scan, split, OCR, prepare for LLM
Vous ne pouvez pas sélectionner plus de 25 sujets Les noms de sujets doivent commencer par une lettre ou un nombre, peuvent contenir des tirets ('-') et peuvent comporter jusqu'à 35 caractères.
Evgeniy Ierusalimov a154a1627f updated PaddleOCR with PPv6, introduced helping param --main-lang, remove local llm qwen2.5:7b due to hallucinations il y a 3 jours
..
latex updated PaddleOCR with PPv6, introduced helping param --main-lang, remove local llm qwen2.5:7b due to hallucinations il y a 3 jours
markdown code refactoring il y a 4 jours
ocr updated PaddleOCR with PPv6, introduced helping param --main-lang, remove local llm qwen2.5:7b due to hallucinations il y a 3 jours
postprocess updated PaddleOCR with PPv6, introduced helping param --main-lang, remove local llm qwen2.5:7b due to hallucinations il y a 3 jours
split updated PaddleOCR with PPv6, introduced helping param --main-lang, remove local llm qwen2.5:7b due to hallucinations il y a 3 jours
__init__.py initial release with base split functionality il y a 1 semaine
cli_utils.py OCR script with engines SuryaOCR and PaddleOCR il y a 5 jours
env.py refactored code for modularity, SOLID, DRY, KISS il y a 5 jours
image_ocr.py updated PaddleOCR with PPv6, introduced helping param --main-lang, remove local llm qwen2.5:7b due to hallucinations il y a 3 jours
image_prepare.py added --denoise option; border is now 5 pix by default il y a 3 jours
image_utils.py code refactoring il y a 4 jours
models.py code refactoring il y a 4 jours