SamsungLabs / SummaryMixing

This repository implements SummaryMixing, a simpler, faster and much cheaper replacement to self-attention for automatic speech recognition (see: https://arxiv.org/abs/2307.07421). The code is ready to be used with the SpeechBrain toolkit).
Other
86 stars 8 forks source link

Fix Encoder-only SummaryFixing #6

Closed Adel-Moumen closed 2 months ago

Adel-Moumen commented 3 months ago

Hi,

This PR fix an issue related to SummaryMixing when using it as an encoder only.

For more context, please see: #5 :)

TParcollet commented 3 months ago

Thanks @Adel-Moumen, is this copy-pasted from the main SB repo? (just to know if we will get some merge conflicts in the future).

Adel-Moumen commented 3 months ago

Thanks @Adel-Moumen, is this copy-pasted from the main SB repo? (just to know if we will get some merge conflicts in the future).

Yep.