Update README.md

README.md

@@ -16,7 +16,38 @@ metrics:
 
 This model classifies individual 20ms frames of audio based on presence of filled pauses ("eee", "errm", ...).
 
-It was trained on human-annotated Slovenian speech corpus ROG-Artur and achieves F1 of 0.952868.
+It was trained on human-annotated Slovenian speech corpus ROG-Artur and achieves F1 of 0.952868 on the test split of the same dataset.
+
+Evaluation on 800 human-annotated instances  ParlaSpeech-HR and ParlaSpeech-RS produced the following metrics:
+
+```
+Performance on RS:
+Classification report for human vs model on event level: 
+              precision    recall  f1-score   support
+
+           0       0.97      0.87      0.92       234
+           1       0.95      0.99      0.97       542
+
+    accuracy                           0.95       776
+   macro avg       0.96      0.93      0.94       776
+weighted avg       0.95      0.95      0.95       776
+
+Performance on HR:
+Classification report for human vs model on event level: 
+              precision    recall  f1-score   support
+
+           0       0.94      0.84      0.89       242
+           1       0.93      0.98      0.95       531
+
+    accuracy                           0.93       773
+   macro avg       0.93      0.91      0.92       773
+weighted avg       0.93      0.93      0.93       773
+```
+The metrics reported are on event level, which means that if true and 
+predicted filled pauses at least partially overlap, we count them as a 
+True Positive event.
+
+
 
 # Example use:
 ```python