Update README.md

README.md

@@ -129,12 +129,18 @@ The embedding layer was initialized with the number of catalan speakers (47) and
 * f_min: 0
 * f_max: 8000
 * data_statistics:
-**  mel_mean: -6.578195
-**  mel_std: 2.538758
+  * mel_mean: -6578195
+  * mel_std: 2.538758
 * number of samples: 13340
 
 ## Evaluation
 
+Validation values obtained from tensorboard from epoch 2399: 
+(Note that the finetuning started from epoch 1864, as previous ones were trained with VCTK dataset)
+
+* val_dur_loss_epoch: 0.38
+* val_prior_loss_epoch: 0.97
+* val_diff_loss_epoch: 2.195
 
 ## Citation