URGENT: Can't run on GPU despite it beeing installed correctly?

[Zunnen]

I've tried to install all of it again and also testes if torch is installed and recognizing the GPU, which it is.

C:\Users\Zunnen>python
Python 3.10.8 (tags/v3.10.8:aaaf517, Oct 11 2022, 16:50:30) [MSC v.1933 64 bit (AMD64)] on win32
Type "help", "copyright", "credits" or "license" for more information.

import torch
torch.cuda.is_available()
True

Yet when I try to transcribe a file in whisper it tells me that

C:\Users\Zunnen>whisper leslie_freetime.mp3 --model base --device cuda Traceback (most recent call last): File "C:\Users\Zunnen\AppData\Local\Programs\Python\Python310\Scripts\whisper-script.py", line 33, in <module> sys.exit(load_entry_point('whisper==1.0', 'console_scripts', 'whisper')()) File "C:\Users\Zunnen\AppData\Local\Programs\Python\Python310\lib\site-packages\whisper\transcribe.py", line 304, in cli model = load_model(model_name, device=device, download_root=model_dir) File "C:\Users\Zunnen\AppData\Local\Programs\Python\Python310\lib\site-packages\whisper\__init__.py", line 106, in load_model checkpoint = torch.load(fp, map_location=device) File "C:\Users\Zunnen\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\serialization.py", line 712, in load return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args) File "C:\Users\Zunnen\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\serialization.py", line 1049, in _load result = unpickler.load() File "C:\Users\Zunnen\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\serialization.py", line 1019, in persistent_load load_tensor(dtype, nbytes, key, _maybe_decode_ascii(location)) File "C:\Users\Zunnen\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\serialization.py", line 1001, in load_tensor wrap_storage=restore_location(storage, location), File "C:\Users\Zunnen\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\serialization.py", line 970, in restore_location return default_restore_location(storage, map_location) File "C:\Users\Zunnen\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\serialization.py", line 175, in default_restore_location result = fn(storage, location) File "C:\Users\Zunnen\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\serialization.py", line 152, in _cuda_deserialize device = validate_cuda_device(location) File "C:\Users\Zunnen\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\serialization.py", line 136, in validate_cuda_device raise RuntimeError('Attempting to deserialize object on a CUDA ' 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.

I dont know what to do honestly

[FurkanGozukara]

You can watch my tutorial video i run it on windows OS with GPU

https://www.youtube.com/watch?v=msj3wuYf3d8

[Zunnen]

well the video is good but it doesen't answer my problem. so dont selfpromote

[richardburleigh]

@Zunnen People are taking time to help you for free, please be respectful.

Regarding your issue, sometimes Conda is better at interacting with local drivers. You can check 4 Steps to install Anaconda and PyTorch on Windows 10.

[Sharrnah]

Can you maybe provide more info about your GPU?
like: what GPU do you have? What Driver Version? What CUDA Version?

Maybe try to run pip install with -U argument to have it update dependencies in case the versions are wrong.

Check if the whisper command you are running is actually using the correct python version. Maybe run it with python -m whisper to have it use your python version.

Let me know if anything helped you.

[Zunnen]

So I have a RTX 2080 Super and CUDA is on Version 11.8. Driver should also be new enough.

You may be right about using the wrong python tho. Can you eleborate on how i specify which one it should be using?
Thanks so far tho

[Sharrnah]

Sorry. i am still relatively new to Python.
You can maybe try to find where the whisper command is actually located by running Get-Command whisper in a PowerShell.
Or see if it returns multiple Python versions when running Get-Command python.