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

优化merge segments 参数，解决新闻联播男女主持人“晚上好”合并一个speakid问题

Browse Source
This commit is contained in:
wuhongsheng 2024-06-28 15:03:39 +08:00
parent c3ec6b9b9e
commit fa74a6e26c
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/campplus/utils.py
View File

@ -169,7 +169,7 @@ def merge_seque(distribute_res):
return res
def smooth(res, mindur=1):
def smooth(res, mindur=0.7):
# if only one segment, return directly
if len(res) < 2:
return res