Update README.md

README.md

@@ -23,7 +23,11 @@ license: "apache-2.0"
 ## Usage
 
 本项目开源在中文文本纠错项目：[pycorrector](https://github.com/shibing624/pycorrector)，可支持t5模型，通过如下命令调用：
+```
+pip install -U pycorrector
+```
 
+run:
 ```python
 from pycorrector.t5.t5_corrector import T5Corrector
 nlp = T5Corrector("shibing624/mengzi-t5-base-chinese-correction").batch_t5_correct
@@ -48,6 +52,8 @@ mengzi-t5-base-chinese-correction
 `-- tokenizer.json
 ```
 
+如果需要训练t5-correction，请参考[https://github.com/shibing624/pycorrector/tree/master/pycorrector/t5](https://github.com/shibing624/pycorrector/tree/master/pycorrector/t5)
+
 ### 训练数据集
 #### SIGHAN+Wang271K中文纠错数据集
 
@@ -74,16 +80,7 @@ SIGHAN+Wang271K中文纠错数据集，数据格式：
 ]
 ```
 
-```shell
-macbert4csc
-    ├── config.json
-    ├── pytorch_model.bin
-    ├── special_tokens_map.json
-    ├── tokenizer_config.json
-    └── vocab.txt
-```
 
-如果需要训练t5-correction，请参考[https://github.com/shibing624/pycorrector/tree/master/pycorrector/t5](https://github.com/shibing624/pycorrector/tree/master/pycorrector/t5)
 
 
 ## Citation