Update README.md

README.md

@@ -111,7 +111,7 @@ The metric takes four optional input parameters: __label2id__, __stuff__, __per_
         ["WATER", "SKY", "LAND", "CONSTRUCTION", "ICE", "OWN_BOAT"]`
 
 * `per_class: bool = True`: By default, the results are split up per class.
-    Setting this to False will aggregate the results (average the _scores_, sum up the _numbers_; see below for explanation of _scoress_ and _numbers_)
+    Setting this to False will aggregate the results (average the _scores_, sum up the _numbers_; see below for explanation of _scores_ and _numbers_)
 * `split_sq_rq: bool = True`: By default, the PQ-score is returned in three parts: the PQ score itself, and split into the segmentation quality (SQ) and recognition quality (RQ) part.
     Setting this to False will return the PQ score only (PQ=RQ*SQ).