HunyuanOCR
Breaks down how a one-billion-parameter OCR model completes detection, recognition and layout parsing in a single pass, and covers deployment for receipts, subtitles and multilingual image translation.
HunyuanOCR is Tencent Hunyuan's open end-to-end text recognition model, doing detection, recognition, layout parsing, field extraction and image translation in a single forward pass with roughly one billion parameters. It covers street scenes, handwriting and dense receipts or tables, and handles image translation across about fourteen languages. Weights, a technical report and inference examples are published for cloud and edge use.
