RDLTR

Short for Read Later. Save links from any browser or phone. Click to save, read to clear. The full tour

One line. Many voicesSeek and you shall find

huggingface.co favicondatalab-to/surya-ocr-2

kept by

Surya OCR 2 is a 650M-parameter vision-language model achieving 83.3% on olmOCR-bench and 87.2% on a 91-language benchmark, offering layout analysis, table recognition, and OCR in a single model.