From bc723ea200144bd6fa8a5dff4b9a780feda144fc Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 29 六月 2023 18:55:01 +0800
Subject: [PATCH] dcos
---
funasr/utils/timestamp_tools.py | 65 +++++++++++++++++++-------------
1 files changed, 38 insertions(+), 27 deletions(-)
diff --git a/funasr/utils/timestamp_tools.py b/funasr/utils/timestamp_tools.py
index 09c3bec..4e7a8a9 100644
--- a/funasr/utils/timestamp_tools.py
+++ b/funasr/utils/timestamp_tools.py
@@ -1,5 +1,5 @@
-from pydoc import TextRepr
-from scipy.fftpack import shift
+from itertools import zip_longest
+
import torch
import copy
import codecs
@@ -19,7 +19,7 @@
sil_in_str=True
):
if not len(char_list):
- return []
+ return "", []
START_END_THRESHOLD = 5
MAX_TOKEN_DURATION = 12
TIME_RATE = 10.0 * 6 / 1000 / 3 # 3 times upsampled
@@ -80,6 +80,7 @@
def time_stamp_sentence(punc_id_list, time_stamp_postprocessed, text_postprocessed):
+ punc_list = ['锛�', '銆�', '锛�', '銆�']
res = []
if text_postprocessed is None:
return res
@@ -89,44 +90,54 @@
return res
if len(text_postprocessed) == 0:
return res
+
if punc_id_list is None or len(punc_id_list) == 0:
res.append({
'text': text_postprocessed.split(),
"start": time_stamp_postprocessed[0][0],
- "end": time_stamp_postprocessed[-1][1]
+ "end": time_stamp_postprocessed[-1][1],
+ 'text_seg': text_postprocessed.split(),
+ "ts_list": time_stamp_postprocessed,
})
return res
if len(punc_id_list) != len(time_stamp_postprocessed):
- res.append({
- 'text': text_postprocessed.split(),
- "start": time_stamp_postprocessed[0][0],
- "end": time_stamp_postprocessed[-1][1]
- })
- return res
-
- sentence_text = ''
+ print(" warning length mistach!!!!!!")
+ sentence_text = ""
+ sentence_text_seg = ""
+ ts_list = []
sentence_start = time_stamp_postprocessed[0][0]
+ sentence_end = time_stamp_postprocessed[0][1]
texts = text_postprocessed.split()
- for i in range(len(punc_id_list)):
- sentence_text += texts[i]
- if punc_id_list[i] == 2:
- sentence_text += ','
+ punc_stamp_text_list = list(zip_longest(punc_id_list, time_stamp_postprocessed, texts, fillvalue=None))
+ for punc_stamp_text in punc_stamp_text_list:
+ punc_id, time_stamp, text = punc_stamp_text
+ # sentence_text += text if text is not None else ''
+ if text is not None:
+ if 'a' <= text[0] <= 'z' or 'A' <= text[0] <= 'Z':
+ sentence_text += ' ' + text
+ elif len(sentence_text) and ('a' <= sentence_text[-1] <= 'z' or 'A' <= sentence_text[-1] <= 'Z'):
+ sentence_text += ' ' + text
+ else:
+ sentence_text += text
+ sentence_text_seg += text + ' '
+ ts_list.append(time_stamp)
+
+ punc_id = int(punc_id) if punc_id is not None else 1
+ sentence_end = time_stamp[1] if time_stamp is not None else sentence_end
+
+ if punc_id > 1:
+ sentence_text += punc_list[punc_id - 2]
res.append({
'text': sentence_text,
"start": sentence_start,
- "end": time_stamp_postprocessed[i][1]
+ "end": sentence_end,
+ "text_seg": sentence_text_seg,
+ "ts_list": ts_list
})
sentence_text = ''
- sentence_start = time_stamp_postprocessed[i][1]
- elif punc_id_list[i] == 3:
- sentence_text += '.'
- res.append({
- 'text': sentence_text,
- "start": sentence_start,
- "end": time_stamp_postprocessed[i][1]
- })
- sentence_text = ''
- sentence_start = time_stamp_postprocessed[i][1]
+ sentence_text_seg = ''
+ ts_list = []
+ sentence_start = sentence_end
return res
--
Gitblit v1.9.1