Update README.md

README.md

@@ -50,7 +50,7 @@ Galician is a low-resource language which prior to this project lacked a semanti
 
 ### Training Data
 
-This model was pre-trained on the [SpanishSRL Dataset](http://www.nilc.icmc.usp.br/portlex/index.php/en/projects/propbankbringl) produced as part of this same project.
+This model was pre-trained on the [SpanishSRL Dataset](https://huggingface.co/datasets/mbruton/spanish_srl) produced as part of this same project.
 This model was fine-tuned on the "train" portion of the [GalicianSRL Dataset](https://huggingface.co/datasets/mbruton/galician_srl) produced as part of this same project.
 
 #### Training Hyperparameters