# Training Data with supervised\_embeddings is slow, How can i improve training

**URL:** <https://forum.rasa.com/t/training-data-with-supervised-embeddings-is-slow-how-can-i-improve-training/11076>\
**Category:** Tutorials, Resources & Videos\
**Created:** [June 6, 2019, 12:17pm UTC](https://forum.rasa.com/t/training-data-with-supervised-embeddings-is-slow-how-can-i-improve-training/11076 "2019-06-06T12:17:41Z")\
**Posts on this page:** 1\
**Showing post:** 6

<div class="post-metadata">

**Author:** ![Remy](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/remy/32/2030_2.png) [@Remy](https://forum.rasa.com/u/Remy)\
**Post date:** [June 12, 2019, 11:08am UTC](https://forum.rasa.com/t/training-data-with-supervised-embeddings-is-slow-how-can-i-improve-training/11076/6 "2019-06-12T11:08:54Z")

</div>

Not that I know of. You have to remember that if you add some utterances the model needs to relate those words to the other sentences it knows. It can’t do that without retraining everything because it has to adjust the word vectors for the -already trained- intents.

---

_[View the full topic](https://forum.rasa.com/t/training-data-with-supervised-embeddings-is-slow-how-can-i-improve-training/11076)._