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 19:24:23 +08:00
parent a6ccb955ed
commit 25de54910e
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
funasr/datasets/large_datasets/utils/hotword_utils.py
View File

@ -6,7 +6,8 @@ def sample_hotword(length,
sample_rate, sample_rate,
double_rate, double_rate,
pre_prob, pre_prob,
pre_index=None): pre_index=None,
pre_hwlist=None):
if length < hotword_min_length: if length < hotword_min_length:
return [-1] return [-1]
if random.random() < sample_rate: if random.random() < sample_rate:

1
funasr/datasets/large_datasets/utils/tokenize.py
View File

@ -63,7 +63,6 @@ def tokenize(data,
if _find != -1: if _find != -1:
# _find = text[:_find].count(" ") # bpe sometimes # _find = text[:_find].count(" ") # bpe sometimes
pre_index = [_find, _find + max(hw.count(" "), 1)] pre_index = [_find, _find + max(hw.count(" "), 1)]
# import pdb; pdb.set_trace()
break break
hotword_indxs = sample_hotword(length, **hw_config, pre_index=pre_index) hotword_indxs = sample_hotword(length, **hw_config, pre_index=pre_index)
data['hotword_indxs'] = hotword_indxs data['hotword_indxs'] = hotword_indxs