mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-12-11 06:55:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

Use dropout in attention, on attn weights.

Browse Source
This commit is contained in:
Daniel Povey 2022-09-22 19:18:50 +08:00
parent 24aea947d2
commit ce3f59d9c7
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
egs/librispeech/ASR/pruned_transducer_stateless7/conformer.py
View File

@ -168,7 +168,7 @@ class ConformerEncoderLayer(nn.Module):
self.d_model = d_model
self.self_attn = RelPositionMultiheadAttention(
d_model, nhead, dropout=0.0
d_model, nhead, dropout=dropout,
)
self.feed_forward = nn.Sequential(