# Multilingual OCR

PP-OCRv4_mobile_det is an efficient text detection model optimized for mobile devices developed by the PaddleOCR team, suitable for deployment on edge devices.

PP-OCRv5_mobile_rec is the latest generation of text line recognition model developed by the PaddleOCR team. It supports the recognition of four languages: Simplified Chinese, Traditional Chinese, English, and Japanese, and is suitable for various complex text scenarios.

PP-OCRv5_server_rec is the latest generation of text line recognition model developed by the PaddleOCR team, supporting the recognition of multilingual and complex text scenarios.

An image-to-text model fine-tuned based on Microsoft Florence-2 foundation model, supporting Swedish and English, specializing in historical handwritten text recognition and optical character recognition.

An image text-to-text model built on Mistral-Small-3.1-24B-Instruct-2503, supporting multilingual processing

InternVL3-2B is an advanced Multimodal Large Language Model (MLLM) developed by OpenGVLab, featuring exceptional multimodal perception and reasoning capabilities, supporting tool usage, GUI agents, industrial image analysis, 3D visual perception, and more.

PaliGemma 2 is an upgraded vision-language model based on Gemma 2, supporting multilingual image-text input and text output, specifically designed for vision-language tasks

The int4 quantized version of MiniCPM-o 2.6, significantly reducing GPU VRAM usage while supporting multimodal processing capabilities.

PaliGemma 2 is an upgraded vision-language model launched by Google, combining the capabilities of Gemma 2 and SigLIP vision models, supporting multilingual image-text interaction tasks.

PaliGemma 2 is a vision-language model based on Gemma 2, supporting image+text input and text output, suitable for various vision-language tasks.

PaliGemma 2 is a vision-language model based on Gemma 2, supporting image and text input to generate text output, suitable for various vision-language tasks.

PaliGemma 2 is a vision-language model based on Gemma 2, supporting image and text inputs with text generation output, suitable for various vision-language tasks.

A Devanagari optical character recognition model based on the TrOCR architecture, specifically fine-tuned for Nepali/Devanagari script

A Thai and English optical character recognition model fine-tuned from the TrOCR base handwriting model, excelling in processing handwritten text line images

This model is specifically trained for Urdu OCR tasks and is most suitable for processing single-line Urdu text images, primarily focusing on printed text.

This is a TrOCR-based medieval cursive script recognition model, specifically designed for identifying handwritten texts in Latin, French, Italian, Spanish, and Catalan from the medieval period.

TrOCR-Ru is an optical character recognition model fine-tuned on synthetic datasets of Russian and English, based on microsoft/trocr-base-handwritten, focusing on image-to-text tasks.

TrOCR is a Transformer-based optical character recognition model designed to extract text content from images.

An OCR system based on Transformer architecture, specifically designed for recognizing Central Kurdish text, trained using synthetic data.

Pix2Struct is a visual question answering model fine-tuned for OCR-VQA tasks, capable of parsing textual content in images and answering questions

Pix2Struct is an image encoder-text decoder model trained on image-text pairs, supporting various tasks including image captioning and visual question answering.

Pix2Struct is an image encoder-text decoder model trained on image-text pairs for multitasking, specifically fine-tuned for chart question answering tasks

This model is a fine-tuned version of donut-base on a Latvian receipt dataset, primarily used for receipt image processing tasks

An optical character recognition (OCR) model based on TensorFlow 2 and PyTorch, supporting multilingual text detection and recognition

Optical Character Recognition technology based on TensorFlow 2 and PyTorch, supporting multilingual document recognition