search

JarodMica / ai-voice-cloning

GNU General Public License v3.0
567 stars 127 forks source link

Does sample size affects the required amount of GPU memory? #94

Open thanhchauns2 opened 5 months ago

thanhchauns2 commented 5 months ago

Hi Jarods, just curious because when I selected the "High quality" option instead of "Ultra Fast", it showed:

torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 74344.76 GiB. GPU 0 has a total capacity of 23.99 GiB of which 0 bytes is free. Of the allocated memory 31.41 GiB is allocated by PyTorch, and 773.88 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation.  See documentation for Memory Management  (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)