AIOmarRehan commited on
Commit
a40c093
Β·
verified Β·
1 Parent(s): 10f27a0

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +6 -7
app.py CHANGED
@@ -137,17 +137,16 @@ interface = gr.Interface(
137
  The final result is chosen by majority vote, using confidence scores to break ties.
138
  The output shows the final label, its confidence, and the predictions for each chunk.\n"
139
  "\nHow the Model Makes Predictions
 
 
140
 
141
- The audio is split into 5-second chunks and each chunk is turned into a Mel-spectrogram. A CNN predicts a label and confidence score for every chunk.
142
- The final result is based on:
143
 
144
- Majority vote β€” the class that appears most often across chunks.
145
 
146
- Tie-breaker β€” if two or more classes appear the same number of times, the model selects the one with the highest total confidence across its chunks.
147
 
148
- Final confidence β€” the average confidence of all chunks predicted as the final class.
149
-
150
- The output shows the final label, its confidence, and the per-chunk predictions.\n"
151
  ),
152
  )
153
 
 
137
  The final result is chosen by majority vote, using confidence scores to break ties.
138
  The output shows the final label, its confidence, and the predictions for each chunk.\n"
139
  "\nHow the Model Makes Predictions
140
+ The audio is split into 5-second chunks and each chunk is turned into a Mel-spectrogram. A CNN predicts a label and confidence score for every chunk.
141
+ The final result is based on:
142
 
143
+ Majority vote β€” the class that appears most often across chunks.
 
144
 
145
+ Tie-breaker β€” if two or more classes appear the same number of times, the model selects the one with the highest total confidence across its chunks.
146
 
147
+ Final confidence β€” the average confidence of all chunks predicted as the final class.
148
 
149
+ The output shows the final label, its confidence, and the per-chunk predictions.\n"
 
 
150
  ),
151
  )
152