K_OCR v0.1
WASM ready
GitHub ↗
100% client-side · nothing leaves your device

Read scanned documents. Right in your browser.

Drop a flat page or screenshot in Khmer/English.

Drop an image, or click to browse
PNG · JPG · WEBP - processed locally
First scan is slow: the OCR models (~37 MB) download and load on demand. Later scans use the local cache and are fast. Please be patient.
Extracted text
Nothing scanned yet.