datalab-to/indra: fast cpu OCR: line detection, CTC recognition, reading order, markdown
Read the original at github.com→★ 1178 stars
Original headline: "datalab-to/indra: 1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy"
Coverage timeline
- Oct 13, 11:07 UTC GitHub Trending (AI) lead source datalab-to/indra: 1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy