Including manga ocr in android app?

[clausagerskov]

How feasible would it be to use manga ocr to power a manga reading app?
Would a typical smartphone be able to run ocr on a line of text in a reasonable amount of time?
How big would the installation be?
And would it even be technically possible to include it in the app code?

[Mar2ck]

I got manga-ocr running on Android via termux and it took about 3-4 seconds per image on a Snapdragon 8+ Gen 1. That's a significant delay but not unuseably slow.

Shipping PyTorch in an app is very impractical though, realistically you would port to ONNX and run the model on NPU via NNAPI to speed up inference and reduce battery consumption. Also the model itself is 444 MB so quantizing to int8/int4 would be a must to keep storage requirements down.

[lifes71]

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\LENOVO\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 1726, in _slow_forward result = self.forward(*input, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\LENOVO\AppData\Local\Programs\Python\Python311\Lib\site-packages\transformers\models\bert\modeling_bert.py", line 1357, in forward outputs = self.bert( ^^^^^^^^^^ File "C:\Users\LENOVO\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\LENOVO\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\LENOVO\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 1726, in _slow_forward result = self.forward(*input, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\LENOVO\AppData\Local\Programs\Python\Python311\Lib\site-packages\transformers\models\bert\modeling_bert.py", line 1062, in forward raise ValueError("You have to specify either input_ids or inputs_embeds") ValueError: You have to specify either input_ids or inputs_embeds
@Mar2ck can you help?

[Mar2ck]

can you help?

You should make a seperate issue for this. In the issue put how you're getting to this error: installing from pip or cloning the repo, the command you're running, etc.