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 text postprocess

Browse Source
This commit is contained in:
jmwang66 2022-12-23 10:40:23 +08:00
parent ff477cf148
commit d653df71cb
1 changed files with 3 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
funasr/utils/postprocess_utils.py
View File

@ -12,10 +12,8 @@ def isChinese(ch: str):
def isAllChinese(word: Union[List[Any], str]):
word_lists = []
table = str.maketrans('', '', string.punctuation)
for i in word:
cur = i.translate(table)
cur = cur.replace(' ', '')
cur = i.replace(' ', '')
cur = cur.replace('</s>', '')
cur = cur.replace('<s>', '')
word_lists.append(cur)
@ -31,10 +29,8 @@ def isAllChinese(word: Union[List[Any], str]):
def isAllAlpha(word: Union[List[Any], str]):
word_lists = []
table = str.maketrans('', '', string.punctuation)
for i in word:
cur = i.translate(table)
cur = cur.replace(' ', '')
cur = i.replace(' ', '')
cur = cur.replace('</s>', '')
cur = cur.replace('<s>', '')
word_lists.append(cur)
@ -43,7 +39,7 @@ def isAllAlpha(word: Union[List[Any], str]):
return False
for ch in word_lists:
if ch.isalpha() is False:
if ch.isalpha() is False and ch != "'":
return False
elif ch.isalpha() is True and isChinese(ch) is True:
return False