Microsoft's new open source Phi 3.5 vision model is really good at OCR/text extraction — even on handwriting! You can prompt it to extract tabular data as well.
— Dylan Freedman (@dylfreed) August 26, 2024
It's permissively licensed (MIT). Play around with it here: https://t.co/5onmYAwNu7 https://t.co/EE0caDnQYn pic.twitter.com/hjYieofnKw