How can I access a language code for Urdu?

Question

I am retraining a POS tag model of STANZA library. After updating the CONLLU files (dev,test, train), when I try to prepare the script by

python3 -m stanza.utils.datasets.prepare_pos_treebank UD_URDU-UDTB

It gives the following error

raise ValueError("Unable to find language code for %s" % lang)
ValueError: Unable to find language code for URDU

How can I fix it

Answer 1

It expects capitalization to be standard. Perhaps that is something we can update. Try UD_Urdu-UDTB