Skip to content

A Streamlit application to predict language of the text entered by user. The project contains vectoriser and language detection model files as the dependencies

License

Notifications You must be signed in to change notification settings

Khalidsid/language_predictor

Repository files navigation

language_predictor

Application description: A Streamlit application to predict language of the text entered by user.

Model developed: Multinomial Naive Bias classifier

Info on Training : Ipynb files contains details of model training and evaluations

Dataset: The model is trained on dataset availabele at : https://www.kaggle.com/code/suryadeepti/language-detction

Deployment: streamlit_app.py files contains application deployment part only. vectoriser and language detection model files are the main dependencies.

Streamlit Application: https://languagepredictor-nb.streamlit.app/

Languages Trained on:

Language (Examples)

  1. English 1385
  2. French 1014
  3. Spanish 819
  4. Portugeese 739
  5. Italian 698
  6. Russian 692
  7. Sweedish 676
  8. Malayalam 594
  9. Dutch 546
  10. Arabic 536
  11. Turkish 474
  12. German 470
  13. Tamil 469
  14. Danish 428
  15. Kannada 369
  16. Greek 365
  17. Hindi 63

About

A Streamlit application to predict language of the text entered by user. The project contains vectoriser and language detection model files as the dependencies

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published