Update README.md

README.md

@@ -125,9 +125,10 @@ The model was trained on 2 **Catalan** speech datasets
 
 ### Training procedure
 
-***Catalan Matcha-TTS*** was not trained from scratch. Instead, we finetuned the model from the English multispeaker checkpoint 
-(trained with the [VCTK dataset](https://huggingface.co/datasets/vctk)) provided by the authors. 
-The embedding layer was initialized with the number of catalan speakers (47) and original hyperparameters were kept.
+***Catalan Matcha-TTS*** was finetuned from the English multispeaker checkpoint, 
+which was trained with the [VCTK dataset](https://huggingface.co/datasets/vctk) and provided by the model authors.
+
+The embedding layer was initialized with the number of catalan speakers (47) and the original hyperparameters were kept.
 
 ### Training Hyperparameters