Merge pull request #770 from alibaba-damo-academy/dev_lhn

hnluo

2023-07-21 3aef6df36d182f7e41e522805a96127f504eda5d

 funasr/datasets/preprocessor.py

@@ -11,7 +11,7 @@
import numpy as np
import scipy.signal
import soundfile
import jieba


from funasr.text.build_tokenizer import build_tokenizer
from funasr.text.cleaner import TextCleaner
@@ -659,6 +659,7 @@
        self.split_text_name = split_text_name
        self.seg_jieba = seg_jieba
        if self.seg_jieba:
            import jieba
            jieba.load_userdict(seg_dict_file)

    @classmethod