FunASR/funasr/utils/build_model.py
speech_asr 58fb22cb2b update
2023-04-19 10:09:51 +08:00

14 lines
340 B
Python

import logging
def build_model(args):
if args.token_list is not None:
with open(args.token_list, encoding="utf-8") as f:
token_list = [line.rstrip() for line in f]
args.token_list = list(token_list)
vocab_size = len(token_list)
logging.info(f"Vocabulary size: {vocab_size}")