Update README.md

README.md

@@ -18,7 +18,7 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 0.110480
+         value: 0.104575
 ---
 # Wav2Vec2-Large-XLSR-53-Moroccan-Darija
 
@@ -26,14 +26,16 @@ model-index:
 
 - Fine-tuned on 50 hours of labeled Darija Audios extracted from MDVC corpus which contains more than 1000 hours of Moroccan Darija "ary".
 - Fine-tuning is ongoing 24/7 to enhance accuracy.
-- We are consistently adding data to the model every day (We prefer not to add all MDVC Corpus at once as we are trying to standardize more and more the way we write this language).
+- We are consistently adding data to the model every day (We prefer not to add all MDVC Corpus at once as we are trying to standardize more and more the way we write the Moroccan Darija.
 
 <table><thead><tr><th><strong>Training Loss</strong></th> <th><strong>Validation</strong></th> <th><strong>Loss Wer</strong></th></tr></thead> <tbody><tr>
-<td>0.530900</td>
-<td>0.131443</td>
-<td>0.110480</td>
+<td>0.490800</td>
+<td>0.123569</td>
+<td>0.104575</td>
 </tr> </tbody></table>
 
+<i>- NB: The training Loss has gone higher because we increased mask_time_prob to 50%. Training is still on to decrease it.</i>
+
 ## Usage
 
 The model can be used directly as follows: