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

fix start timestamp in sentence_info (#2024)

Browse Source 
Previously, the start timestamp was defined as the last character's timestamp[0] of the previous sentence. It has now been changed to the first character's timestamp[0] of the current sentence.
This commit is contained in:
lingji-yidong 2024-08-19 13:36:59 +08:00 committed by GitHub
parent 3a2f6693a1
commit f43da18b5e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
funasr/utils/timestamp_tools.py
View File

@ -141,6 +141,8 @@ def timestamp_sentence(
) )
for punc_stamp_text in punc_stamp_text_list: for punc_stamp_text in punc_stamp_text_list:
punc_id, timestamp, text = punc_stamp_text punc_id, timestamp, text = punc_stamp_text
if sentence_start is None and timestamp is not None:
sentence_start = timestamp[0]
# sentence_text += text if text is not None else '' # sentence_text += text if text is not None else ''
if text is not None: if text is not None:
if "a" <= text[0] <= "z" or "A" <= text[0] <= "Z": if "a" <= text[0] <= "z" or "A" <= text[0] <= "Z":
@ -183,7 +185,7 @@ def timestamp_sentence(
sentence_text = "" sentence_text = ""
sentence_text_seg = "" sentence_text_seg = ""
ts_list = [] ts_list = []
sentence_start = timestamp[0] if timestamp is not None else sentence_start sentence_start = None
return res return res
@ -272,4 +274,4 @@ def timestamp_sentence_en(
sentence_text = "" sentence_text = ""
sentence_text_seg = "" sentence_text_seg = ""
ts_list = [] ts_list = []
return res return res