bugfix v1.1.11

funasr/utils/postprocess_utils.py

@@ -125,11 +125,11 @@ def abbr_dispose(words: List[Any], time_stamp: List[List] = None) -> List[Any]:
             if time_stamp is not None:
                 end = time_stamp[ts_nums[num]][1]
                 ts_lists.append([begin, end])
-        else:            
+        else:
+            word_lists.append(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] != " ":
+            if time_stamp is not None and ts_nums[num] < len(time_stamp) and words[num] != " ":
-                word_lists.append(words[num])
                 begin = time_stamp[ts_nums[num]][0]
                 end = time_stamp[ts_nums[num]][1]
                 ts_lists.append([begin, end])
@@ -302,28 +302,29 @@ def sentence_postprocess_sentencepiece(words):
     sentence = "".join(word_lists)
     return sentence, real_word_lists
 
+
 emo_dict = {
-        "<|HAPPY|>": "😊",
+    "<|HAPPY|>": "😊",
-        "<|SAD|>": "😔",
+    "<|SAD|>": "😔",
-        "<|ANGRY|>": "😡",
+    "<|ANGRY|>": "😡",
-        "<|NEUTRAL|>": "",
+    "<|NEUTRAL|>": "",
-        "<|FEARFUL|>": "😰",
+    "<|FEARFUL|>": "😰",
-        "<|DISGUSTED|>": "🤢",
+    "<|DISGUSTED|>": "🤢",
-        "<|SURPRISED|>": "😮",
+    "<|SURPRISED|>": "😮",
 }
 
 event_dict = {
-        "<|BGM|>": "🎼",
+    "<|BGM|>": "🎼",
-        "<|Speech|>": "",
+    "<|Speech|>": "",
-        "<|Applause|>": "👏",
+    "<|Applause|>": "👏",
-        "<|Laughter|>": "😀",
+    "<|Laughter|>": "😀",
-        "<|Cry|>": "😭",
+    "<|Cry|>": "😭",
-        "<|Sneeze|>": "🤧",
+    "<|Sneeze|>": "🤧",
-        "<|Breath|>": "",
+    "<|Breath|>": "",
-        "<|Cough|>": "🤧",
+    "<|Cough|>": "🤧",
 }
 
-lang_dict =  {
+lang_dict = {
     "<|zh|>": "<|lang|>",
     "<|en|>": "<|lang|>",
     "<|yue|>": "<|lang|>",
@@ -333,81 +334,90 @@ lang_dict =  {
 }
 
 emoji_dict = {
-        "<|nospeech|><|Event_UNK|>": "❓",
+    "<|nospeech|><|Event_UNK|>": "❓",
-        "<|zh|>": "",
+    "<|zh|>": "",
-        "<|en|>": "",
+    "<|en|>": "",
-        "<|yue|>": "",
+    "<|yue|>": "",
-        "<|ja|>": "",
+    "<|ja|>": "",
-        "<|ko|>": "",
+    "<|ko|>": "",
-        "<|nospeech|>": "",
+    "<|nospeech|>": "",
-        "<|HAPPY|>": "😊",
+    "<|HAPPY|>": "😊",
-        "<|SAD|>": "😔",
+    "<|SAD|>": "😔",
-        "<|ANGRY|>": "😡",
+    "<|ANGRY|>": "😡",
-        "<|NEUTRAL|>": "",
+    "<|NEUTRAL|>": "",
-        "<|BGM|>": "🎼",
+    "<|BGM|>": "🎼",
-        "<|Speech|>": "",
+    "<|Speech|>": "",
-        "<|Applause|>": "👏",
+    "<|Applause|>": "👏",
-        "<|Laughter|>": "😀",
+    "<|Laughter|>": "😀",
-        "<|FEARFUL|>": "😰",
+    "<|FEARFUL|>": "😰",
-        "<|DISGUSTED|>": "🤢",
+    "<|DISGUSTED|>": "🤢",
-        "<|SURPRISED|>": "😮",
+    "<|SURPRISED|>": "😮",
-        "<|Cry|>": "😭",
+    "<|Cry|>": "😭",
-        "<|EMO_UNKNOWN|>": "",
+    "<|EMO_UNKNOWN|>": "",
-        "<|Sneeze|>": "🤧",
+    "<|Sneeze|>": "🤧",
-        "<|Breath|>": "",
+    "<|Breath|>": "",
-        "<|Cough|>": "😷",
+    "<|Cough|>": "😷",
-        "<|Sing|>": "",
+    "<|Sing|>": "",
-        "<|Speech_Noise|>": "",
+    "<|Speech_Noise|>": "",
-        "<|withitn|>": "",
+    "<|withitn|>": "",
-        "<|woitn|>": "",
+    "<|woitn|>": "",
-        "<|GBG|>": "",
+    "<|GBG|>": "",
-        "<|Event_UNK|>": "",
+    "<|Event_UNK|>": "",
 }
 
