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