Adding one decimal to the reported WER

README.md

@@ -26,7 +26,7 @@ model-index:
         metrics:
           - name: WER
             type: wer
-            value: 11.94
+            value: 11.944
       - task:
           name: Automatic Speech Recognition
           type: automatic-speech-recognition
@@ -39,7 +39,7 @@ model-index:
         metrics:
           - name: WER
             type: wer
-            value: 10.64
+            value: 10.647
 ---
 # whisper-largev2-faroese-8k-steps-100h
 The "whisper-largev2-faroese-8k-steps-100h" is an acoustic model suitable for Automatic Speech Recognition in Faroese. It is the result of fine-tuning the model "openai/whisper-large-v2" with 100 hours of Faroese data released by the Ravnur Project (https://maltokni.fo/en/) from the Faroe Islands.