luosiallen / Diff-Foley

Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models
Apache License 2.0
157 stars 19 forks source link

How to get AudioSet-V2A? #18

Closed BingliangLi closed 3 months ago

BingliangLi commented 6 months ago

Could you please release the url list of this subset for AudioSet? Or upload this to Huggingface dataset? This is kinda important if anyone want to compare with your model.

BingliangLi commented 3 months ago

Any update on this? @luosiallen

sakshamsingh1 commented 1 month ago

Hi, I have the same question.

  1. What video-ids are in AudioSet-V2A?
  2. How do you filter these videos?