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

add speaker-attributed ASR task for alimeeting

Browse Source
This commit is contained in:
smohan-speech 2023-05-06 16:38:09 +08:00
parent a73123bcfc
commit 3b7e4b0d34
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
funasr/utils/postprocess_utils.py
View File

@ -106,17 +106,18 @@ def abbr_dispose(words: List[Any], time_stamp: List[List] = None) -> List[Any]:
if num in abbr_begin:
if time_stamp is not None:
begin = time_stamp[ts_nums[num]][0]
word_lists.append(words[num].upper())
abbr_word = words[num].upper()
num += 1
while num < words_size:
if num in abbr_end:
word_lists.append(words[num].upper())
abbr_word += words[num].upper()
last_num = num
break
else:
if words[num].encode('utf-8').isalpha():
word_lists.append(words[num].upper())
abbr_word += words[num].upper()
num += 1
word_lists.append(abbr_word)
if time_stamp is not None:
end = time_stamp[ts_nums[num]][1]
ts_lists.append([begin, end])
@ -241,4 +242,4 @@ def sentence_postprocess(words: List[Any], time_stamp: List[List] = None):
if ch != ' ':
real_word_lists.append(ch)
sentence = ''.join(word_lists).strip()
return sentence, real_word_lists
return sentence, real_word_lists