[Feature Request] Allow the API to return the captured text mask

[bd-charu]

Is it possible to return the detected mask in another method? It should look something like this:

Class MangaOcr(...):
   ...
def __call__(...):
    ...
def text(...):
    # same as __call__
    __call__(...)
def mask(...):
    # modified __call__ where text mask is the output (same size with input)

[kha-white]

It's not possible, because text segmentation is not a part of the current pipeline. You'd need a separate model for this task.