Update README.md

README.md

@@ -88,7 +88,7 @@ Consider splitting long sequences to process them separately.
 
 ## Training and evaluation data
 
-The model was fine-tuned and evaluated on splits the [DTA reviEvalCorpus](https://huggingface.co/datasets/ybracke/dta-reviEvalCorpus-v1).
+The model was fine-tuned and evaluated on the [DTA reviEvalCorpus](https://huggingface.co/datasets/ybracke/dta-reviEvalCorpus-v1).
 *DTA reviEvalCorpus* is a parallel corpus of German texts from the period between 1780 to 1899, that aligns sentences in historical spelling of with their normalizations.
 The training set contains 96 documents with 4.6M source tokens, the dev and test set contain 13 documents (405K tokens) and 12 documents (381K tokens), respectively. 
 For more information, see the [dataset card](https://huggingface.co/datasets/ybracke/dta-reviEvalCorpus-v1) of the corpus.