add speaker-attributed ASR task for alimeeting

smohan-speech

2023-05-06 3b7e4b0d34ab0989b942ba84e077fadc5b96c036

 funasr/utils/postprocess_utils.py

@@ -106,17 +106,18 @@
        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 @@
            if ch != ' ':
                real_word_lists.append(ch)
        sentence = ''.join(word_lists).strip()
        return sentence, real_word_lists
        return sentence, real_word_lists