[Fix] TF - add bf16 numpy dtype conversion

[felixdittrich92]

ref.: #1342

[codecov]

Codecov Report

Merging #1344 (e942c16) into main (50d65d7) will decrease coverage by 0.01%.
Report is 1 commits behind head on main.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##             main    #1344      +/-   ##
==========================================
- Coverage   95.78%   95.77%   -0.01%     
==========================================
  Files         154      154              
  Lines        6902     6910       +8     
==========================================
+ Hits         6611     6618       +7     
- Misses        291      292       +1     

Flag	Coverage Δ
unittests	95.77% <100.00%> (-0.01%)	⬇️

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

Files	Coverage Δ
...s/detection/differentiable_binarization/pytorch.py	97.77% <100.00%> (ø)
...etection/differentiable_binarization/tensorflow.py	95.16% <100.00%> (ø)
doctr/models/detection/linknet/pytorch.py	98.19% <100.00%> (ø)
doctr/models/detection/linknet/tensorflow.py	94.89% <100.00%> (ø)
doctr/models/modules/transformer/pytorch.py	100.00% <100.00%> (ø)
doctr/models/recognition/crnn/pytorch.py	94.68% <100.00%> (ø)
doctr/models/recognition/crnn/tensorflow.py	97.59% <100.00%> (ø)
doctr/models/recognition/master/pytorch.py	95.53% <100.00%> (+0.04%)	⬆️
doctr/models/recognition/master/tensorflow.py	98.23% <100.00%> (+0.01%)	⬆️
doctr/models/recognition/parseq/pytorch.py	97.18% <100.00%> (+0.01%)	⬆️
... and 7 more

... and 2 files with indirect coverage changes

[felixdittrich92]

overwritten by #1346