Update README.md

README.md

@@ -9,7 +9,7 @@ tags:
 - robust-speech-event
 - xlsr-fine-tuning-week
 datasets:
-- common_voice
+- mozilla-foundation/common_voice_8_0
 - name: Serbian comodoro Wav2Vec2 XLSR 300M CV8
   results:
   - task:
@@ -18,7 +18,21 @@ datasets:
     dataset:
       name: Common Voice 8
       type: mozilla-foundation/common_voice_8_0
-      args: hsb
+      args: sr
+    metrics:
+       - name: Test WER
+         type: wer
+         value: 48.3
+       - name: Test CER
+         type: cer
+         value: 18.5
+  - task:
+      name: Automatic Speech Recognition 
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice 8
+      type: mozilla-foundation/common_voice_8_0
+      args: sr
     metrics:
        - name: Test WER
          type: wer
@@ -38,6 +52,11 @@ It achieves the following results on the evaluation set:
 - Wer: 0.4825
 - Cer: 0.1847
 
+Evaluation on  speech-recognition-community-v2/dev_data gave the following results:
+
+- WER: 0.9718373107518604
+- CER: 0.8302740620263108
+
 ## Model description
 
 More information needed