Update README.md

Revert to normalized WER for the time being

README.md

@@ -28,27 +28,8 @@ model-index:
       args: ml
     metrics:
     - type: wer
-      value: 38.62068965517241
+      value: 11.49
       name: WER
-    - type: cer
-      value: 7.325639739086803
-      name: CER
-  - task:
-      type: automatic-speech-recognition
-      name: Automatic Speech Recognition
-    dataset:
-      name: FLEURS
-      type: google/fleurs
-      config: ml_in
-      split: test
-      args: ml_in
-    metrics:
-    - type: wer
-      value: 27.850740045862
-      name: WER
-    - type: cer
-      value: 8.821352343856674
-      name: CER
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You