python/FunASR-XL.git

			@@ -122,12 +122,14 @@
			abbr_word += words[num].upper()
			num += 1
			word_lists.append(abbr_word)
			if time_stamp is not None:
			if time_stamp is not None and ts_nums[num] < len(time_stamp):
			end = time_stamp[ts_nums[num]][1]
			ts_lists.append([begin, end])
			else:
			word_lists.append(words[num])
			if time_stamp is not None and words[num] != " ":
			# length of time_stamp may not equal to length of words because of the (somehow improper) threshold set in timestamp_tools.py line 46, e.g., length of time_stamp can be zero but length of words is not.
			# Moreover, move "word_lists.append(words[num])" into if clause, to keep length of word_lists and length of ts_lists equal.
			if time_stamp is not None and ts_nums[num] < len(time_stamp) and words[num] != " ":
			begin = time_stamp[ts_nums[num]][0]
			end = time_stamp[ts_nums[num]][1]
			ts_lists.append([begin, end])
			@@ -300,28 +302,29 @@
			sentence = "".join(word_lists)
			return sentence, real_word_lists


			emo_dict = {
			"<\|HAPPY\|>": "😊",
			"<\|SAD\|>": "😔",
			"<\|ANGRY\|>": "😡",
			"<\|NEUTRAL\|>": "",
			"<\|FEARFUL\|>": "😰",
			"<\|DISGUSTED\|>": "🤢",
			"<\|SURPRISED\|>": "😮",
			"<\|HAPPY\|>": "😊",
			"<\|SAD\|>": "😔",
			"<\|ANGRY\|>": "😡",
			"<\|NEUTRAL\|>": "",
			"<\|FEARFUL\|>": "😰",
			"<\|DISGUSTED\|>": "🤢",
			"<\|SURPRISED\|>": "😮",
			}

			event_dict = {
			"<\|BGM\|>": "🎼",
			"<\|Speech\|>": "",
			"<\|Applause\|>": "👏",
			"<\|Laughter\|>": "😀",
			"<\|Cry\|>": "😭",
			"<\|Sneeze\|>": "🤧",
			"<\|Breath\|>": "",
			"<\|Cough\|>": "🤧",
			"<\|BGM\|>": "🎼",
			"<\|Speech\|>": "",
			"<\|Applause\|>": "👏",
			"<\|Laughter\|>": "😀",
			"<\|Cry\|>": "😭",
			"<\|Sneeze\|>": "🤧",
			"<\|Breath\|>": "",
			"<\|Cough\|>": "🤧",
			}

			lang_dict = {
			lang_dict = {
			"<\|zh\|>": "<\|lang\|>",
			"<\|en\|>": "<\|lang\|>",
			"<\|yue\|>": "<\|lang\|>",
			@@ -331,81 +334,92 @@
			}

			emoji_dict = {
			"<\|nospeech\|><\|Event_UNK\|>": "❓",
			"<\|zh\|>": "",
			"<\|en\|>": "",
			"<\|yue\|>": "",
			"<\|ja\|>": "",
			"<\|ko\|>": "",
			"<\|nospeech\|>": "",
			"<\|HAPPY\|>": "😊",
			"<\|SAD\|>": "😔",
			"<\|ANGRY\|>": "😡",
			"<\|NEUTRAL\|>": "",
			"<\|BGM\|>": "🎼",
			"<\|Speech\|>": "",
			"<\|Applause\|>": "👏",
			"<\|Laughter\|>": "😀",
			"<\|FEARFUL\|>": "😰",
			"<\|DISGUSTED\|>": "🤢",
			"<\|SURPRISED\|>": "😮",
			"<\|Cry\|>": "😭",
			"<\|EMO_UNKNOWN\|>": "",
			"<\|Sneeze\|>": "🤧",
			"<\|Breath\|>": "",
			"<\|Cough\|>": "😷",
			"<\|Sing\|>": "",
			"<\|Speech_Noise\|>": "",
			"<\|withitn\|>": "",
			"<\|woitn\|>": "",
			"<\|GBG\|>": "",
			"<\|Event_UNK\|>": "",
			"<\|nospeech\|><\|Event_UNK\|>": "❓",
			"<\|zh\|>": "",
			"<\|en\|>": "",
			"<\|yue\|>": "",
			"<\|ja\|>": "",
			"<\|ko\|>": "",
			"<\|nospeech\|>": "",
			"<\|HAPPY\|>": "😊",
			"<\|SAD\|>": "😔",
			"<\|ANGRY\|>": "😡",
			"<\|NEUTRAL\|>": "",
			"<\|BGM\|>": "🎼",
			"<\|Speech\|>": "",
			"<\|Applause\|>": "👏",
			"<\|Laughter\|>": "😀",
			"<\|FEARFUL\|>": "😰",
			"<\|DISGUSTED\|>": "🤢",
			"<\|SURPRISED\|>": "😮",
			"<\|Cry\|>": "😭",
			"<\|EMO_UNKNOWN\|>": "",
			"<\|Sneeze\|>": "🤧",
			"<\|Breath\|>": "",
			"<\|Cough\|>": "😷",
			"<\|Sing\|>": "",
			"<\|Speech_Noise\|>": "",
			"<\|withitn\|>": "",
			"<\|woitn\|>": "",
			"<\|GBG\|>": "",
			"<\|Event_UNK\|>": "",
			}

