Update README.md

README.md

@@ -22,10 +22,10 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 9.926
+         value: 9.633
        - name: Test CER
          type: cer
-         value: 2.807
+         value: 2.614
   - task: 
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
@@ -141,11 +141,11 @@ input_values = processor(resampled_audio, return_tensors="pt").input_values
 with torch.no_grad():
     logits = model(input_values).logits
 transcription = processor.batch_decode(logits.numpy()).text
-# => ""
+# => "domāju ka viņam viss labi"
 ```
 
 ### Eval results on Common Voice 8 "test" (WER):
 
 | Without LM | With LM (run `./eval.py`) |
 |---|---|
-| 16.997 | 9.926 |
+| 16.997 | 9.633 |