Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

add postprocess for sensevoice

北念5448e926a215
diff --git a/examples/industrial_data_pretraining/sense_voice/demo.py b/examples/industrial_data_pretraining/sense_voice/demo.py
index 36355710e..42b15c19d 100644
--- a/examples/industrial_data_pretraining/sense_voice/demo.py
+++ b/examples/industrial_data_pretraining/sense_voice/demo.py
@@ -5,12 +5,15 @@
import sys
from funasr import AutoModel
+from funasr.utils.postprocess_utils import rich_transcription_postprocess
model_dir = "iic/SenseVoiceSmall"
input_file = (
"https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav"
)
+input_file = ("/nfs/beinian.lzr/workspace/models/modelscope_models/SenseVoice/example/rich_2.wav")
+
model = AutoModel(
model=model_dir,
)
@@ -22,4 +25,6 @@ res = model.generate(
use_itn=False,
)
-print(res)
+text = rich_transcription_postprocess(res[0]["text"])
+
+print(text)
diff --git a/funasr/utils/postprocess_utils.py b/funasr/utils/postprocess_utils.py
index 34f933c96..c4a078931 100644
--- a/funasr/utils/postprocess_utils.py
+++ b/funasr/utils/postprocess_utils.py
@@ -299,3 +299,113 @@ def sentence_postprocess_sentencepiece(words):
real_word_lists.append(ch)
sentence = "".join(word_lists)
return sentence, real_word_lists
+
+emo_dict = {
+ "<|HAPPY|>": "😊",
+ "<|SAD|>": "😔",
+ "<|ANGRY|>": "😡",
+ "<|NEUTRAL|>": "",
+ "<|FEARFUL|>": "😰",
+ "<|DISGUSTED|>": "🤢",
+ "<|SURPRISED|>": "😮",
+}
+
+event_dict = {
+ "<|BGM|>": "🎼",
+ "<|Speech|>": "",
+ "<|Applause|>": "👏",
+ "<|Laughter|>": "😀",
+ "<|Cry|>": "😭",
+ "<|Sneeze|>": "🤧",
+ "<|Breath|>": "",
+ "<|Cough|>": "🤧",
+}
+
+lang_dict = {
+ "<|zh|>": "<|lang|>",
+ "<|en|>": "<|lang|>",
+ "<|yue|>": "<|lang|>",
+ "<|ja|>": "<|lang|>",
+ "<|ko|>": "<|lang|>",
+ "<|nospeech|>": "<|lang|>",
+}
+
+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|>": "",
+}
+
+emo_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]
+
+ 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
+
+ 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()
+