TrOCR Transformer-based Optical Character Recognition Microsoft Hugging Face TrOCR Demo

In this video I look at TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models. The TrOCR model was proposed in TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models by Minghao Li, Tengchao Lv, Lei Cui, Yijuan Lu, Dinei Florencio, Cha Zhang, Zhoujun Li, Furu Wei. TrOCR consists of an image Transformer encoder and an autoregressive text Transformer decoder to perform optical character recognition (OCR). I also show a demo of TrOCR using a Google Collab notebook
If you like such content please subscribe to the channel here:
https://www.youtube.com/c/RitheshSreenivasan?sub_confirmation=1

If you like to support me financially, It is totally optional and voluntary. Buy me a coffee here: https://www.buymeacoffee.com/rithesh
Relevant Links:
https://arxiv.org/abs/2109.10282
https://huggingface.co/docs/transformers/model_doc/trocr
https://colab.research.google.com/drive/1LBQtUdUXBeo4m6zfh270ae1ntjEN-OPT?usp=sharing
https://huggingface.co/spaces/nielsr/TrOCR-handwritten
https://github.com/microsoft/unilm/tree/master/trocr

Видео TrOCR Transformer-based Optical Character Recognition Microsoft Hugging Face TrOCR Demo канала Rithesh Sreenivasan