This one is tricky since it's a dataset of images IIUC the images are prepared from the VocalMat dataset, see this issue https://github.com/vocalpy/vak/issues/758 and I think the VocalMat dataset includes audio? so we might be able to provide both audio and images
This one is tricky since it's a dataset of images
IIUC the images are prepared from the VocalMat dataset, see this issue
vocalpy/vak#758
and I think the VocalMat dataset includes audio?
so we might be able to provide both audio and images