update model card

README.md

@@ -26,6 +26,12 @@ model-index:
        - name: Test CER (no LM)
          type: cer
          value: 6.53
+       - name: Test WER (with LM)
+         type: wer
+         value: 15.065
+       - name: Test CER (with LM)
+         type: cer
+         value: 3.077
 ---
 
 # XLS-R-300M Uzbek CV8
@@ -53,7 +59,7 @@ The model is not reliable enough to use as a substitute for live captions for ac
 
 ## Training and evaluation data
 
-The 50% of the `train` common voice official split was used as training data. The 50% of the official `dev` split was used as validation data, and the full `test` set was used for final evaluation.
+The 50% of the `train` common voice official split was used as training data. The 50% of the official `dev` split was used as validation data, and the full `test` set was used for final evaluation of the model without LM, while the model with LM was evaluated only on 500 examples from the `test` set.
 
 The kenlm language model was compiled from the target sentences of the train + other datasets.