I’m working on a text classifier using AraBERT. My application is working locally however it’s not working in deployment because of the model’s text pre-processing function that uses AraBERT as an rgument like the following:
from arabert.preprocess import ArabertPreprocessor model_name = "aubmindlab/bert-base-arabertv2" arabert_prep = ArabertPreprocessor(model_name=model_name) text = "ولن نبالغ إذا قلنا: إن 'هاتف' أو 'كمبيوتر المكتب' في زمننا هذا ضروري" arabert_prep.preprocess(text)
The model name doesn’t seem to be recognized as an argiment, and I thought of having it in
requiremnets.txt like I would do with a spacy language model like the following:
fr-core-news-lg @ https://github.com/explosion/spacy-models/releases/download/fr_core_news_lg-3.3.0/fr_core_news_lg-3.3.0.tar.gz
But I’m not sure of the link to place in there.
FileNotFoundError: [Errno 2] No such file or directory: 'java'
Do you have any ideas on how to solve this problem?
Thank you so much in advance.