These models perform optical character recognition, extracting text from images. They can help digitize text from scanned documents, photos, and other visual media.

Best for Extracting LaTeX Equations: mickeybeurskens/latex-ocr

If you frequently work with LaTeX equations in image form, the mickeybeurskens/latex-ocr model is the perfect tool. It specializes in recognizing LaTeX formatting, making it easy to convert equations from papers, slides, or handwritten notes into usable LaTeX code.

This model produces clean, accurate equation extractions that are ready to use in your documents. It’s a huge time-saver for researchers, students, and anyone else who needs to digitize mathematical notation.

Best for General Text Extraction: abiruyt/text-extract-ocr

For most other OCR tasks, we recommend the abiruyt/text-extract-ocr model. This versatile tool makes it simple to extract plain text from a wide variety of images.

Note that for equations or unusual formatting, our LaTeX OCR pick will likely produce better results. But in most cases, abiruyt/text-extract-ocr is the way to go.