wenke Bai / Audio Public

Target: CM33 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.

Audio

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 (10 samples)

View all

CLEER.5l1tkgt7

ID: 1663957124

Label: CLEER

Sample length: 1s

cleer.687k9oit.s2

ID: 2318202200

Label: cleer

Sample length: 1s

cleer.687k9oit.s5

ID: 2318202203

Label: cleer

Sample length: 1s

cleer.687k9oit.s6

ID: 2318202206

Label: cleer

Sample length: 1s

unknown.5nmr912q

ID: 1775021830

Label: hello

Sample length: 1s

cleer.687k9oit.s1

ID: 2318202199

Label: cleer

Sample length: 1s

unknown.5nmr8mnp

ID: 1775021574

Label: hello

Sample length: 1s

unknown.5nmr8sui

ID: 1775021726

Label: hello

Sample length: 1s

Model accuracy (Unoptimized (float32))

Validation set

Test set

On-device performance (CM33, Quantized (int8))

Latency

137 ms.

Peak RAM usage

37.1K

Flash usage

109.9K

Run this model

On any device

Clone project

Dataset summary

Data collected

10s

Sensor

audio @ 16KHz

Labels

cleer, CLEER, hello

Project info

Project ID	634620
License	Apache 2.0
No. of views	517
No. of clones	0