Openlearnia Browser OCR

Page images stay local — model weights download on opt-in (size disclosed above the gate)

RapidOCR English

Fast plain-text OCR without WebGPU. Adapted from client-ocr / RapidOCR (MIT + Apache-2.0).

1. Download model (~14 MB)

Loads RapidOCR English PP-OCRv4 (det+rec+cls) via ONNX Runtime Web from ModelScope. No WebGPU required. Orientation model is cached; MVP runs det+rec.

Model not loaded

2. Image or PDF

Drop a page image or PDF here or click to browse

PNG, JPG, WEBP, or PDF — one PDF page at a time

3. Plain text

  

Need 中文? Try RapidOCR Chinese. Need layout? Try Granite-Docling.