text_to_speech / data_dict.py
waysolong
gui
f42d33e
raw
history blame contribute delete
917 Bytes
'''
Author: Wxl
Date: 2024-03-13 15:39:46
LastEditors: waysolong [email protected]
LastEditTime: 2024-03-13 15:41:25
FilePath: \text_to_speech\data_dict.py
Description:
Copyright (c) 2024 by ${git_name} email: ${git_email}, All Rights Reserved.
'''
import os
import json
scp_file1 = "train\gp.scp"
with open(scp_file1, 'rt',encoding="utf-8") as f:
lines1 = f.read().split('\n')
scp_file2 = "train\py.scp"
res = {}
with open(scp_file2, 'rt',encoding="utf-8") as f:
lines2 = f.read().split('\n')
for line1,line2 in zip(lines1,lines2):
le1 = (line1.replace(" sil","").split(" ")[1:])
le2 = (line2.replace(" sil","").split(" ")[1:])
if len(le1)!=(len(le2)):
print(456)
else:
for l1,l2 in zip(le1,le2):
res[l1] = l2
print(res)
with open("dict_han_pinyin.json","w",encoding="utf-8") as f:
json.dump(res,f,ensure_ascii=False,indent=4)