# spaCy Training Model vs Prodigy

**URL:** <https://support.prodi.gy/t/spacy-training-model-vs-prodigy/5453>\
**Category:** Uncategorized\
**Tags:** usage, spacy, solved\
**Created:** [March 21, 2022, 6:53am UTC](https://support.prodi.gy/t/spacy-training-model-vs-prodigy/5453 "2022-03-21T06:53:05Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![kylebigelow](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/kylebigelow/32/3642_2.png) [@kylebigelow](https://support.prodi.gy/u/kylebigelow)\
**Post date:** [March 21, 2022, 6:53am UTC](https://support.prodi.gy/t/spacy-training-model-vs-prodigy/5453/1 "2022-03-21T06:53:05Z")

</div>

Should I train a new model in spaCy before working with the features in Prodigy?

This page recommends to use prodigy:

> **[Training Pipelines & Models · spaCy Usage Documentation](https://spacy.io/usage/training/)**
>
> Train and update components on your own data and integrate custom models

Do these processes work together or conflict?

Thanks

---

<div class="post-metadata">

**Author:** ![ljvmiranda921](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/ljvmiranda921/32/3197_2.png) [@ljvmiranda921](https://support.prodi.gy/u/ljvmiranda921)\
**Post date:** [March 21, 2022, 7:35am UTC](https://support.prodi.gy/t/spacy-training-model-vs-prodigy/5453/2 "2022-03-21T07:35:44Z")

</div>

Hi @kylebigelow , welcome to Prodigy!

No, these processes don't conflict with one another. You can train a model even [from Prodigy](https://prodi.gy/docs/recipes#training). If you will be annotating data, your workflow may be: annotate data -\> train spaCy model using `prodigy train` -\> evaluate. Under the hood, the `prodigy train` command also calls the same functions as spaCy, so you're virtually using the same setup.