把漢字轉成拼音后可以進行深度學習分類,做內容識別
1.安裝
pip install pypinyin
2.使用
from pypinyin import Style, pinyin content = pinyin('漢語拼音') print(content)
E:\python>python pinyin.py
[['hàn'], ['yǔ'], ['pīn'], ['yīn']]
設置拼音風格
普通
from pypinyin import Style, pinyin content = pinyin('漢語拼音', style=Style.NORMAL) print(content)
E:\python>python pinyin.py
[['han'], ['yu'], ['pin'], ['yin']]
首字母
from pypinyin import Style, pinyin content = pinyin('漢語拼音', style=Style.FIRST_LETTER) print(content)
E:\python>python pinyin.py
[['h'], ['y'], ['p'], ['y']]
將漢字轉換為拼音並生成 slug 字符串
import pypinyin from pypinyin import Style content = pypinyin.slug('漢語拼音') print(content)
E:\python\>python pinyin.py
han-yu-pin-yin
修改分隔字符串
import pypinyin from pypinyin import Style content = pypinyin.slug('漢語拼音',separator=' ') print(content)
E:\python>python pinyin.py
han yu pin yin
更多可見