YomiNinja is an application for extracting text from any type of visual content.
merged_github.mp4
The extracted text overlays the original content, allowing for quick look-ups with pop-up dictionaries like Yomichan.
It minimizes distractions and simplifies the process of looking up unfamiliar words.
This feature is especially beneficial for language learners who study through videos or games.
YomiNinja is perfect for:
- Language learners who study through games, videos, or any other visual content.
- Anyone who values a distraction-free, efficient way to look up unfamiliar words.
- Users looking for seamless text extraction and workflow improvement.
You need Windows 10 or 11 and VCRedist Runtimes installed.
Download and install the latest release.
- Text extraction from the entire screen or specific window.
- Automatic text copying.
- Built-in pop-up dictionary.
- Text extraction from snip.
- Text extraction from custom templates (define extraction patterns for specific use cases).
- Automatic refresh text extraction.
- Anki integration.
- History.
- Text translation.
- Support for more OCR engines.
YomiNinja currently supports text extraction in:
- English
- Japanese
- Chinese
- Korean
Currently, PaddleOCR is used for text extraction, which generally produces very good results in Asian languages such as Chinese or Japanese.
It supports dozens of languages, that will be integrated into this application in the future.
- Clone git repository
git clone https://github.com/matt-m-o/YomiNinja.git && cd YomiNinja
- Download and extract the latest build of PPOCR-Inference-Service inside the "./bin/ppocr" directory.
- Install node modules
cd yomininja-e && npm install
- Generate gRPC Protobuf types
npm run grpc-types
- Build distribution
npm run dist