Fair point.
So what about Tensor flow and some local LLM to do the job?
You just need to find a reliable LLM in HuggingFace, for example.
Fair point.
So what about Tensor flow and some local LLM to do the job?
You just need to find a reliable LLM in HuggingFace, for example.
Ok so from the error, you have a version of pillow that is incompatible.
You have to downgrade pillow to version 11.
That’s the first step.
EDIT: Sorry just saw the rest of your comment. Do you really have to use that tech?
You have other alternatives. Amazon AWS has a service for handwriting ocr, can’t remember the name though.
You can also have a look at this, but it’s paid: https://www.handwritingocr.com/
More ocr alternatives: https://github.com/michaelben/OCR-handwriting-recognition-libraries
+1 for tesseract. I knew about this one a while ago. It may not recognise all handwriting, but you can train it to get better at it.
So if you follow the instructions from the link again, can you make it work?
Ok excellent.
Let’s go step by step.
You say you tried to configure pip but failed.
What was the error? Any logs? Did you follow the steps from the link you provided?
Depending on your question, maybe you have a lemmy group (sublemmy?) for the tech you are working with.
Or you can try ask here.
Myself and others can try and help you.
I’m test driving Deezer as Spotify alternative.
Looks really promising. You can even import your Spotify playlists and music to Deezer.


US tech is a big pile of garbage.
All of it is to make you addicted, to track you, to influence you, to collect all sort of intel about you, and then use that against you. And they will serve you ads as the cherry on top.
For me they can all disappear and be gone. There are plenty of activities (internet or otherwise) that can be done without that pile of shit.
I have Proton with custom domain as email service, I have my own encrypted backup in an European VPS, have my own private cloud also in European VPS.
Don’t need US garbage.
Excellent. So let’s try to do that instead.
From what I can see from the docs, Gradio is used to build a web interface and have a nice UI to visualise things.
Let’s put Gradio aside for now and sort out Pytorch in Docker.
Select your LLM and make sure Pytorch works well with that.
If you run into trouble or get stuck let me known.
I’ll grab my laptop and try it myself.
nice starting point: https://rocm.docs.amd.com/projects/radeon-ryzen/en/latest/docs/install/installrad/wsl/install-pytorch.html