[orientation] Enable usage of custom trained orientation models

[felixdittrich92]

This PR:

• Add ability that users can train and use there own orientation models
• Open interface to load custom orient models
• Add corresponding doc section and tests

Any feedback is welcome 🤗

NOTE:
Overwriting is i think a temp solution to avoid blowing up the ocr_predictor args until we have a solution for a better interface.

Request: #1698

[felixdittrich92]

That's required for the isinstance check in classification.zoo

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 96.42%. Comparing base (4434213) to head (64e8f8c).
Report is 1 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1708      +/-   ##
==========================================
+ Coverage   96.41%   96.42%   +0.01%     
==========================================
  Files         164      164              
  Lines        7777     7782       +5     
==========================================
+ Hits         7498     7504       +6     
+ Misses        279      278       -1     

Flag	Coverage Δ
unittests	96.42% <100.00%> (+0.01%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[odulcy-mindee]

Nice PR, looks good to me !