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.

Sign up for GitHub

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

Jump to bottom

pytorch ver. `>=2.1.0` breaks compatibility with all `conformer_ctc` recipes #1610

Open

JinZr opened this issue Apr 28, 2024 · 0 comments

Collaborator

JinZr commented Apr 28, 2024

pytorch added two additional parameters to their implementation of the class TransformerDecoder, see
https://github.com/pytorch/pytorch/blame/94b328ee4592605f490d422f57ad4747a92ac339/torch/nn/modules/transformer.py#L498 and pytorch/pytorch#97166

the modification breaks all conformer_ctc recipes (and possibly other recipes i haven't looked into), causing

TypeError: TransformerDecoderLayer.forward() got an unexpected keyword argument 'tgt_is_causal'

This error can be bypassed by simply adding memory_is_causal and tgt_is_causal to the forward func of class TransformerDecoderLayer.

The text was updated successfully, but these errors were encountered:

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment