Fix typo

README.md

@@ -67,7 +67,7 @@ The model was trained for 300 epochs on 16 V100 GPUs. This takes 3 days, with 4
 
 ## Evaluation results
 
-This model achieves an AP (average precision) the following results on COCO 2017 validation: a box AP (average precision) of **38.8**, a segmentation AP (average precision) of **31.1** and a PQ (panoptic quality) of **43.4**.
+This model achieves the following results on COCO 2017 validation: a box AP (average precision) of **38.8**, a segmentation AP (average precision) of **31.1** and a PQ (panoptic quality) of **43.4**.
 
 For more details regarding evaluation results, we refer to table 5 of the original paper.