Added NKJP1M / PDB corpus.

src/lambo/resources/languages.txt

@@ -92,6 +92,7 @@ UD_Persian-PerDT fa Persian *
 UD_Persian-Seraji fa Persian
 UD_Polish-LFG pl Polish
 UD_Polish-PDB pl Polish *
+UD_Polish-NKJP1M_PDB pl Polish
 UD_Pomak-Philotis ? Pomak
 UD_Portuguese-Bosque pt Portuguese
 UD_Portuguese-CINTIL pt Portuguese *

src/lambo/utils/generate_languages_txt.py

@@ -8,6 +8,7 @@ Uses the previous version of the file to translate language names to ISO codes.
 - adding '?' as ISO code for the new languages outside the standard
 - selected UD_German-GSD as default in place of UD_German-HDT, which lacks spacing information
 - corrected language code for UD_Norwegian-Bokmaal from nn to no
+- added UD_Polish-NKJP1M_PDB from https://huggingface.co/datasets/ipipan/nlprepl/tree/main/ud_tagset/fair_by_document_type/_conllu
 """
 from pathlib import Path