 emo_set = {"😊", "😔", "😡", "😰", "🤢", "😮"}
-event_set = {"🎼", "👏", "😀", "😭", "🤧", "😷",}
+event_set = {
+    "🎼",
+    "👏",
+    "😀",
+    "😭",
+    "🤧",
+    "😷",
+}
+
 
 def format_str_v2(s):
-        sptk_dict = {}
+    sptk_dict = {}
-        for sptk in emoji_dict:
+    for sptk in emoji_dict:
-                sptk_dict[sptk] = s.count(sptk)
+        sptk_dict[sptk] = s.count(sptk)
-                s = s.replace(sptk, "")
+        s = s.replace(sptk, "")
-        emo = "<|NEUTRAL|>"
+    emo = "<|NEUTRAL|>"
-        for e in emo_dict:
+    for e in emo_dict:
-                if sptk_dict[e] > sptk_dict[emo]:
+        if sptk_dict[e] > sptk_dict[emo]:
-                        emo = e
+            emo = e
-        for e in event_dict:
+    for e in event_dict:
-                if sptk_dict[e] > 0:
+        if sptk_dict[e] > 0:
-                        s = event_dict[e] + s
+            s = event_dict[e] + s
-        s = s + emo_dict[emo]
+    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):
+    def get_emo(s):
-                return s[-1] if s[-1] in emo_set else None
+        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
 
-        s = s.replace("<|nospeech|><|Event_UNK|>", "❓")
+    def get_event(s):
-        for lang in lang_dict:
+        return s[0] if s[0] in event_set else None
-                s = s.replace(lang, "<|lang|>")
+
-        s_list = [format_str_v2(s_i).strip(" ") for s_i in s.split("<|lang|>")]
+    s = s.replace("<|nospeech|><|Event_UNK|>", "❓")
-        new_s = " " + s_list[0]
+    for lang in lang_dict:
-        cur_ent_event = get_event(new_s)
+        s = s.replace(lang, "<|lang|>")
-        for i in range(1, len(s_list)):
+    s_list = [format_str_v2(s_i).strip(" ") for s_i in s.split("<|lang|>")]
-                if len(s_list[i]) == 0:
+    new_s = " " + s_list[0]
-                        continue
+    cur_ent_event = get_event(new_s)
-                if get_event(s_list[i]) == cur_ent_event and get_event(s_list[i]) != None:
+    for i in range(1, len(s_list)):
-                        s_list[i] = s_list[i][1:]
+        if len(s_list[i]) == 0:
-                #else:
+            continue
-                cur_ent_event = get_event(s_list[i])
+        if get_event(s_list[i]) == cur_ent_event and get_event(s_list[i]) != None:
-                if get_emo(s_list[i]) != None and get_emo(s_list[i]) == get_emo(new_s):
+            s_list[i] = s_list[i][1:]
-                        new_s = new_s[:-1]
+        # else:
-                new_s += s_list[i].strip().lstrip()
+        cur_ent_event = get_event(s_list[i])
-        new_s = new_s.replace("The.", " ")
+        if get_emo(s_list[i]) != None and get_emo(s_list[i]) == get_emo(new_s):
-        return new_s.strip()
+            new_s = new_s[:-1]
-    
+        new_s += s_list[i].strip().lstrip()
+    new_s = new_s.replace("The.", " ")
+    return new_s.strip()

funasr/version.txt

@@ -1 +1 @@
-1.1.10
+1.1.11