LLMs are not the type of model to use for this task. There are more specialized models that have much higher accuracy and full results. You can probably find the latest by looking around the OCR ecosystem.

▲

WillAdams 6 hours ago | parent | next [-]

A co-worker in a different program whose invoicing was much simpler and more straight-forward tried to automate this using OCR and Python and had a higher error rate and still had to set hand-written checks aside to handle manually.

I couldn't find an OCR system which was:

- free/affordable

- able to cope with arbitrary check sizes/hand-written checks and my occasional need to arrange multiple invoices in a stack with the check rotate 90 degrees so that all the numbers are visible

- which would capture the data from a scan in such a way that it could be easily used to rename the file

If you know of a system which is flexible enough to do this which is essentially free, let me know.

	▲	verdverm 6 hours ago \| parent [-]
		llm/transformers may actually be better than prior methods (not my area of expertise) I did see a talk recently of fine-tuning a small LLM specifically for receipt transcription: https://www.youtube.com/watch?v=vDyxCHl-p8s https://github.com/fw-ai/cookbook/tree/main/training/case-st... HF has OCR LLM based models too, eg: https://huggingface.co/baidu/Unlimited-OCR

▲

youre-wrong3 6 hours ago | parent | prev [-]

[dead]