minlik/docllm-yi-34b
Text Generation β’ 38B β’ Updated β’ 31 β’ 1
Document AI
-
-
JinghuiLuAstronaut/DocLLM_baichuan2_7b
Text Generation β’ 9B β’ Updated β’ 22 β’ 5 -
docling-project/docling-models
Updated β’ 1.47M β’ 231 -
DocLayout YOLO
π196Demo for DocLayout-YOLO
-
DocQuery βΒ Document Query Engine
π¦289 -
impira/layoutlm-document-qa
Document Question Answering β’ 0.1B β’ Updated β’ 347k β’ 1.21k -
HURIDOCS/pdf-document-layout-analysis
Updated β’ 316 β’ 137 -
HuggingFaceM4/Docmatix
Viewer β’ Updated β’ 2.55M β’ 18.6k β’ 318 -
docling-project/DocLayNet-v1.1
Viewer β’ Updated β’ 63.5k β’ 2.23k β’ 28 -
cmarkea/doc-vqa
Viewer β’ Updated β’ 12.1k β’ 569 β’ 19 -
google/paligemma-3b-pt-224
Image-Text-to-Text β’ 3B β’ Updated β’ 267k β’ 663 -
Noise-Aware Training of Layout-Aware Language Models
Paper β’ 2404.00488 β’ Published β’ 9 -
Paligemma2 Vqav2
π¨47PaliGemma2 LoRA finetuned on VQAv2
-
OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations
Paper β’ 2412.07626 β’ Published β’ 30 -
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion
Paper β’ 2503.11576 β’ Published β’ 180 -
docling-project/SmolDocling-256M-preview
Image-Text-to-Text β’ 0.3B β’ Updated β’ 28.9k β’ 1.64k -
Towards Effective Extraction and Evaluation of Factual Claims
Paper β’ 2502.10855 β’ Published β’ 3 -
ByteDance/Dolphin
Image-Text-to-Text β’ 0.4B β’ Updated β’ 318 β’ 519 -
nanonets/Nanonets-OCR-s
Image-Text-to-Text β’ 4B β’ Updated β’ 12.6k β’ 1.6k -
Nanonets Ocr S
π35https://nanonets.com/research/nanonets-ocr-s/
-
numind/NuMarkdown-8B-Thinking
Image-to-Text β’ 8B β’ Updated β’ 1.43k β’ 498 -
dots-studio/dots.ocr
Image-Text-to-Text β’ 3B β’ Updated β’ 503k β’ 1.35k -
Multimodal OCR2
π»143FireRed / Nanonets / Monkey / Thyme / Typhoon / SmolDocling
-
microsoft/trocr-small-handwritten
Image-to-Text β’ Updated β’ 81.8k β’ 73 -
ibm-granite/granite-docling-258M
Image-Text-to-Text β’ 0.3B β’ Updated β’ 283k β’ 1.29k -
granite-docling-258M demo
π282Convert and query documents from images
-
Granite Docling 258M WebGPU
π£162Convert document images to HTML
-
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text β’ 1.0B β’ Updated β’ 7.92k β’ 1.68k -
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Paper β’ 2510.14528 β’ Published β’ 129 -
PaddleOCR-VL Online Demo
π255Extract and visualize text, tables, formulas, and charts from images
-
nanonets/Nanonets-OCR2-3B
Image-Text-to-Text β’ 4B β’ Updated β’ 230k β’ 517 -
nanonets/Nanonets-OCR2-1.5B-exp
Image-Text-to-Text β’ 2B β’ Updated β’ 263 β’ 51 -
deepseek-ai/DeepSeek-OCR
Image-Text-to-Text β’ 3B β’ Updated β’ 2.09M β’ β’ 3.46k -
lightonai/LightOnOCR-1B-1025
Image-to-Text β’ 1B β’ Updated β’ 20.3k β’ 256 -
HuggingFaceFW/ocr-annotations
Viewer β’ Updated β’ 1.62k β’ 61 β’ 20 -
HuggingFaceFW/finepdfs_lang_classification
Viewer β’ Updated β’ 3.08M β’ 9.99k β’ 5 -
HuggingFaceFW/finepdfs
Viewer β’ Updated β’ 476M β’ 79.1k β’ 951 -
microsoft/Fara-7B
Image-Text-to-Text β’ 8B β’ Updated β’ 2.82k β’ 624 -
tencent/HunyuanOCR
Image-Text-to-Text β’ 1B β’ Updated β’ 821k β’ 842 -
HunyuanOCR Technical Report
Paper β’ 2511.19575 β’ Published β’ 24 -
ApsaraStackMaaS/EvoQwen2.5-VL-Retriever-7B-v1
Visual Document Retrieval β’ 8B β’ Updated β’ 283 β’ 18 -
bevaya/GutenOCR-3B
Image-Text-to-Text β’ 4B β’ Updated β’ 252 β’ 27 -
bevaya/GutenOCR-7B
Image-Text-to-Text β’ 8B β’ Updated β’ 151 β’ 26 -
microsoft/VibeVoice-ASR
Automatic Speech Recognition β’ 9B β’ Updated β’ 671k β’ 1.32k -
Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign
Text-to-Speech β’ 2B β’ Updated β’ 456k β’ 453 -
Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
Text-to-Speech β’ 2B β’ Updated β’ 1.9M β’ β’ 2.18k -
Qwen3-TTS Technical Report
Paper β’ 2601.15621 β’ Published β’ 80 -
Qwen3-TTS Demo
π2.35kGenerate speech from text with voice design, cloning, or presets
-
ibm-granite/granite-vision-3.3-2b-chart2csv-preview
Image-Text-to-Text β’ 3B β’ Updated β’ 1.39k β’ 17 -
Qwen/Qwen3-ASR-1.7B
Automatic Speech Recognition β’ 2B β’ Updated β’ 1.35M β’ β’ 1.21k -
AttentionRetriever: Attention Layers are Secretly Long Document Retrievers
Paper β’ 2602.12278 β’ Published β’ 2 -
DiffusionGemma vs Gemma-4 β Post-OCR Correction
π°23Diffusion vs autoregressive LLM on historical OCR cleanup
-
lightonai/LightOnOCR-2-1B
Image-Text-to-Text β’ 1B β’ Updated β’ 602k β’ β’ 848 -
BHL OCR Leaderboard
π20OCR & VLM character error rates on 18thβ19th-c. book pages
-
small-models-for-glam/kraken-ppocrv6-medium
Image-to-Text β’ Updated β’ 18 -
Unlimited OCR
π498Extract text from images or PDFs with real-time streaming OCR
-
baidu/Unlimited-OCR
Image-Text-to-Text β’ 3B β’ Updated β’ 2.77M β’ 4.9k -
mohit67890/imajev-4b
Image-Text-to-Text β’ Updated β’ 3.73k β’ 107 -
akhilaaa3/Jev-Omni
Text Classification β’ 12B β’ Updated β’ 5.94k β’ 434 -
neuphonic/neudecide
Audio Classification β’ Updated β’ 778 β’ 80 -
SoMarkAI/OXR-1.0
2B β’ Updated β’ 899 β’ 66