# High-precision text recognition

A dedicated text line recognition model for Devanagari in the PP-OCRv3_rec series developed by the PaddleOCR team, supporting Devanagari recognition with an average accuracy of 96.44%.

PP-OCRv4_server_rec is a text line recognition model in the PP-OCRv4_rec series developed by the PaddleOCR team. It supports text line recognition in general Chinese and English scenarios, mainly focusing on Chinese.

A document text recognition model enhanced based on PP-OCRv4_server_rec, supporting over 15,000 characters, including traditional Chinese characters, Japanese characters, and special symbols.

Qaari 0.1 Urdu is a model optimized for optical character recognition (OCR) of Urdu text. It is fine-tuned based on Qwen/Qwen2-VL-2B and has significantly improved Urdu OCR capabilities.

A model focused on Vietnamese speech recognition, supporting high-accuracy speech-to-text conversion.