Update paddlepaddle OCR models
Open
cloudy-sfu
opened this issue 2 years ago
•
2 comments
- [x] CN model: https://paddleocr.bj.bcebos.com/PP-OCRv4/chinese/ch_PP-OCRv4_rec_infer.tar
- [x] EN model: https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar
- [x] Support language selection (unified to tesseract OCR)
- [ ] Simplify model downloading process (remove "parse_lang" and dictionary lookup process).
- [ ] Download with progress bar (improve "network" module).
- [ ] Fine language fixing (do not delete unrelated models).
- [ ] ~~Remove dependency to the "mklml" library. If necessary, migrate to ONNX model and remove "paddlepaddle" dependencies.~~
- [x] Wait fixing: https://github.com/PaddlePaddle/Paddle/issues/61709