Edge Impulse Experts / Rain_Thunder_sound Public

Target: Nordic nRF52840 DK (Cortex-M4F 64MHz) Clone this project

Welcome to Edge Impulse, the largest community of edge AI developers!
This is a public Edge Impulse project, use the navigation bar to see all data and models in this project; or clone to retrain or deploy to any edge device.

Rain_Thunder_sound

Keyword spotting

About this project

This public Edge Impulse project does not have a README yet. Clone this project to add new data or retrain this project, or to deploy this project to a device.

Data (135 samples)

View all

z_unknown.494urkhs.s1

ID: 467827117

Label: z_unknown

Sample length: 2s

z_unknown.494ugeak.s2

ID: 467827124

Label: z_unknown

Sample length: 2s

rain.spalshing.s3

ID: 467827153

Label: rain

Sample length: 2s

thunder.1.s5

ID: 467827139

Label: thunder

Sample length: 2s

z_unknown.494uuhkb.s2

ID: 467827105

Label: z_unknown

Sample length: 2s

rain.loop-1250.s5

ID: 467827175

Label: rain

Sample length: 2s

rain.big-thunder-with-rain-1291.s1

ID: 467827151

Label: thunder

Sample length: 2s

rain.494vc1jb.s2

ID: 467827096

Label: rain

Sample length: 2s

Model accuracy (Unoptimized (float32))

Validation set

93.2%

Test set

92.2%

On-device performance (Nordic nRF52840 DK (Cortex-M4F 64MHz), Quantized (int8))

Latency

155 ms.

Peak RAM usage

3.2K

Flash usage

545.5K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

4m 29s

Sensor

audio @ 16KHz

Labels

rain, thunder, z_unknown

Project info

Project ID	270172
Project version	1
License	Apache 2.0
No. of views	35,839
No. of clones	11