gridtext 文件读入的中文

gridtext_analysis.py

# 说明文档
# https://blog.csdn.net/duxin_csdn/article/details/88966295
# 库文件位置
# https://github.com/kylebgorman/textgrid
# 解析代码
import textgrid

def is_chinese(uchar):
    """判断一个unicode是否是汉字"""
    if (uchar >= u'\u4e00') and (uchar<=u'\u9fa5'):
        return True
    else:
        return False


tg = textgrid.TextGrid()
tg.read('./REC0001.textgrid')
for item in tg:
    # print(item.name, item.intervals, len(item.intervals))
    for i in item.intervals:
        print(i.mark, type(i.mark), type(i.mark.encode('utf-8')))

# 文件导入应有格式
"""
File type = "ooTextFile"
Object class = "TextGrid"

xmin = 0
xmax = 144.43
tiers? <exists>
size = 3
item []:
    item [1]:
        class = "IntervalTier"
        name = "GLOBAL"
        xmin = 0
        xmax = 144.43
        intervals: size = 1
        intervals [1]:
            xmin = 0
            xmax = 144.43
            text = "[speaker]: 1 male, 2 male, 3 male; [language]: 1 普通话, 2 普通话, 3 普通话"
    item [2]:
        class = "IntervalTier"
        name = "SPEAKER"
        xmin = 0
        xmax = 144.43
        intervals: size = 2
        intervals [1]:
            xmin = 0
            xmax = 1.1184741690417594
            text = ""
        intervals [2]:
            xmin = 1.1184741690417594
            xmax = 1.7980652315593901
            text = "3"
    item [2]:
        class = "IntervalTier"
        name = "CONTENT"
        xmin = 0
        xmax = 144.43
        intervals: size = 2
        intervals [1]:
            xmin = 0
            xmax = 1.1184741690417594
            text = "[ENS]"
        intervals [2]:
            xmin = 1.1184741690417594
            xmax = 1.7980652315593901
            text = "[UNK]你好"
        intervals [3]:
            xmin = 1.7980652315593901
            xmax = 2.7925887376827525
            text = "[ENS]"
        intervals [4]:
            xmin = 2.7925887376827525
            xmax = 3.604782934350176
            text = "[*]"
"""