support for Baidu's PaddleOCR (supports gpu, newer, and more actively developed compared to Tesseract)

apm1467 / videocr

Extract hardcoded subtitles from videos using machine learning

MIT License

506 stars 117 forks source link

support for Baidu's PaddleOCR (supports gpu, newer, and more actively developed compared to Tesseract) #40

Open devmaxxing opened 2 years ago

devmaxxing commented 2 years ago

In case this is still being maintained, it would be nice if it could also support PaddleOCR.

I have a working fork here with some added features (e.g. cropping, the ability to skip frames) that I wouldn't mind merging back into the original: https://github.com/oliverfei/videocr-PaddleOCR