Saeid Seyfi

Handwritten line recognizer for Persian / Arabic / English text plus math symbols, fine-tuned on the saeidseyfi/khattat dataset (line crops, input 32x256, max 88 label chars). CPU (2-core) budget fine-tune; decoder+head trained, STR backbone frozen The training pipeline is time-budgeted and fully resumable — continuing on a GPU with the same script converges substantially further. - best.pt -- model checkpoint (state dict + vocab) - vocab.txt -- 176-char vocabulary (fa / ar / en / digits / math) - demokhattatparseq.mp4 -- demo: test lines, ground truth vs prediction - evalreport.json, log.txt, worstsamples.json -- metrics

A from-scratch hybrid OCR pipeline for the saeidseyfi/khattat dataset, built by saeidseyfi from 100% free, offline components — no training required, no paid APIs. 1. OpenCV preprocessing — upscale, Otsu/adaptive binarization, deskew, morphology 2. EasyOCR (fa+ar+en) — CRAFT detection + CRNN recognition 3. Tesseract 5 (tessdatabest: fas / ara / eng) — LSTM models with word confidences 4. Confidence ensemble — script detection + weighted candidate selection + language normalization 5. pix2tex (LaTeX-OCR) for math formulas — ViT -> LaTeX + math-token candidate scoring 6. OpenCV contour classification for hand-drawn shapes (10 classes) 7. Caption OCR — first ink cluster below the shape -> en…