zeeshansayyed / arabicsos Goto Github PK

hello , thank you so much for sharing your tools

i'm trying to make it work , so i followed the instructions by installing the requierements
then i have typed the cmd : wget -v -O catboost_1.model https://iu.box.com/shared/static/mcu4frnipinfw7ery0wetrax7u7zzsxp.model

i couldn't install it with the -L parameters i have an error message

it show that i receive messeges it take a while then it done
then i tried this cmd :
python segmenter.py sample/wiki_books_test_0.txt -o sample/my_segmented_wiki_books_test_0.txt

i hade this message error :

Traceback (most recent call last):
File "segmenter.py", line 46, in
segment(args.in_file, args.out_file)
File "segmenter.py", line 24, in segment
model.load_model("models/catboost_1.model")
File "c:\users\twins\anaconda3\lib\site-packages\catboost\core.py", line 2589, in load_model
self._load_model(fname, format)
File "c:\users\twins\anaconda3\lib\site-packages\catboost\core.py", line 1315, in _load_model
self._object._load_model(model_file, format)
File "_catboost.pyx", line 4681, in _catboost._CatBoost._load_model
File "_catboost.pyx", line 4684, in _catboost._CatBoost._load_model
_catboost.CatBoostError: c:/program files (x86)/go agent/pipelines/buildmaster/catboost.git/catboost/libs/model/model_import_interface.h:19: Model file doesn't exist: models/catboost_1.model

could you help me please ?! i need this tool so much
thank you

Thanks for you sharing...
I want to know if arabic needs segmentation like chinese?
I mean if when doing nlp task with arabic, split it to words is needed?
Thanks!