Hugging Face's logo

MIT
/
ast-finetuned-audioset-10-10-0.4593

Audio Classification Transformers PyTorch Safetensors audio-spectrogram-transformer Inference Endpoints
Model card Files Community
11

How can I use for audio classification

#3
by Oncecaddy - opened
Discussion
Oncecaddy

Hello,
I want to do audio classification. How can I download and use pretrained models? Thanks.

nielsr
 Massachusetts Institute of Technology org

Hi,

You can easily do that using the audio classification pipeline.

See also the code snippet here.

thelou1s

Is there a quantization for pytorch mobile? thx

nielsr
 Massachusetts Institute of Technology org

Hi,

Yes you can use the Optimum library for that: https://huggingface.co/docs/optimum. It allows to export your model to ONNX among other formats, making the model smaller with quantization, etc.

Sign up or log in to comment