speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

auto frontend

Browse Source
This commit is contained in:
游雁 2024-06-05 10:34:50 +08:00
parent 46568227c9
commit 545d69ae92
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
funasr/models/llm_asr/adaptor.py
View File

@ -90,7 +90,7 @@ class Transformer(nn.Module):
llm_dim,
kwargs.get("attention_dropout_rate", 0.0),
),
positionwise_layer(
PositionwiseFeedForward(
llm_dim,
llm_dim // 4,
kwargs.get("dropout_rate", 0.0),