Ace the AI-102 exam! Learn the exact Docker command to deploy Azure Cognitive Services in containers for language detection. Perfect for Azure AI Engineers working with speech analysis.
Table of Contents
Question
You work for a Canadian company named Xerigon Inc. You plan to deploy a containerized version of an Azure Cognitive Services service that analyzes podcasts and determines if the announcer is speaking French, English, or Russian.
You configure https://xerigon.cognitiveservices.azure.com as the endpoint URI for the service, and you pull the latest version of the Speech container.
You want to run the container on an Azure virtual machine using Docker.
You run the following Docker command to run the container on the Azure virtual machine:
docker run –rm -it -p 5000:5000 \
A \
eula=accept \
apikey= 8675309411abcdef1234567890abcdef1234567890abcdef1234\
billing= B \
Complete the command by dragging the appropriate addresses from the right to the appropriate letter on the left.
Address:
- mcr.microsoft.com/product/azure-cognitive-services/speechservices/speech-to-text/about
- mcr.microsoft.com/product/azure-cognitive-services/speechservices/language-detection/about
- mcr.microsoft.com/azure-cognitive-services/textanalytics/language
- https://xerigon.cognitiveservices.azure.com
- https://xerigon.blob.core.windows.net
- wasb://xerigon.blob.core.windows.net
Answer
A. mcr.microsoft.com/product/azure-cognitive-services/speechservices/language-detection/about
B. https://xerigon.cognitiveservices.azure.com
Explanation
The Docker command would be as follows:
docker run –rm -it -p 5000:5000 \
mcr.microsoft.com/product/azure-cognitive-services/speechservices/language-detection/about \
eula=accept \
apikey= 8675309411abcdef1234567890abcdef1234567890abcdef1234 \
billing= https://xerigon.cognitiveservices.azure.com \
To run a container, you need to execute the docker run command with the following parameters:
- The –rm parameter removes the container and any anonymous volumes if they exist.
- The -it parameter allows you to run the container in interactive mode.
- The -p parameter specifies the inbound and outbound port. For example, -p 5000:5000 specifies 5000 as the inbound and outbound port for communication.
- The -billing parameter specifies the endpoint used by the service.
You would specify mcr.microsoft.com/product/azure-cognitive-services/speechservices/language-detection/about as the container image. There are several categories of Azure AI service containers that have images for various AI services, such as language, speech, and vision. The image in this URL is grouped in the speech container category and is used for detecting speech language, such as determining the language used by the narrator.
You would specify the endpoint URI of https://xerigon.cognitiveservices.azure.com as the value for the -billing parameter.
You would not use the mcr.microsoft.com/azure-cognitive-services/textanalytics/language container image. This image is used to determine the language of written text. In this scenario, you are identifying the speech of a narrator, not reading text.
You would not use the mcr.microsoft.com/product/azure-cognitive-services/speechservices/speech-to-text/about container image. This image is used to convert spoken language to text. In this scenario, you are identifying the language of a narrator, not converting spoken language to text.
The URL of xerigon.blob.core.windows.net is used to access blob storage. You can use the URL wasb://xerigon.blob.core.windows.net to access blob storage of HDInsight, and clients that support HTTPS can access blob storage through the URL https://xerigon.blob.core.windows.net.
Microsoft Azure AI Engineer Associate AI-102 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Microsoft Azure AI Engineer Associate AI-102 exam and earn Microsoft Azure AI Engineer Associate AI-102 certification.