Release notes

Current deep learning model: v2.7.9(28 Sept. 2022)

September 28, 2022

Cochl.Sense SDK v1.2.0 released

  • Changes:
    • audiosourcefile now awaits for a file path (wav or mp3) instead of a buffer
    • audio is downsampled if the sample rate is greater than 22050
    • added a new “device_name” field to identify the device on the dashboard
    • no service concept
    • new model

Breaking changes

Following the new no-service concept, the models format has been modified.


July 07, 2022

Cochl.Sense SDK v1.1.0 released

  • Changes:
    • Multi-tag support
    • Mew logging format applied
    • Fixed a memory leak related to metrcis
    • CPU usage reduced
    • Network usage reduced
    • Metrics related parameters have been added
    • When the program shutdown, the process is terminated after trying to push all metrics stored locally to the server.

Breaking changes

Following the new multi-tag feature, the metric format has been modified.

See Upload SDK Analytics for more information.


Mar 10, 2022

First release of Cochl.Sense SDK for Python(v1.0.0)


Mar 02, 2022

First release of Cochl.Sense SDK for C++(v1.0.0)