Audio – Live Detection
Help
Settings
Booting…
idle
Fused score over time
Window (s)
fused (raw)
fused (EMA)
thresh ON
thresh OFF
Live audio detection
Detection
Start
Thresholds
Hysteresis
OFF
ON
Model
Active model
Select a previously trained model.
Source
Audio input
Sender (WebRTC)
Microphone (Receiver)
Live top classes
Show chart
Displays the model’s Top-K (non-excluded) classes. Scores are raw (not percentages).
Active model weights
Show chart
Normalized Top-K weights used by detection.
Logs
Display logs
Log inference
Log ALL classes
Top-N
Autoscroll
Clear Logs
Export JSON
Settings
×
Sample Rate (target Hz)
Frame length (s)
Hop (s)
Per-class EMA τ (s)
Fused score EMA τ (s)
Min ON hold (ms)
OFF delta (below ON)
Max results from MP
Penalty map (inference)