Update README.md

README.md

@@ -22,6 +22,12 @@ Note that the texts should be segmented into words using Juman++ in advance.
 
 ### How to use
 
+requirement
+
+```shell
+pip install sentencepiece
+```
+
 You can use this model directly with a pipeline for text generation. Since the generation relies on some randomness, we set a seed for reproducibility:
 
 ```python
@@ -38,8 +44,8 @@ generator("早稲田 大学 で 自然 言語 処理 を", max_length=30, do_sam
 ```
 
 ```python
-from transformers import ReformerTokenizer, GPT2Model
-tokenizer = ReformerTokenizer.from_pretrained('nlp-waseda/gpt2-small-japanese')
+from transformers import AutoTokenizer, GPT2Model
+tokenizer = AutoTokenizer.from_pretrained('nlp-waseda/gpt2-small-japanese')
 model = GPT2Model.from_pretrained('nlp-waseda/gpt2-small-japanese')
 text = "早稲田 大学 で 自然 言語 処理 を"
 encoded_input = tokenizer(text, return_tensors='pt')