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

fix hotword tokenize

Browse Source
This commit is contained in:
haoneng.lhn 2023-07-17 14:24:42 +08:00
parent bcf3b48647
commit 52b36291e1
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/datasets/large_datasets/utils/tokenize.py
View File

@ -54,9 +54,9 @@ def tokenize(data,
length = len(text)
if 'hw_tag' in data:
pre_index = None
if hw_config['pre_hwlist'] is not None and hw_config['pre_prob'] > 0:
# enable preset hotword detect in sampling
pre_index = None
for hw in hw_config['pre_hwlist']:
hw = " ".join(seg_tokenize(hw, seg_dict))
_find = " ".join(text).find(hw)