Multilingual OCR and Image-to-Text
11 repos
Optical character recognition systems and image-to-text models supporting multiple languages. The cluster centers on deep learning approaches to document analysis and text extraction, with repos like DeepSeek-OCR and Unlimited-OCR representing core implementations using transformer-based architectures and modern ML frameworks. Tools here handle everything from basic character recognition to structured document understanding across diverse language scripts.
Python · 2
safetensors ·11,885
image-text-to-text ·11,587
multilingual ·11,276
custom_code ·11,067
vision-language ·10,923
transformers ·10,324
eval-results ·10,311
feature-extraction ·8,897
deepseek_vl_v2 ·4,492
deepseek ·4,492
