Update README.md

README.md

@@ -16,22 +16,28 @@ metrics:
 
 # Frame classification for filled pauses
 
-This model classifies individual 20ms frames of audio based on presence of filled pauses ("eee", "errm", ...).
+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](http://hdl.handle.net/11356/1992) and achieves F1 of 0.968 for the positive class on
-te test split of the same dataset.
 
+# Training data
 
-# Evaluation
+The model was trained on human-annotated Slovenian speech corpus 
+[ROG-Artur](http://hdl.handle.net/11356/1992). Recordings from the train split were segmented into 
+at most 30s long chunks. 
 
-Although the output of the model is a series 0 or 1, describing their  20ms frames, the evaluation was done on
-event level; spans of consecutive outputs 1 were bundled together into one event. When the true and predicted
-events partially overlap, this is counted as a true positive. We report precisions, recalls, and f1-scores of the positive class.
+# Evaluation
 
+Although the output of the model is a series 0 or 1, describing their  20ms frames, 
+the evaluation was done on event level; spans of consecutive outputs 1 were 
+bundled together into one event. When the true and predicted
+events partially overlap, this is counted as a true positive. 
+We report precisions, recalls, and F1-scores of the positive class.
 
 ## Evaluation on ROG corpus
 
 
+
 | postprocessing |   recall |   precision |    F1 |
 |------:|---------:|------------:|------:|
 |none|    0.981 |       0.955 | 0.968 |
@@ -39,13 +45,18 @@ events partially overlap, this is counted as a true positive. We report precisio
 
 ## Evaluation on ParlaSpeech corpora
 
-For every language in the [ParlaSpeech collection](https://huggingface.co/collections/classla/parlaspeech-670923f23ab185f413d40795), 
+For every language in the 
+[ParlaSpeech collection](https://huggingface.co/collections/classla/parlaspeech-670923f23ab185f413d40795), 
 400 instances were sampled and annotated by human annotators. 
 
 
-Since ParlaSpeech corpora are too big to be manually segmented as ROG is, we observed a few failure modes when inferring.  It was discovered that post-processing can be used
-to improve results. False positives were observed to be caused by improper audio segmentation, which is why disabling predictions that start at the start of the audio or 
-end at the end of the audio can be beneficial. Another failure mode is predicting very short events, which is why ignoring very short predictions 
+Since ParlaSpeech corpora are too big to be manually segmented as ROG is,
+we observed a few failure modes when inferring.  It was discovered 
+that post-processing can be used to improve results. False positives 
+were observed to be caused by improper audio segmentation, which is 
+why disabling predictions that start at the start of the audio or 
+end at the end of the audio can be beneficial. Another failure mode 
+is predicting very short events, which is why ignoring very short predictions 
 can be safely discarded. 
 
 With added postprocessing, the model achieves the following metrics: