Update README.md

README.md

@@ -18,7 +18,7 @@ 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 0.95 for the positive class on
+It was trained on human-annotated Slovenian speech corpus [ROG-Artur](http://hdl.handle.net/11356/1992) and achieves F1 of 0.968 for the positive class on
 te test split of the same dataset.
 
 
@@ -58,7 +58,7 @@ With added postprocessing, the model achieves the following metrics:
 | PL     | drop_short_initial_and_final  |    0.903 |       0.947 | 0.924 |
 | RS     | drop_short_initial_and_final  |    0.966 |       0.915 | 0.94  |
 
-
+Fop details on postprocessing see function `frames_to_intervals` in the code snippet below.
 
 # Example use:
 ```python