Ian Sampson

I’ll second the request for an official `pad` implementation when PyTorch 1.12.0 support rolls out, though as a workaround I’ve been able to compile `torchaudio.models.Conformer` to CoreML with PyTorch 1.11.0...

> @iansampson thanks for the info. I'm trying to convert another implementation from nvidia/NeMo instead. > Were you also able to run it/any console warnings? > Are you using it...

Thanks for the quick response! Just tested with the latest release (6.0b1) and yes, the results are pretty much the same (prediction time: 106.645615 s; mlpackage size: 538.8 MB).

I think I’ve traced the problem to the GRU layer used in TransformerEncoderLayer (aia_inter_new.py, line 41). Here’s a simple script that reproduces the problem: ``` python import time import numpy...

Good question! I don’t have any plans to add receipt validation in the near future, as I’m pretty busy with other projects and it’d be a significant amount of work....

Interesting video, thanks for sharing it! Yes, App Attest alone is hardly foolproof, so a combination of checks is likely the safest approach. I’d certainly welcome a PR for receipt...