If this seems too complicated you can change Max to use google for speech-to-text instead in the .env
- download the cuda toolkit:
https://developer.nvidia.com/cuda-downloads - now to get the cudann files we need to get the latest version 8.9.7, which is here:
https://developer.nvidia.com/rdp/cudnn-archive - you will need to create an account with nvidia to get access to the download
- unzip cudann and copy all of the .dll files
- paste the .dll files in the toolkit\cuda\bin folder (for example:
C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.6\bin) - now we need to add those .dll's to your PATH, to do this hit the windows key and type "enviro",
- select "edit the system environment variables"
- select button on the bottom right "Environment Variables"
- in the lower window "System variables" find and select "Path"
- select "Edit"
- select "Browse"
- browse to the same location as step 4, where you just put the .dll files
- then select a ok a bunch of times and close out the menu
