replaced cv dev with test

README.md

@@ -20,7 +20,7 @@ model-index:
         metrics:
           - name: Test CER
             type: cer
-            value: 12.14
+            value: 24.09
       - task:
           name: Automatic Speech Recognition
           type: automatic-speech-recognition
@@ -63,7 +63,7 @@ With the addition of the language model, it achieves the following results:
 
 | Dataset                          | CER    |
 | -------------------------------- | ------ |
-| `Common Voice`                   | 12.14% |
+| `Common Voice`                   | 24.09% |
 | `Robust Speech Event - Dev Data` | 56.86% |
 
 ## Training procedure

common_voice_zh-HK_test_eval_results.txt

@@ -0,0 +1,2 @@
+WER: 0.8074245939675174
+CER: 0.24090044061926724