Update README.md

README.md

@@ -21,6 +21,28 @@ model-index:
           - name: Test CER
             type: cer
             value: 24.09
+      - task:
+          name: Automatic Speech Recognition
+          type: automatic-speech-recognition
+        dataset:
+          name: Common Voice 7
+          type: mozilla-foundation/common_voice_7_0
+          args: zh-HK
+        metrics:
+          - name: Test CER
+            type: cer
+            value: 23.10
+      - task:
+          name: Automatic Speech Recognition
+          type: automatic-speech-recognition
+        dataset:
+          name: Common Voice 8
+          type: mozilla-foundation/common_voice_8_0
+          args: zh-HK
+        metrics:
+          - name: Test CER
+            type: cer
+            value: 23.02
       - task:
           name: Automatic Speech Recognition
           type: automatic-speech-recognition
@@ -57,6 +79,8 @@ The model achieves the following results on evaluation without a language model:
 | Dataset                          | CER    |
 | -------------------------------- | ------ |
 | `Common Voice`                   | 31.73% |
+| `Common Voice 7`                 | 23.11% |
+| `Common Voice 8`                 | 23.02% |
 | `Robust Speech Event - Dev Data` | 56.60% |
 
 With the addition of the language model, it achieves the following results:
@@ -64,6 +88,8 @@ With the addition of the language model, it achieves the following results:
 | Dataset                          | CER    |
 | -------------------------------- | ------ |
 | `Common Voice`                   | 24.09% |
+| `Common Voice 7`                 | 23.10% |
+| `Common Voice 8`                 | 23.02% |
 | `Robust Speech Event - Dev Data` | 56.86% |
 
 ## Training procedure