# Using Custom SpaCy model

**URL:** <https://forum.rasa.com/t/using-custom-spacy-model/24024>\
**Category:** Rasa Open Source\
**Created:** [January 27, 2020, 3:58pm UTC](https://forum.rasa.com/t/using-custom-spacy-model/24024 "2020-01-27T15:58:34Z")\
**Posts on this page:** 1\
**Showing post:** 8

<div class="post-metadata">

**Author:** ![taimoor-ahmed](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/taimoor-ahmed/32/4108_2.png) [@taimoor-ahmed](https://forum.rasa.com/u/taimoor-ahmed)\
**Post date:** [April 21, 2020, 10:02am UTC](https://forum.rasa.com/t/using-custom-spacy-model/24024/8 "2020-04-21T10:02:37Z")

</div>

@Talhag958 I didn’t end up using the SpaCy model for Urdu because I was unable to integrate it in RASA. Here is my config.yml file which I am using.

# Configuration for Rasa NLU.

# [Components](https://rasa.com/docs/rasa/nlu/components/)

language: ur

pipeline:

- name: WhitespaceTokenizer
- name: RegexFeaturizer
- name: LexicalSyntacticFeaturizer
- name: CountVectorsFeaturizer
- name: CountVectorsFeaturizer analyzer: “char\_wb” min\_ngram: 1 max\_ngram: 4
- name: DIETClassifier epochs: 100
- name: EntitySynonymMapper
- name: ResponseSelector epochs: 100

policies:

- name: MemoizationPolicy
- name: KerasPolicy
- name: MappingPolicy
- name: FormPolicy

---

_[View the full topic](https://forum.rasa.com/t/using-custom-spacy-model/24024)._