Update README.md

README.md

@@ -91,7 +91,7 @@ The model was trained on 3 Catalan speech datasets
 |---------------------|----------|---------|
 | Festcat             | ca       | 22      |
 | OpenSLR69           | ca       | 5       |
-| lafresca            | ca       | 5       |
+| lafresca            | ca       | 3.5     |
 
 
 
@@ -118,13 +118,13 @@ We also modified the mel spectrogram loss to use 128 bins and fmax of 11025 inst
 
 Evaluation was done using the metrics on the original repo, after ~ 1000 epochs we achieve:
 
-* val_loss: 
-* f1_score: 
-* mel_loss: 
-* periodicity_loss:
-* pesq_score: 
-* pitch_loss: 
-* utmos_score: 
+* val_loss: 3.57
+* f1_score: 0.95
+* mel_loss: 0.22
+* periodicity_loss: 0.113
+* pesq_score: 3.31
+* pitch_loss: 31.61
+* utmos_score: 3.33
 
 
 ## Citation