NDStein commited on
Commit
df83a1e
·
verified ·
1 Parent(s): d354f05

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -1
README.md CHANGED
@@ -63,7 +63,12 @@ Shorter audio samples may lead to reduced prediction accuracy.
63
 
64
  The model outputs a dictionary of the following form `{"depression":score, "anxiety": score}`.
65
 
66
- If `quantize=False` (see the Usage section below), the scores are returned as raw float values which correlate monotonically with PHQ-9 and GAD-7.
 
 
 
 
 
67
 
68
  If `quantize=True` the scores are converted into integers representing the severity of depression and anxiety.
69
 
 
63
 
64
  The model outputs a dictionary of the following form `{"depression":score, "anxiety": score}`.
65
 
66
+ If `quantize=False` (see the Usage section below), the scores are returned as raw float values on arbitrary scales which correlate monotonically with PHQ-9 for depression and GAD-7 for anxiety.
67
+ For reference the cumulative distribution of scores for each label sum is plotted below.
68
+
69
+ ![score_phq](https://cdn-uploads.huggingface.co/production/uploads/64b8497349bde5d94815adf7/WEL01JNdj0zOTIEDx8KJQ.png)
70
+
71
+ ![score_gad](https://cdn-uploads.huggingface.co/production/uploads/64b8497349bde5d94815adf7/605obGq_k-h_E-gxuXoxh.png)
72
 
73
  If `quantize=True` the scores are converted into integers representing the severity of depression and anxiety.
74