ira2laefsky / Old Bird 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 Arduino Portenta H7 (Cortex-M7 480MHz).
Quantized (int8)
Latency
Ram
Flash
Accuracy
MFE Transfer learning (Keyword Spotting) Total
22 ms.110 ms. 132 ms.
24.7K45.0K 45.0K
-122.7K -
95.83%
Unoptimized (float32)
Latency
Ram
Flash
Accuracy
MFE Transfer learning (Keyword Spotting) Total
22 ms.514 ms. 536 ms.
24.7K69.8K 69.8K
-246.9K -
95.83%

Latest build

No deployments yet

Run this model

Scan QR code or launch in browser to test your prototype