# Model for Audio classification

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-for-audio-classification%2F27810%3E%5C
**Category:** 🤗Transformers\
**Created:** [December 14, 2022, 1:24pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-for-audio-classification%2F27810 "2022-12-14T13:24:00Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![amitkayal](https://avatars.discourse-cdn.com/v4/letter/a/dfb087/32.png) [@amitkayal](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Famitkayal)%5C
**Post date:** [December 14, 2022, 1:24pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-for-audio-classification%2F27810%2F1 "2022-12-14T13:24:00Z")

</div>

Hello All,

I need to finetune model for audio classification was wondering what is most appropriate one for such. I found superb/hubert-base-superb-er and [Audio classification](https://huggingface.co/docs/transformers/tasks/audio_classification) but could not locate any sagemaker notebook or colab notebook with steps of finetune. Would appreciate if anyone can point me towards right direction.

Thanks

---

<div class="post-metadata">

**Author:** ![nielsr](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/nielsr/32/39617_2.png) [@nielsr](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fnielsr)%5C
**Post date:** [December 16, 2022, 2:59pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-for-audio-classification%2F27810%2F2 "2022-12-16T14:59:37Z")

</div>

Hi,

Here’s the official example notebook for audio classification: [notebooks/audio\_classification.ipynb at main · huggingface/notebooks · GitHub](https://github.com/huggingface/notebooks/blob/main/examples/audio_classification.ipynb).

Also note that we’ve just added the [Audio Spectrogram Transformer (AST)](https://huggingface.co/docs/transformers/model_doc/audio-spectrogram-transformer), which is state-of-the-art for audio classification. You can replace the model in the notebook above by AST.

---

<div class="post-metadata">

**Author:** ![amitkayal](https://avatars.discourse-cdn.com/v4/letter/a/dfb087/32.png) [@amitkayal](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Famitkayal)%5C
**Post date:** [January 23, 2023, 1:46pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmodel-for-audio-classification%2F27810%2F3 "2023-01-23T13:46:00Z")

</div>

Hi @nielsr Thanks a lot for your response. I am also looking for speaker name identification and this also means in a org, we can have hundreds of speakers. Will this model can handle such ones? Thanks