Which model to select

[John6666]

If I assume that the document is an image, it would be around here.
If it’s text information, I think Qwen 2.5 0.5B or SmoLLM would work.

Accelerating Document AI

Improving Key-Value Pair Extraction with LayoutLM and LiLT on Custom OCR Dataset

I am working on an OCR project to perform document understanding on a specific type of document with a fixed layout (e.g., mandate forms). The layout has minor variations across images. My goal is to accurately extract key-value pairs and output them in JSON format. What I Have Done Dataset Preparation: I created a dataset of 231 annotated images in FUNSD format using the UBIAI tool. The annotations include bounding boxes and labels (KEY, VALUE). Models Used: I fine-tuned both LayoutLMv3 …

Which Model Should I Choose: TrOCR, TrOCR + LayoutLM, or Donut?

I am developing a web application to process a collection of scanned domain-specific documents with five different types of documents, as well as one type of handwritten form. The form contains a mix of printed and handwritten text, while others are entirely printed but all of the other documents would contain the name of the person. Key Requirements: Search Functionality – Users should be able to search for a person’s name and retrieve all associated scanned documents. Key-Value Pair Extracti…