TrOCR is an end-to-end text recognition approach with pre-trained image Transformer and text Transformer models, which leverages the Transformer architecture for both image understanding and wordpiece-level text generation. TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models, Minghao Li, Tengchao Lv, Lei Cui, Yijuan Lu, Dinei Florencio, Cha Zhang, Zhoujun Li, Furu Wei, A