Dots OCR
🏢
161
Extract and convert document layout to markdown with visual overlay
OCR
-
-
nvidia/Llama-Nemotron-VLM-Dataset-v1
Viewer • Updated • 2.86M • 2.92k • 168 -
loay/Arabic-OCR-Qwen2.5-VL-7B-Vision
Image-to-Text • 8B • Updated • 120 • 5 -
LiquidAI/LFM2-VL-1.6B
Image-Text-to-Text • 2B • Updated • 83.9k • 233 -
prithivMLmods/coreOCR-7B-050325-preview
Image-Text-to-Text • 8B • Updated • 498 • 15 -
ordaktaktak/Persian-OCR-230k
Viewer • Updated • 230k • 99 • 2 -
mohajesmaeili/Persian_Arabic_TextLine_Image_Ocr_Small
Viewer • Updated • 120k • 110 • 15 -
mohajesmaeili/Persian_Arabic_TextLine_Image_Ocr_Medium
Viewer • Updated • 791k • 337 • 18 -
hezarai/parsynth-ocr-200k
Viewer • Updated • 200k • 841 • 24 -
AliShafiee2003/persian-ocr-garshasp-70c
Viewer • Updated • 2.6M • 252 • 3 -
hezarai/parsynth-ocr-4m
Viewer • Updated • 4.15M • 142 -
Reza2kn/Bina-0.1-Koochik
Image-Text-to-Text • 0.7B • Updated • 1.47k • 32 -
lightonai/LightOnOCR-2-1B
Image-Text-to-Text • 1B • Updated • 189k • • 833 -
baidu/Unlimited-OCR
Image-Text-to-Text • 3B • Updated • 2.02M • 4.3k -
Arabic OCR Demos
🐢72Arabic OCR Models Demo
-
Manuscript OCR
📊5Extract and correct text from document images
-
GLM OCR Demo
📄122Multimodal OCR model for complex document understanding.
-
BHL OCR Leaderboard
📖17OCR & VLM character error rates on 18th–19th-c. book pages
-
Tibetan OCR Leaderboard
📜1Explore Tibetan OCR model rankings on the BDRC benchmark
-
Japanese OCR
⛩63Extract Japanese text from images
-
🖼️MultilingualOCR
👁55Extract text from images in multiple languages