Open yupm opened 1 year ago
It's not a priority for me right now, but I agree that it would be nice to drop the torch dependency. Another option is ONNX.
Hey there @yupm I'm currently trying to replicate MangaOcr outside of python so I can give you some hints. You can find here #45 a way to export an ONNX model and drop both the transformers & torch dependencies. However consider that this model alone (ONNX file) is more than 500M and I guess you cannot lower that.
Hello.. Currently I am trying to bundle a deb package for Poricom which uses manga_ocr. However, the torch dependencies of the transformers backend are making the deb excessively large.
I wonder if you could advise or help regarding reducing the size of the bundle by using another backend such as TF or JAX.