# SpeechT5 Text to Speech fine tuning runtime error

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fspeecht5-text-to-speech-fine-tuning-runtime-error%2F67472%3E%5C
**Category:** Models\
**Created:** [December 30, 2023, 12:58pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fspeecht5-text-to-speech-fine-tuning-runtime-error%2F67472 "2023-12-30T12:58:47Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Walelign](https://avatars.discourse-cdn.com/v4/letter/w/5f9b8f/32.png) [@Walelign](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FWalelign)%5C
**Post date:** [December 30, 2023, 12:58pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fspeecht5-text-to-speech-fine-tuning-runtime-error%2F67472%2F1 "2023-12-30T12:58:47Z")

</div>

I am fine tuning SpeechT5 for new language by my own dataset.  
I did all the steps successfully, but I got the following error when i tried to run  
trainer.train()

RuntimeError: Sizes of tensors must match except in dimension 2. Expected size 16 but got size 256 for tensor number 1 in the list.  
Anyone help me?

---

<div class="post-metadata">

**Author:** ![kamii](https://avatars.discourse-cdn.com/v4/letter/k/439d5e/32.png) [@kamii](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fkamii)%5C
**Post date:** [January 12, 2024, 3:32pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fspeecht5-text-to-speech-fine-tuning-runtime-error%2F67472%2F2 "2024-01-12T15:32:09Z")

</div>

did you find a fix to this or a work around?