Some details about how to inference

[DthdZK]

Dear Author, Is the test set in the inference.py the entire VGGSound dataset? I see that the code needs to use the dataloader of this dataset, so how do I implement it if I want to execute inference.py on any other audio?

[guyyariv]

Hello, and thanks for reaching out. I suggest making a copy of the dataloader class and adapting it for your audio files. In the current code, handling VGGSound , during inference, involves simply loading the audio files from a directory without any complex processing.

[DthdZK]

thanks a lot!