How to make it work with CUDA enabled GPU? GTX 1050 Ti- 4GB #47
-
edit : i prepared an excellent tutorial video after my all experience : https://www.youtube.com/watch?v=q8Q8CCDdSKo I have installed python 3.9.9 It installed everything and it works fine However later i learned that I have to installed CUDA enabled Torch For that what do I need to do ? First run this command? Then which version to install?
Any help appreciated I am using pip and Windows 10 |
Beta Was this translation helpful? Give feedback.
Replies: 6 comments 10 replies
-
I found this on the github for pytorch: pytorch/pytorch#30664 (comment) I just modified it to meet the new install instructions. I'm running Windows 11. Seems that you have to remove the cpu version first to install the gpu version. That's my understanding of it at least. pip uninstall torch After doing this I was able to run the following command ( choose whatever model fits your needs best ): |
Beta Was this translation helpful? Give feedback.
-
It is much easier using Docker for this. Assuming you have the latest Nvidia driver and Docker Engine installed here is a suggested example Dockerfile that works fine for me:
Build using the command: To run a container using the current directory as input:
Enjoy the ride |
Beta Was this translation helpful? Give feedback.
-
These steps are tested on Windows 11 with CUDA 11.7 + torch 1.12.1
Reference: Start Locally | PyTorch |
Beta Was this translation helpful? Give feedback.
-
For Windows 11, an important step for me was to figure out the version of CUDA installed by the Driver as outlined here, not installing the matching version caused me trouble. By calling this command: |
Beta Was this translation helpful? Give feedback.
-
Here is my approach on Windows 10 with 2080 Ti.
|
Beta Was this translation helpful? Give feedback.
-
Additionally, do below if the issue is not fixed after following the answer post here.
|
Beta Was this translation helpful? Give feedback.
I found this on the github for pytorch: pytorch/pytorch#30664 (comment)
I just modified it to meet the new install instructions. I'm running Windows 11. Seems that you have to remove the cpu version first to install the gpu version. That's my understanding of it at least.
pip uninstall torch
pip cache purge
pip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu116
After doing this I was able to run the following command ( choose whatever model fits your needs best ):
whisper "audio.wav" --model medium --device cuda