# Alternative approaches for text classification task

**URL:** <https://discuss.huggingface.co/t/alternative-approaches-for-text-classification-task/24924>\
**Category:** 🤗Transformers\
**Created:** [October 25, 2022, 7:29am UTC](https://discuss.huggingface.co/t/alternative-approaches-for-text-classification-task/24924 "2022-10-25T07:29:01Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![fabmeyer](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/fabmeyer/32/12222_2.png) [@fabmeyer](https://discuss.huggingface.co/u/fabmeyer)\
**Post date:** [October 25, 2022, 7:29am UTC](https://discuss.huggingface.co/t/alternative-approaches-for-text-classification-task/24924/1 "2022-10-25T07:29:01Z")

</div>

I am trying to classify every single feed from a stream of news feeds.  
I tried zero-shot classification with bart-large-mnli however it was very slow (I have about 200 labels at the moment).

1. How can I speed up the task with zero-shot classification? It will be deployed on a server without GPU
2. Are there other, better suited, approaches for this task (many small texts with many labels)?

Many thanks 🙏