breezedeus / Pix2Text

An Open-Source Python3 tool with SMALL models for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conversion of visual content into text-based representations. 80+ languages are supported.
https://p2t.breezedeus.com
MIT License
1.98k stars 188 forks source link

Spanish options #146

Open AlonsoFU opened 2 months ago

AlonsoFU commented 2 months ago

Hi! i am starting to use the library, but i want to work with spanish configurations. Is there a way to do that? Which is the best configuration? Much much thanks in advance.

AlonsoFU commented 2 months ago

To add a little more context to the problem, there are special spanish characters that the model is not registering. For example the characters: ñ, á, é, í...

breezedeus commented 2 months ago

Hi, Pix2Text uses the EasyOCR text recognition engine for Spanish language support. I cannot add recognition for other Spanish characters on top of it. Sorry. You can consider replacing EasyOCR with another Spanish OCR engine.