# Problem with finetuning model whisper

**URL:** <https://discuss.huggingface.co/t/problem-with-finetuning-model-whisper/116278>\
**Category:** Beginners\
**Created:** [November 7, 2024, 7:33pm UTC](https://discuss.huggingface.co/t/problem-with-finetuning-model-whisper/116278 "2024-11-07T19:33:42Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Rina00](https://avatars.discourse-cdn.com/v4/letter/r/9e8a1a/32.png) [@Rina00](https://discuss.huggingface.co/u/Rina00)\
**Post date:** [November 7, 2024, 7:33pm UTC](https://discuss.huggingface.co/t/problem-with-finetuning-model-whisper/116278/1 "2024-11-07T19:33:42Z")

</div>

I have retrained the whisper-large-v3-turbo model on my local data (there are few of them, 55 audio for several minutes and text to them), but the model that I retrained works worse than the original one. Why?