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

sdpa bugfix

Browse Source
This commit is contained in:
游雁 2024-07-24 01:08:52 +08:00
parent 54e630159d
commit 20d32f68e8
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/sense_voice/whisper_lib/model.py
View File

@ -312,7 +312,7 @@ class TextDecoder(nn.Module):
n_state,
n_head,
cross_attention=True,
att_type="default",
att_type=kwargs.get("att_type", "default"),
)
for _ in range(n_layer)
]