PantsuDango/Dango-Translator
Dango Translator
Dango-Translator is an OCR translation system and multi-engine translation client designed to extract text from images or screens and replace it with translated content. It functions as an image text translator and real-time screen translator, utilizing optical character recognition to convert text between different languages automatically.
The software distinguishes itself through coordinate-based image typesetting and a glossary manager. These tools allow for the replacement of original image content with translated text in the same area and the use of specialized dictionaries to ensure consistent translation of specific terms and phrases.
The system supports real-time screen polling to monitor visual changes, plugin-based adapters for integrating various third-party translation services or local language models, and cloud-synced configuration to maintain user preferences across devices.
Features
- Image Text Translators - Extracts text from images and replaces it with translated content while preserving visual style and layout.
- Multilingual Text Processing - Processes and translates text across multiple languages using various translation engines and local models.
- Optical Character Recognition - Converts images of text into machine-encoded text using online or local recognition methods.
- Screen Text Extractors - Performs optical character recognition on arbitrary screen regions to extract non-selectable text.
- Real-Time Screen Translators - Provides real-time screen polling and OCR to translate and replace on-screen text instantly.
- Multi-Engine Clients - Connects to multiple third-party translation services and local language models for cross-language conversion.
- Translation API Integrations - Provides a client-side implementation to connect with various third-party translation services via APIs.
- Real-Time Screen Translators - Captures screen regions via optical character recognition and translates content in real time.
- Image Bounding Box Typesetting - Calculates text positioning and dimensions within images based on OCR bounding boxes for precise translation placement.
- Visual Change Polling - Continuously monitors defined screen regions for visual changes to trigger automatic text recognition and translation.
- Translation Term Mapping - Uses a glossary manager to ensure consistent translation of specialized terms and phrases.
- Translation - Supports importing and exporting specialized terminology lists to ensure consistency in automated translations.
- Model Adapter Plugins - Uses a standardized API wrapper to integrate various external translation services and local models as plugins.
