iarakis / Ascensores Ermua Public

Target: Cortex-M4F 80MHz 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.

Ascensores Ermua

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 (14,568 samples)

View all

5c8af87a_nohash_1.wav.2lnvfi13

ID: 90761106

Label: up

Sample length: 1s

dff327c5_nohash_1.wav.2lnvvatf

ID: 90753983

Label: three

Sample length: 1s

5eb5fc74_nohash_1.wav.2lnvoq66

ID: 90757302

Label: two

Sample length: 554ms

8a1c449e_nohash_0.wav.2lo015j3

ID: 90753467

Label: one

Sample length: 1s

377e916b_nohash_0.wav.2lo01m91

ID: 90753077

Label: one

Sample length: 853ms

fb7c9b3b_nohash_0.wav.2lnvntt4

ID: 90757569

Label: zero

Sample length: 1s

1ecfb537_nohash_1.wav.2lnvsprq

ID: 90755607

Label: three

Sample length: 1s

eb3f7d82_nohash_0.wav.2lnvd7nq

ID: 90761498

Label: down

Sample length: 1s

Model accuracy (Unoptimized (float32))

Validation set

88.7%

Test set

79.9%

On-device performance (Cortex-M4F 80MHz, Quantized (int8))

Latency

172 ms.

Peak RAM usage

16.8K

Flash usage

35.6K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

4h 0m 8s

Sensor

audio @ 16KHz

Labels

background, down, glass_breaking, gunshots, one and 4 others

Project info

Project ID	80558
Project version	1
License	No license attached
No. of views	156,584
No. of clones	7