# Help in finetuning ASR models

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhelp-in-finetuning-asr-models%2F29464%3E%5C
**Category:** Beginners\
**Created:** [January 12, 2023, 6:55pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhelp-in-finetuning-asr-models%2F29464 "2023-01-12T18:55:49Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![Davide85](https://avatars.discourse-cdn.com/v4/letter/d/67e7ee/32.png) [@Davide85](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FDavide85)%5C
**Post date:** [January 12, 2023, 6:55pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhelp-in-finetuning-asr-models%2F29464%2F1 "2023-01-12T18:55:49Z")

</div>

Hi all,

Excuse me, I am a newbie. My problem is about the finetuning of ASR models (especially [facebook/s2t-small-librispeech-asr · Hugging Face](https://huggingface.co/facebook/s2t-small-librispeech-asr)) on my custom dataset consisting of my recording. Where can I find a piece of example for that?

Thanks in advance,

Davide

---

<div class="post-metadata">

**Author:** ![stevhliu](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/stevhliu/32/18373_2.png) [@stevhliu](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fstevhliu)%5C
**Post date:** [January 12, 2023, 7:03pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhelp-in-finetuning-asr-models%2F29464%2F2 "2023-01-12T19:03:01Z")

</div>

Hi, there is a task guide for ASR in the docs [here](https://huggingface.co/docs/transformers/tasks/asr) 🙂

---

<div class="post-metadata">

**Author:** ![Davide85](https://avatars.discourse-cdn.com/v4/letter/d/67e7ee/32.png) [@Davide85](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FDavide85)%5C
**Post date:** [January 13, 2023, 6:05pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhelp-in-finetuning-asr-models%2F29464%2F3 "2023-01-13T18:05:14Z")

</div>

Thank you so much. The above guide uses a transformers dataset object, while, in my case, I have the raw wave files. How I can convert these data in order to finetune the ASR model?  
Thank you,  
Davide

---

<div class="post-metadata">

**Author:** ![stevhliu](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/stevhliu/32/18373_2.png) [@stevhliu](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fstevhliu)%5C
**Post date:** [January 13, 2023, 7:00pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhelp-in-finetuning-asr-models%2F29464%2F4 "2023-01-13T19:00:30Z")

</div>

You can create your own audio dataset with your files to get a `Dataset` object.

The easiest option is probably the `AudioFolder` builder. You just have to create a dataset repo on the Hub and upload your audio files to it. Then you can load it like:

```plaintext
from datasets import load_dataset
dataset = load_dataset("audiofolder", data_dir="/path/to/data")

```

Check out the docs [here](https://huggingface.co/docs/datasets/audio_dataset#audiofolder) for more details!