Support subword and word language models

Closes #199 (closed)

Ref https://redmine.teklia.com/issues/4941

requirements.txt

@@ -6,10 +6,12 @@ flashlight-text==0.0.4
 imageio==2.26.1
 imagesize==1.4.1
 mdutils==1.6.0
+nltk==3.8.1
 numpy==1.24.3
 prettytable==3.8.0
 PyYAML==6.0
 scipy==1.10.1
+sentencepiece==0.1.99
 teklia-line-image-extractor==0.2.8rc5
 tenacity==8.2.3
 tensorboard==2.12.2