CUDA runs out of memory.

[Aryandrag]

I keep running into this error:
torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 26.00 MiB. GPU 0 has a total capacity of 4.00 GiB of which 0 bytes is free. Of the allocated memory 6.50 GiB is allocated by PyTorch, and 333.05 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)

What could I do to fix this?
Really sorry if this is a stupid question.

[spicytigermeat]

When are you running into this error?

If this is during transcription, you should choose a smaller Whisper model in the settings.