Introducing OCRCourse! ๐ŸŽ‰

Hey everyone,

Iโ€™m excited to introduce OCRCourse! By utilizing advanced OCR pretraining with grounding capabilities, weโ€™re pushing the boundaries of parsing-free methods for text recognition. Our data will be open-sourced soon, and both the model and paper are on the way!

Stay tuned for updates! :star2:

Hereโ€™s an example running on a mobile emulator. :iphone::computer: :