YuanGongND / ssast

Code for the AAAI 2022 paper "SSAST: Self-Supervised Audio Spectrogram Transformer".

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

question: example usage for inference, rather than training

sammlapp opened this issue · comments

Thanks for providing this great code base. Is there a simple example of how to use run inference with one of the pre-trained models?

hi there,

There is one for AST: https://colab.research.google.com/github/YuanGongND/ast/blob/master/colab/AST_Inference_Demo.ipynb

You can replace the model with SSAST pretrained model. But since you do not care about training, you probably can stick on AST.

We also have an audio large language model that has an API: https://huggingface.co/spaces/yuangongfdu/LTU, input an audio and ask it an question.

-Yuan