			emo_set = {"😊", "😔", "😡", "😰", "🤢", "😮"}
			event_set = {"🎼", "👏", "😀", "😭", "🤧", "😷",}
			event_set = {
			"🎼",
			"👏",
			"😀",
			"😭",
			"🤧",
			"😷",
			}


			def format_str_v2(s):
			sptk_dict = {}
			for sptk in emoji_dict:
			sptk_dict[sptk] = s.count(sptk)
			s = s.replace(sptk, "")
			emo = "<\|NEUTRAL\|>"
			for e in emo_dict:
			if sptk_dict[e] > sptk_dict[emo]:
			emo = e
			for e in event_dict:
			if sptk_dict[e] > 0:
			s = event_dict[e] + s
			s = s + emo_dict[emo]
			sptk_dict = {}
			for sptk in emoji_dict:
			sptk_dict[sptk] = s.count(sptk)
			s = s.replace(sptk, "")
			emo = "<\|NEUTRAL\|>"
			for e in emo_dict:
			if sptk_dict[e] > sptk_dict[emo]:
			emo = e
			for e in event_dict:
			if sptk_dict[e] > 0:
			s = event_dict[e] + s
			s = s + emo_dict[emo]

			for emoji in emo_set.union(event_set):
			s = s.replace(" " + emoji, emoji)
			s = s.replace(emoji + " ", emoji)
			return s.strip()
			for emoji in emo_set.union(event_set):
			s = s.replace(" " + emoji, emoji)
			s = s.replace(emoji + " ", emoji)
			return s.strip()


			def rich_transcription_postprocess(s):
			def get_emo(s):
			return s[-1] if s[-1] in emo_set else None
			def get_event(s):
			return s[0] if s[0] in event_set else None
			def get_emo(s):
			return s[-1] if s[-1] in emo_set else None

			s = s.replace("<\|nospeech\|><\|Event_UNK\|>", "❓")
			for lang in lang_dict:
			s = s.replace(lang, "<\|lang\|>")
			s_list = [format_str_v2(s_i).strip(" ") for s_i in s.split("<\|lang\|>")]
			new_s = " " + s_list[0]
			cur_ent_event = get_event(new_s)
			for i in range(1, len(s_list)):
			if len(s_list[i]) == 0:
			continue
			if get_event(s_list[i]) == cur_ent_event and get_event(s_list[i]) != None:
			s_list[i] = s_list[i][1:]
			#else:
			cur_ent_event = get_event(s_list[i])
			if get_emo(s_list[i]) != None and get_emo(s_list[i]) == get_emo(new_s):
			new_s = new_s[:-1]
			new_s += s_list[i].strip().lstrip()
			new_s = new_s.replace("The.", " ")
			return new_s.strip()

			def get_event(s):
			return s[0] if s[0] in event_set else None

			s = s.replace("<\|nospeech\|><\|Event_UNK\|>", "❓")
			for lang in lang_dict:
			s = s.replace(lang, "<\|lang\|>")
			s_list = [format_str_v2(s_i).strip(" ") for s_i in s.split("<\|lang\|>")]
			new_s = " " + s_list[0]
			cur_ent_event = get_event(new_s)
			for i in range(1, len(s_list)):
			if len(s_list[i]) == 0:
			continue
			if get_event(s_list[i]) == cur_ent_event and get_event(s_list[i]) != None:
			s_list[i] = s_list[i][1:]
			if len(s_list[i]) == 0:
			continue
			# else:
			cur_ent_event = get_event(s_list[i])
			if get_emo(s_list[i]) != None and get_emo(s_list[i]) == get_emo(new_s):
			new_s = new_s[:-1]
			new_s += s_list[i].strip().lstrip()
			new_s = new_s.replace("The.", " ")
			return new_s.strip()