rednote-hilab/dots.ocr
Image-Text-to-Text • Updated
• 206k • 1.27k
OCR Models 👀️📃
-
-
reducto/RolmOCR
Image-Text-to-Text • Updated • 2.7k • 583 -
numind/NuMarkdown-8B-Thinking
Image-to-Text • Updated • 38.1k • 445 -
ChatDOC/OCRFlux-3B
Image-Text-to-Text • Updated • 1.83k • 366 -
echo840/MonkeyOCR
Image-Text-to-Text • Updated • 338 • 514 -
allenai/olmOCR-7B-0225-preview
Image-Text-to-Text • 8B • Updated • 17.7k • 706 -
allenai/olmOCR-7B-0725-FP8
Image-Text-to-Text • 8B • Updated • 1.17k • 18 -
allenai/olmOCR-7B-0725
Image-Text-to-Text • 8B • Updated • 570 • 64 -
allenai/olmOCR-7B-0225-preview-FP8
Image-Text-to-Text • 8B • Updated • 863 • 9 -
Super OCRs Demo
🧪38Experiment with small super OCR models here.
-
prithivMLmods/Camel-Doc-OCR-080125
Image-Text-to-Text • 8B • Updated • 373 • 8 -
prithivMLmods/Camel-Doc-OCR-062825
Image-Text-to-Text • 8B • Updated • 39 • 13 -
prithivMLmods/Perseus-Doc-VL-0712
Image-Text-to-Text • 8B • Updated • 1 • 3 -
prithivMLmods/Megalodon-OCR-Sync-0713
Image-Text-to-Text • 4B • Updated • 60 • 4 -
nanonets/Nanonets-OCR-s
Image-Text-to-Text • 4B • Updated • 51.9k • 1.59k -
unsloth/Nanonets-OCR-s-GGUF
Image-Text-to-Text • 3B • Updated • 3.35k • 59 -
typhoon-ai/typhoon-ocr-7b
Image-Text-to-Text • 8B • Updated • 115k • 77 -
pyannote/segmentation-3.0
Voice Activity Detection • Updated • 15M • 830 -
DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception
Paper • 2410.12628 • Published • 41 -
DocLLM: A layout-aware generative language model for multimodal document understanding
Paper • 2401.00908 • Published • 189 -
NuMarkdown 8b Thinking
👁62Reasoning model specialized for OCR/Markdown generation.
-
NAMAA-Space/Qari-OCR-0.2.2.1-VL-2B-Instruct
Image-Text-to-Text • Updated • 2.75k • 21 -
Ocrbench Leaderboard
🏆216Show OCRBench leaderboard rankings for OCR models
-
OCRBenchv2 Leaderboard
🏆46Display OCRBench leaderboard for text recognition models
-
OCR Time Machine
📚66Extract text from images and XML files using OCR models
-
AIDC-AI/Ovis2.5-9B
Image-Text-to-Text • 9B • Updated • 6.49k • 304