improved to 34.64

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 35.33
+         value: 34.64
 ---
 
 # Wav2Vec2-Large-XLSR-53-Mongolian-v1
@@ -107,7 +107,7 @@ result = test_dataset.map(evaluate, batched=True, batch_size=8)
 print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
 ```
 
-**Test Result**: 35.33 % 
+**Test Result**: 34.64 % 
 
 
 ## Training