search

AIGC-Audio / AudioGPT

AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
https://huggingface.co/spaces/AIGC-Audio/AudioGPT
Other
10.04k stars 863 forks source link

Requires CUDA #56

Closed lkraider closed 1 year ago

lkraider commented 1 year ago

I am trying to run it on a MacBook Air M1.

After installing and trying to run, I get the error:

| /opt/homebrew/anaconda3/envs/audiogpt/lib/python3.8/site-packages/torch/cuda/__init__.py:211 in  │
│ _lazy_init                                                                                       │
│                                                                                                  │
│   208 │   │   │   │   "Cannot re-initialize CUDA in forked subprocess. To use CUDA with "        │
│   209 │   │   │   │   "multiprocessing, you must use the 'spawn' start method")                  │
│   210 │   │   if not hasattr(torch._C, '_cuda_getDeviceCount'):                                  │
│ ❱ 211 │   │   │   raise AssertionError("Torch not compiled with CUDA enabled")                   │
│   212 │   │   if _cudart is None:                                                                │
│   213 │   │   │   raise AssertionError(                                                          │
│   214 │   │   │   │   "libcudart functions unavailable. It looks like you have a broken build?   │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
AssertionError: Torch not compiled with CUDA enabled
rxtrippy commented 1 year ago

AudioGPT uses large scale models so its probably a good idea to use a GPU with CUDA Cores to speed up the process. If your still having trouble and you dont mind long wait times, you can update the torch,device to the 'cpu' instead of 'cuda[0]' or"cuda[1]". I wouldnt recommend though, run the tool through GPU instance if all else fails

lkraider commented 1 year ago

Replacing device="cuda:0" with device="mps" seems to work for initializing torch on the mac M1.