Sfoglia il codice sorgente

add speaker-attributed ASR task for alimeeting

smohan-speech 2 anni fa
parent
commit
3b7e4b0d34
1 ha cambiato i file con 5 aggiunte e 4 eliminazioni
  1. 5 4
      funasr/utils/postprocess_utils.py

+ 5 - 4
funasr/utils/postprocess_utils.py

@@ -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