David Nicholson

After reading `das.AudioSequence` again closely I realize that our `WindowDataset` is actually a restricted case of `AudioSequence`, as it is used during training. Restricted because `AudioSequence` introduces a notion of...

The other thing I get out of reading the `das.AudioSequence` dataset more closely is that life is just easier if we can treat the data as a giant array (hence,...

Renamed this issue (again?) After working with these datasets more I think I am understanding that: * it's always frame classification -- the only difference is the targets * we...

Thinking about this again. One schema that might work is to mirror the structure of the package after refactor, where we have the high-level commands and then we group model...

Another annoyance about the current config is having to put a dummy table with the model name, as in https://github.com/vocalpy/vak/issues/734#issuecomment-1899334864, that matches the key-value pair `model = "name` This would...

Fixed by #750

Going to keep the abstraction and save the vectors as described here, I ended up reinventing this idea in #651 -- see discussion there

Looks like we can do this with `datalad-osf`: https://docs.datalad.org/projects/osf/en/latest/tutorial/exportdatacode.html Apparently storage in the OSF project becomes a datastore for the GitHub repository

Hi @kalleknast just want to let you know we didn't forget about you. This is still on the to-do list. @yardencsGitHub has me working on other things (https://github.com/vocalpy/vak/pull/605) but this...

Thank you @kalleknast I will test this. Should have a chance this weekend. If it works fine I will just add the option in the config as we discussed and...