keep only the results of relevant language

docs/en/benchmark/README.rst

@@ -157,17 +157,6 @@ Resource Occupancy
 Word Error Rate Performance Test
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-+-----------+-----------+
-| Model     |  aishell  |
-| Type      |   test    |
-+===========+===========+
-| MultiNet  |    9.5%   |
-| 5_cn      |           |
-+-----------+-----------+
-| MultiNet  |    5.2%   |
-| 6_cn      |           |
-+-----------+-----------+
-
 +-------------+-------------+-------------+ 
 | Model       | librispeech | librispeech |
 | Type        |  test-clean | test-other  |
@@ -177,10 +166,6 @@ Word Error Rate Performance Test
 | MultiNet6-en| 9.0%        | 21.3%       |
 +-------------+-------------+-------------+
 
-.. note::
-
-    The Pinyin withon tone is used to calculate Chinese WER In this test.
-
 Speech Commands Performance Test
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 

docs/zh_CN/benchmark/README.rst

@@ -168,15 +168,6 @@ Word Error Rate 性能测试
 | 6_cn      |           |
 +-----------+-----------+
 
-+-------------+-------------+-------------+ 
-| Model       | librispeech | librispeech |
-| Type        |  test-clean | test-other  |
-+=============+=============+=============+
-| MultiNet5-en| 16.5%       | 41.4%       |
-+-------------+-------------+-------------+
-| MultiNet6-en| 9.0%        | 21.3%       |
-+-------------+-------------+-------------+
-
 .. note::
 
     中文使用没有声调的拼音单元去计算WER.