speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

bugfix v1.1.11

Browse Source
This commit is contained in:
游雁 2024-10-10 15:32:08 +08:00
parent 5fc1d918aa
commit 2330e58f5f
2 changed files with 99 additions and 89 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

186
funasr/utils/postprocess_utils.py
View File

@ -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] != " ":
word_lists.append(words[num])
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])
@ -302,28 +302,29 @@ def sentence_postprocess_sentencepiece(words):
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|>",
@ -333,81 +334,90 @@ lang_dict = {
}
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:]
# 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()

2
funasr/version.txt
View File

@ -1 +1 @@
1.1.10
1.1.11