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

update

Browse Source
This commit is contained in:
shixian.shi 2023-06-27 19:17:26 +08:00
parent 41481008e2
commit bbea0265f1
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

@ -59,7 +59,7 @@ def tokenize(data,
pre_index = None
for hw in hw_config['pre_hwlist']:
hw = " ".join(seg_tokenize(hw, seg_dict))
_find = " ".join(text.find(hw))
_find = " ".join(text).find(hw)
if _find != -1:
_find = text[:_find].count(" ") # bpe sometimes
pre_index = [_find, _find + max(hw.count(" "), 1)]