# Why do we still need to retrain Rasa while BERT and other models are already trained?

**URL:** <https://forum.rasa.com/t/why-do-we-still-need-to-retrain-rasa-while-bert-and-other-models-are-already-trained/54757>\
**Category:** Getting Started with Rasa\
**Created:** [August 10, 2022, 2:22pm UTC](https://forum.rasa.com/t/why-do-we-still-need-to-retrain-rasa-while-bert-and-other-models-are-already-trained/54757 "2022-08-10T14:22:00Z")\
**Posts on this page:** 1\
**Showing post:** 1

<div class="post-metadata">

**Author:** ![RasaEnthusiast](https://avatars.discourse-cdn.com/v4/letter/r/b77776/32.png) [@RasaEnthusiast](https://forum.rasa.com/u/RasaEnthusiast)\
**Post date:** [August 10, 2022, 2:22pm UTC](https://forum.rasa.com/t/why-do-we-still-need-to-retrain-rasa-while-bert-and-other-models-are-already-trained/54757/1 "2022-08-10T14:22:01Z")

</div>

I’m new with RASA and NLP bots in general. I’ve been coding conversational bots with RASA and I have a silly question.

Since we can plug BERT, GPT-X and the likes in the pipeline, I don’t understand why we need to ‘re train’ Rasa with things such as entity recognition in the nlu.yml file or even chit chat phrases?

---

_[View the full topic](https://forum.rasa.com/t/why-do-we-still-need-to-retrain-rasa-while-bert-and-other-models-are-already-trained/54757)._