Update readme

README.md

@@ -19,11 +19,15 @@ metrics:
 This model require Mecab and senetencepiece with XLNetTokenizer.
 See details https://qiita.com/mkt3/items/4d0ae36f3f212aee8002
 
+This model uses NFKD as the normalization method for character encoding.
+Japanese muddle marks and semi-muddle marks will be lost.
+
+*日本語の濁点・半濁点がないモデルです*
+
 #### How to use
 
 ```python
-import MeCab
-import subprocess
+from fugashi import Tagger 
 
 from transformers import (
     pipeline,
@@ -33,11 +37,7 @@ from transformers import (
 
 class XLNet():
     def __init__(self):
-        cmd = 'echo `mecab-config --dicdir`"/mecab-ipadic-neologd"'
-        path = (subprocess.Popen(cmd, stdout=subprocess.PIPE, 
-            shell=True).communicate()[0]).decode('utf-8')
-        self.m = MeCab.Tagger(f"-Owakati -d {path}")
-
+        self.m = Tagger('-Owakati') 
         self.gen_model = XLNetLMHeadModel.from_pretrained("hajime9652/xlnet-japanese")
         self.gen_tokenizer = XLNetTokenizer.from_pretrained("hajime9652/xlnet-japanese")