An error initializing English pipeline (on the MLH-dev branch)
avidale opened this issue · comments
When I run the following code
from laser_encoders import LaserEncoderPipeline
laser2 = LaserEncoderPipeline(lang="eng")
I get an error:
KeyError Traceback (most recent call last)
File ~/dev/LASER/laser_encoders/download_models.py:73, in LaserModelDownloader.get_language_code(self, language_list, lang)
72 try:
---> 73 lang_3_4 = language_list[lang]
74 if isinstance(lang_3_4, tuple):
KeyError: 'eng'
Expected behavior: loading the tokenizer and the model for LASER-2 (which is the default choice for English and 100-ish other languages).