dengcunqin/speech_paraformer-large_asr_nat-zh-cantonese-en-16k-vocab8501-online/write_tokens_from_txt.py

import json
from pathlib import Path
import sys

config = sys.argv[1]
token_list_out = sys.argv[2]

config = Path(config)

token_list = []

with config.open("r", encoding="utf-8") as f:
	for idx, line in enumerate(f):
		line = line.rstrip()
		token_list.append(line)

file = open(token_list_out, 'w', encoding='utf-8')
json.dump(token_list, file, ensure_ascii=False, indent=4)
file.close()