1 [00:02<00:00, 2.69s/it] 3DMM Extraction In Video:: 100%|████████████████████████████| 1/1 [00:00<00:00, 6.54it/s] zsh: segmentation fault python inference.py --driven_audio --source_image --enhancer gfpgan (sadtalker) xx@xxdeMacBook-Pro SadTalker % /Users/xxa/anaconda3/envs/sadtalker/lib/python3.8/multiprocessing/resource_tracker.py:216: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown warnings.warn('resource_tracker: There appear to be %d '

[October27]

@vinthony 请帮忙看看谢谢，是我电脑不支持吗

[derek1981]

upgrade librosa to 0.10.1 ,it`s work for me

[shisaq]

upgrade librosa to 0.10.1 ,it`s work for me

Are you using SadTalker client or Stable Diffusion extension? How did you manage to upgrade librosa? Thanks