Edge Container for Speech Recognition

Containerization has been mainly used in pure software solutions, but it is gradually finding its way into the industrial systems. This paper introduces edge container with artificial intelligence for speech recognition, which performs voice control function of actuator as a part Human Machine Interface (HMI). work proposes procedure creating voice-controlled applications modern hardware and resources. The created architecture integrates well-known digital technologies such containerization, cloud, computing commercial processing tool. methodology enable actual recognition on device local network, rather than like majority recent solutions. Linux containers are designed to run without any additional configuration setup by end user. A simple adaptation commands via file may be considered an contribution work. was verified experiments running different devices, PC, Tinker Board 2, Raspberry Pi 3 4. proposed solution practical experiment show how system can created, easily managed distributed many devices around world few seconds. All this achieved downloading two types ready-made complex installations. result proven stable (network-independent) data protection low latency.