This is a pretrained model for language identification of nepali-english code-mixed data used from LinCE.

This model is trained for this below repository.

To install codeswitch:

pip install codeswitch

Identify Language

  • Method-1

from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline

tokenizer = AutoTokenizer.from_pretrained("sagorsarker/codeswitch-nepeng-lid-lince")

model = AutoModelForTokenClassification.from_pretrained("sagorsarker/codeswitch-nepeng-lid-lince")
lid_model = pipeline('ner', model=model, tokenizer=tokenizer)

lid_model("put any nepali english code-mixed sentence")
  • Method-2
from codeswitch.codeswitch import LanguageIdentification
lid = LanguageIdentification('nep-eng') 
text = "" # your code-mixed sentence 
result = lid.identify(text)
New: fine-tune this model in a few clicks by selecting AutoNLP in the "Train" menu!
Downloads last month
Hosted inference API
Token Classification
This model can be loaded on the Inference API on-demand.