File size: 196 Bytes
751936e
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12

import os
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("bert-base-chinese")




# vocab_size = len(tokenizer.get_vocab())
# vocab_size = tokenizer.vocab_size