Yuan Gong

Hi Rongjie, Thanks for reaching out. CLAP is not our work, I just list the results in that paper for reference. You can contact the authors of the CLAP paper...

Thanks for your kind words and best wishes for your research and paper!!

Thanks! I just put a link to the CLAP code in the readme file. Best, Yuan

Hi there, Thanks for reporting that. Could you elaborate which link doesn't work? -Yuan

Do you mean the dropbox link or the Tecent link? Both are hosted by industry-level servers and shouldn't be down. I just tried the 16k dropbox link, that was good....

Thanks for confirming that! Anyone having a downloading problem please leave a message in this thread. -Yuan

Hi, The weight file is used here: https://github.com/YuanGongND/psla/blob/46a53b9f86c95faae73ebd38777e2a6c370dd877/src/run.py#L82-L85 Basically, in `gen_weight_file`, the weight of each sample is `sum(1/class_frequency)`, note for audioset, each sample has multiple classes, that's why `sum` is...

Hi there, I don't have a strong reason to choose one over another. But I felt that fbank is more standard for audio application as it provides some flexibility on...

do you have `sox` installed? if no, please do so. It isn't complex, you can debug it. https://github.com/YuanGongND/psla/blob/76aedd19ad3123be9c5d002809575955683aaade/egs/fsd50k/prep_fsd.py#L22-L36

This is a different problem, you would need to install the dependencies, see https://github.com/YuanGongND/psla#getting-started. The previous issues is not torch related, have you checked sox?