Audio – Live Detection

Booting…
idle

Fused score over time

fused (raw) fused (EMA) thresh ON thresh OFF

Live audio detection

Detection

Thresholds

Hysteresis
OFF
ON

Model

Select a previously trained model.

Source

Audio input

Live top classes

Displays the model’s Top-K (non-excluded) classes. Scores are raw (not percentages).

Active model weights

Normalized Top-K weights used by detection.

Logs