Model for Audio classification

🤗Transformers
1

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 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

2

Hi,

Here’s the official example notebook for audio classification: notebooks/audio_classification.ipynb at main · huggingface/notebooks · GitHub.

Also note that we’ve just added the Audio Spectrogram Transformer (AST), which is state-of-the-art for audio classification. You can replace the model in the notebook above by AST.

3

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