indra17168 / Ambulance Siren Detector Public

Configure your deployment

You can deploy your impulse to any device. This makes the model run without an internet connection, minimizes latency, and runs with minimal power consumption. Read more.
No deployment options available for this project.
Model optimizations can increase on-device performance but may reduce accuracy. Performance estimate for Espressif ESP-EYE (ESP32 240MHz).
Quantized (int8)
Latency
Ram
Flash
Accuracy
MFCC Spectrogram MFE Raw data Classifier 1 MFCC Classifier 2 Spectogram Classifier 3 MFE Classifier 4 RAW Total
361 ms.161 ms.354 ms.4 ms.10 ms.47 ms.16 ms.9 ms. 962 ms.
15.4K27.8K19.8K62.5K3.8K19.2K10.7K17.0K 62.5K
----31.4K35.0K32.4K327.9K -
-
Unoptimized (float32)
Latency
Ram
Flash
Accuracy
MFCC Spectrogram MFE Raw data Classifier 1 MFCC Classifier 2 Spectogram Classifier 3 MFE Classifier 4 RAW Total
361 ms.161 ms.354 ms.4 ms.35 ms.247 ms.86 ms.153 ms. 1,401 ms.
15.4K27.8K19.8K62.5K6.9K68.3K33.3K63.8K 68.3K
----27.4K41.7K31.5K1.2M -
-
To compare model accuracy, clone this project and run model testing.

Run this model

Scan QR code or launch in browser to test your prototype