fairseq/modules/reduced_multihead_attention.py · 0a70c5c505452b7fa2bd7feb1b1e6f6d7f8808c4 · xuchen / Fairseq-S2T · GitLab

Blame History Permalink

optimize the shell scripts for iwslt2022 En-Zh, implement the method of the Efficient Conformer · 0bd92062
xuchen committed Feb 28, 2022

0bd92062

reduced_multihead_attention.py 20.7 KB