Updated README with WER

README.md

@@ -26,13 +26,13 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: TBD
+         value: 5.98
        - name: Google Crowsourced Corpus WER
          type: wer
-         value: TBD
+         value: 12.14
        - name: Audiobook “La llegenda de Sant Jordi” WER
          type: wer
-         value: TBD
+         value: 12.02
 ---
 
 # Wav2Vec2-Large-100k-VoxPopuli-Català
@@ -52,9 +52,9 @@ Word error rate was evaluated on the following datasets unseen by the model:
 
 | Dataset | WER |
 | ------- | --- |
-| [Test split CV+ParlamentParla]((https://github.com/ccoreilly/wav2vec2-catala/blob/master/test.csv)) | TBD |
-| [Google Crowsourced Corpus](https://www.openslr.org/69/) | TBD |
-| Audiobook “La llegenda de Sant Jordi” | TBD | 
+| [Test split CV+ParlamentParla]((https://github.com/ccoreilly/wav2vec2-catala/blob/master/test-filtered.csv)) | 5.98% |
+| [Google Crowsourced Corpus](https://www.openslr.org/69/) | 12.14% |
+| Audiobook “La llegenda de Sant Jordi” | 12.02% | 
 
 
 ## Usage