update docs

This commit is contained in:
maglore9900 2024-10-03 15:37:16 -04:00
parent 54f8f0177d
commit 9c9878abd9
2 changed files with 4 additions and 15 deletions

View File

@ -41,20 +41,9 @@ so basically the steps are pretty simple
> Note: If you are using faster-whisper and have an nvidia GPU you will need to download the cuda tool kit and cudann to leverage your GPU.
>
> If this seems too complicated you can change Max to use google for speech-to-text instead in the .env
> Instructions are [Here](docs/cuda.md)
>
> 1. download the cuda toolkit: `https://developer.nvidia.com/cuda-downloads`
> 2. download cudann: `https://developer.nvidia.com/cudnn-downloads`
> 3. unzip cudann and copy all of the .dll files
> 4. paste the .dll files in the toolkit\cuda\bin folder (for example: `C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.6\bin`)
> 5. now we need to add those .dll's to your PATH, to do this hit the windows key and type "enviro",
> 6. select "edit the system environment variables"
> 7. select button on the bottom right "Environment Variables"
> 8. in the lower window "System variables" find and select "Path"
> 9. select "Edit"
> 10. select "Browse"
> 11. browse to the same location as step 4, where you just put the .dll files
> 12. then select a ok a bunch of times and close out the menu
> If this seems too complicated you can change Max to use google for speech-to-text instead in the .env
# TOOLS

View File

@ -9,9 +9,9 @@ If this seems too complicated you can change Max to use google for speech-to-tex
7. select "edit the system environment variables"
8. select button on the bottom right "Environment Variables"
9. in the lower window "System variables" find and select "Path"
![](images/windows_env.png)
![](../images/windows_env.png)
10. select "Edit"
11. select "Browse"
12. browse to the same location as step 4, where you just put the .dll files
![](images/path.png)
![](../images/path.png)
13. then select a ok a bunch of times and close out the menu