Update README.md

README.md

@@ -95,7 +95,7 @@ pprint(te_results)
 ## Training
 
 ### Training data
-We used the TE dataset in Catalan called [TECA](https://huggingface.co/datasets/projecte-aina/teca) for training and evaluation.
+We used the TE dataset in Catalan called [TE-ca](https://huggingface.co/datasets/projecte-aina/teca) for training and evaluation.
 
 ### Training Procedure
 The model was trained with a batch size of 16 and a learning rate of 5e-5 for 5 epochs. We then selected the best checkpoint using the downstream task metric in the corresponding development set and then evaluated it on the test set.