-
Notifications
You must be signed in to change notification settings - Fork 67
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Error running librispeech_asr_imperceptible_defended.json #1465
Comments
This looks like an ART error, at this line:
It breaks up the inputs into non-batches (removes the first dimension), but the mp3 defense cannot handle non-batches. |
Seeing if this can be mapped to the non-pytorch version. |
The Non-PyTorch version of ImperceptibleASR has been refactored in such a way to make it unable to be generated directly from config. I will remove this config from armory. |
Actually, there is a Mp3CompressionPyTorch defense. Will attempt to make that work. |
Made a PR into ART for an (seemingly related but actually) unrelated Mp3Compression bug I found: |
Made a second bug issue for ART that if resolved (and combined with the Mp3Compression fix) should work: |
To reproduce:
The text was updated successfully, but these errors were encountered: