[MASK]
This is a pretrained model for language identification of hindi-english
code-mixed data used from LinCE
This model is trained for this below repository.
https://github.com/sagorbrur/codeswitch
To install codeswitch:
pip install codeswitch
from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
tokenizer = AutoTokenizer.from_pretrained("sagorsarker/codeswitch-hineng-lid-lince")
model = AutoModelForTokenClassification.from_pretrained("sagorsarker/codeswitch-hineng-lid-lince")
lid_model = pipeline('ner', model=model, tokenizer=tokenizer)
lid_model("put any hindi english code-mixed sentence")
from codeswitch.codeswitch import LanguageIdentification
lid = LanguageIdentification('hin-eng')
text = "" # your code-mixed sentence
result = lid.identify(text)
print(result)