diff --git a/configs/rec/rec_icdar15_train.yml b/configs/rec/rec_icdar15_train.yml
index 7efbd5cf0d963229a94aa43558589b828d17cbd0..3de0ce7741cc8086b41cd1f5b98f6a8bbced90fa 100644
--- a/configs/rec/rec_icdar15_train.yml
+++ b/configs/rec/rec_icdar15_train.yml
@@ -36,12 +36,13 @@ Architecture:
   algorithm: CRNN
   Transform:
   Backbone:
-    name: ResNet
-    layers: 34
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
   Neck:
     name: SequenceEncoder
     encoder_type: rnn
-    hidden_size: 256
+    hidden_size: 96
   Head:
     name: CTCHead
     fc_decay: 0
diff --git a/doc/doc_ch/recognition.md b/doc/doc_ch/recognition.md
index 12c73d3de714a699cb01b8e4592261ee24fe41da..dc06365c6ef66fe5539887a19042dfdbfb45efa3 100644
--- a/doc/doc_ch/recognition.md
+++ b/doc/doc_ch/recognition.md
@@ -167,7 +167,7 @@ tar -xf rec_mv3_none_bilstm_ctc_v2.0_train.tar && rm -rf rec_mv3_none_bilstm_ctc
 
 ```
 # GPU训练 支持单卡，多卡训练，通过--gpus参数指定卡号
-# 训练icdar15英文数据 并将训练日志保存为 tain_rec.log
+# 训练icdar15英文数据 训练日志会自动保存为 "{save_model_dir}" 下的train.log
 python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/train.py -c configs/rec/rec_icdar15_train.yml
 ```
 <a name="数据增强"></a>
@@ -353,8 +353,7 @@ python3 tools/infer_rec.py -c configs/rec/rec_icdar15_train.yml -o Global.checkp
 
 ```
 infer_img: doc/imgs_words/en/word_1.png
-     index: [19 24 18 23 29]
-     word : joint
+        result: ('joint', 0.9998967)
 ```
 
 预测使用的配置文件必须与训练一致，如您通过 `python3 tools/train.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml` 完成了中文模型的训练，
@@ -373,6 +372,5 @@ python3 tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v
 
 ```
 infer_img: doc/imgs_words/ch/word_1.jpg
-     index: [2092  177  312 2503]
-     word : 韩国小馆
+        result: ('韩国小馆', 0.997218)
 ```
diff --git a/doc/doc_en/recognition_en.md b/doc/doc_en/recognition_en.md
index 3be0e1627f0fe09bc9c01da5871321d519273833..bc8faa0fc3df936855ead965f1e22107b576bc7a 100644
--- a/doc/doc_en/recognition_en.md
+++ b/doc/doc_en/recognition_en.md
@@ -162,7 +162,7 @@ Start training:
 
 ```
 # GPU training Support single card and multi-card training, specify the card number through --gpus
-# Training icdar15 English data and saving the log as train_rec.log
+# Training icdar15 English data and The training log will be automatically saved as train.log under "{save_model_dir}"
 python3 -m paddle.distributed.launch --gpus '0,1,2,3'  tools/train.py -c configs/rec/rec_icdar15_train.yml
 ```
 <a name="Data_Augmentation"></a>
@@ -347,8 +347,7 @@ Get the prediction result of the input image:
 
 ```
 infer_img: doc/imgs_words/en/word_1.png
-     index: [19 24 18 23 29]
-     word : joint
+        result: ('joint', 0.9998967)
 ```
 
 The configuration file used for prediction must be consistent with the training. For example, you completed the training of the Chinese model with `python3 tools/train.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml`, you can use the following command to predict the Chinese model:
@@ -366,6 +365,5 @@ Get the prediction result of the input image:
 
 ```
 infer_img: doc/imgs_words/ch/word_1.jpg
-     index: [2092  177  312 2503]
-     word : 韩国小馆
+        result: ('韩国小馆', 0.997218)
 ```
diff --git a/doc/imgs_words_en/.DS_Store b/doc/imgs_words_en/.DS_Store
deleted file mode 100644
index 5008ddfcf53c02e82d7eee2e57c38e5672ef89f6..0000000000000000000000000000000000000000
Binary files a/doc/imgs_words_en/.DS_Store and /dev/null differ