Add more notes

docs/en/benchmark/README.rst

@@ -169,15 +169,19 @@ Word Error Rate Performance Test
 +-----------+-----------+
 
 +-------------+-------------+-------------+ 
-| Distance    | librispeech | librispeech |
-|             |  test-clean | test-other  |
+| Model       | librispeech | librispeech |
+| Type        |  test-clean | test-other  |
 +=============+=============+=============+
 | MultiNet5-en| 16.5%       | 41.4%       |
 +-------------+-------------+-------------+
 | MultiNet6-en| 9.0%        | 21.3%       |
 +-------------+-------------+-------------+
 
-speech commands Performance Test
+.. note::
+
+    The Pinyin withon tone is used to calculate Chinese WER In this test.
+
+Speech Commands Performance Test
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 +-----------+-----------+----------+------------+-------------+
@@ -187,10 +191,10 @@ speech commands Performance Test
 |           |           |          | dB)        | dB)         |
 +===========+===========+==========+============+=============+
 | MultiNet  | 3 m       |          |            |             |
-| 5_cn      |           |          |            |             |
+| 5_en      |           |          |            |             |
 +-----------+-----------+----------+------------+-------------+
 | MultiNet  | 3 m       |          |            |             |
-| 6_cm      |           |          |            |             |
+| 6_en      |           |          |            |             |
 +-----------+-----------+----------+------------+-------------+
 
 

docs/en/speech_command_recognition/README.rst

@@ -48,7 +48,9 @@ Speech Commands Customization Methods
 .. note::
     Mixed Chinese and English is not supported in command words. 
 
-    The command word cannot contain Arabic numerals and special characters.  
+    The command word cannot contain Arabic numerals and special characters.
+
+    Please refer to Chinese version documentation for Chinese speech commands customization methods. 
 
 
 MultiNet6 customize speech commands
@@ -189,14 +191,3 @@ Resource Occupancy
 ------------------
 
 For the resource occupancy for this model, see :doc:`Resource Occupancy <../benchmark/README>`.
-
-
-Other configurations
------------------------
-
-Threshold setting
-~~~~~~~~~~~~~~~~~
-
-::
-
-    More functions are still under development.

docs/zh_CN/benchmark/README.rst

@@ -155,7 +155,7 @@ MultiNet
     +-------------+-------------+-------------+-------------+-------------+
 
 Word Error Rate 性能测试
-~~~~~~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 +-----------+-----------+
 | Model     |  aishell  |
@@ -169,16 +169,20 @@ Word Error Rate 性能测试
 +-----------+-----------+
 
 +-------------+-------------+-------------+ 
-| Distance    | librispeech | librispeech |
-|             |  test-clean | test-other  |
+| Model       | librispeech | librispeech |
+| Type        |  test-clean | test-other  |
 +=============+=============+=============+
 | MultiNet5-en| 16.5%       | 41.4%       |
 +-------------+-------------+-------------+
 | MultiNet6-en| 9.0%        | 21.3%       |
 +-------------+-------------+-------------+
 
-speech commands 性能测试
-~~~~~~~~~~~~~~~~~~~~~~~
+.. note::
+
+    中文使用没有声调的拼音单元去计算WER.
+
+Speech Commands 性能测试
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 +-----------+-----------+----------+------------+-------------+
 | Model     | Distance  | Quiet    | Stationary | Speech      |
@@ -190,7 +194,7 @@ speech commands 性能测试
 | 5_cn      |           |          |            |             |
 +-----------+-----------+----------+------------+-------------+
 | MultiNet  | 3 m       |          |            |             |
-| 6_cm      |           |          |            |             |
+| 6_cn      |           |          |            |             |
 +-----------+-----------+----------+------------+-------------+
 
 TTS

docs/zh_CN/speech_command_recognition/README.rst

@@ -50,18 +50,21 @@ MultiNet 输入为经过前端语音算法（AFE）处理过的音频（格式
     
 
 自定义命令词方法
---------------
+--------------------
 
 .. note::
     不支持中英文混合
+
     不能含有阿拉伯数字和特殊字符
 
+    英语自定义命令词方法请参考英文文档
+
 MultiNet 支持多种且灵活的命令词设置方式，可通过在线或离线方法设置命令词，还允许随时动态增加/删除/修改命令词。
 
 MultiNet5和MultiNet6使用汉语拼音作为基本识别单元。比如“打开空调”，应该写成 “da kai kong tiao”，请使用以下工具将汉字转为拼音： :project_file:`tool/multinet_pinyin.py` 。
- 
+
 MultiNet6 定义方法：
-~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~~~~~~~~
 
 - 中文通过修改  :project_file:`model/multinet_model/fst/commands_cn.txt`
 
@@ -74,7 +77,7 @@ MultiNet6 定义方法：
         2 guan bi kong tiao
 
 MultiNet5 定义方法：
-~~~~~~~~~~~~~~~~~~
+~~~~~~~~~~~~~~~~~~~~~~~~
 
 -  通过 ``menuconfig``
 
@@ -198,12 +201,4 @@ MultiNet 识别结果
 资源消耗
 --------
 
-有关本模型的资源消耗情况，请见 :doc:`资源消耗 <../benchmark/README>`。
-
-其他配置和使用
---------------
-
-阈值设置
-~~~~~~~~
-
-该功能仍在开发中。
+有关本模型的资源消耗情况，请见 :doc:`资源消耗 <../benchmark/README>`。