Today at Microsoft’s annual Build conference we’re announcing that the Translator service on Azure is now available in containers as gated preview. Containers enable you to run some features of the Translator service in your own environment. Containers are ideal for organizations with limited Internet connectivity, or for organizations with specific security and data governance requirements that prevent them from sending information to the cloud. For organizations without these constraints, the Azure Cloud service remains a scalable and secure solution for automatic machine translation.

Containerization is an approach to software distribution in which an application or service, including its dependencies and configuration, is packaged together as a container image that can be deployed on a container host. Containers are isolated from each other and the underlying operating system with a smaller footprint than a virtual machine. Containers can be instantiated from container images for short-term tasks and removed when no longer needed.

Features of Containers

• Keep Data In House: Certain industries may have regulations that prohibit sending data to the cloud. Containers allow data to be kept on premises to comply with these regulations.
• Portable architecture: Containers enable the creation of a portable application architecture that can be deployed on Azure, on-premises, and the edge.
• Flexibility: With containers, you can run the latest models in the Translator service and update those models when you want to update them.

Learn more about the features and functionality of Translator containers in the Translator documentation.

Container support is also available for other Cognitive Services, including Text Analytics, Speech, and Vision to add even more capabilities to your custom-built translation solutions. For instance, you could use Text Analytics containers for language detection prior to translation with Translator containers.

How to get started

Translator containers are currently in gated preview. To get started, review the prequisites for running Translator containers. After you have reviewed the prerequisites you can request approval here.

Container documentation can be found at here.

References:

• Container support for Azure Cognitive Services
• Send your feedback to [email protected]