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 17:41:21 +08:00
parent 2ddf9637fc
commit a3c3e1a250
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
funasr/datasets/large_datasets/utils/tokenize.py
View File

@ -58,10 +58,11 @@ def tokenize(data,
# enable preset hotword detect in sampling
pre_index = None
for hw in hw_config['pre_hwlist']:
_find = data['text'].find(hw)
_find = data['text'][0].find(hw)
if _find != -1:
_find = text[:_find].count(" ") # bpe sometimes
_find = data['text'][0][:_find].count(" ") # bpe sometimes
pre_index = [_find, _find + max(hw.count(" "), 1)]
import pdb; pdb.set_trace()
break
hotword_indxs = sample_hotword(length, **hw_config, pre_index=pre_index)
data['hotword_indxs'] = hotword_indxs