Update README.md

README.md

@@ -46,7 +46,7 @@ We used the CNN10 architecture, a pretrained audio neural network (PANN), introd
 The training data comprised the following data sources:
 
 Strong labels:
-- ECOSoundSet (Funosas et al., 2026): Orthoptera species as well as buzz clips.
+- ECOSoundSet (Funosas et al., 2026): Orthoptera and Hemiptera species as well as buzz clips.
 - Additional annotations by the University of Freiburg and Simon Thorne: Orthoptera species.
 - WABAD (Pérez-Granados et al., 2026): for bird recordings.
 - Edansa-2019 (Çoban, E. B., et al., 2022): for silence recordings
@@ -72,8 +72,8 @@ The input audios to the model were 4s long. If necessary shorter/longer audio fi
 
 ## Evaluation
 
-For the evaluation we only consider the results based on the Orthoptera and Hemiptera species, i.e., the results on silence, buzz, and birds are not considered. 
-We do this, as these classes were merely introduced to learn a more robust feature exctrator, but not in order to classify them later on. The focus lies on the Orthoptera species.
+For the evaluation we only consider the results based on the Orthoptera and Hemiptera (OH) species, i.e., the results on silence, buzz, and birds are not considered. 
+We do this, as these classes were merely introduced to learn a more robust feature exctrator, but not in order to classify them later on. The focus lies on the OH species.
 The performance on the test set, when using the default threshold of 0.5, reached a (macro) **F1 score of .670**.