Update README.md

README.md

@@ -17,13 +17,13 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 0.209228
+         value: 0.194137
 ---
 # Wav2Vec2-Large-XLSR-53-Moroccan-Darija
 
 **wav2vec2-large-xlsr-53** 
 
-- Fine-tuned on 29 hours (29 people) of labeled Darija Audios.
+- Fine-tuned on 30 hours (30 people) of labeled Darija Audios.
 - Transcriptions are performed by a single individual.
 - Each hour of audio is pronounced by a different person.
 - Fine-tuning is ongoing 24/7 to enhance accuracy.
@@ -31,9 +31,9 @@ model-index:
 - Audio database is organized (by sex, age, region, ..)
 
 <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>0.007600</td>
-<td>0.320997</td>
-<td>0.209228</td>
+<td>0.034400</td>
+<td>0.229495</td>
+<td>0.194137</td>
 </tr> </tbody></table>
 
 ## Usage