Update README.md

README.md

@@ -21,15 +21,44 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 0.2960
+         value: 32.74
+       - name: Test CER
+         type: cer
+         value: 7.83
+       - name: Test WER (+LM)
+         type: wer
+         value: 19.55
+       - name: Test CER (+LM)
+         type: cer
+         value: 5.59
+  - task: 
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Robust Speech Event - Dev Data
+      type: speech-recognition-community-v2/dev_data
+      args: it
+    metrics:
+       - name: Test WER
+         type: wer
+         value: 43.23
+       - name: Test CER
+         type: cer
+         value: 13.37
+       - name: Test WER (+LM)
+         type: wer
+         value: 27.51
+       - name: Test CER (+LM)
+         type: cer
+         value: 10.69
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# wav2vec2-xls-r-1b-italian-augmented-cv-ls
+# wav2vec2-xls-r-1b-italian-robust
 
-This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the None dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the Common Voice 7 & Libri Speech datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.2428
 - Wer: 0.2960