Exam AI-102 topic 3 question 50 discussion

Okay, this link provides more information about the approval step, but approval is only necessary when you run the container in a disconnected environment. So if that is mentioned in a question, choosing this step will make more sense. https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-overview#request-approval-to-run-the-container

you are no. 1. Request approval to run container 2. Export model1 to Host1 3. Run the container

Based on what you can choose here I would say it’s a disconnected environment. For a connected environment using docker run allows you to download the model at the same so there is no need to export the model manually and then copy it to the host. Zellck is right in the choices.

Run the container with docker run: B (Request approval precedes), The docker run command will start the container when all three of the following options are provided with valid values: ApiKey, Billing, EULA https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-container-howto#billing-arguments D (Run container), C (Get model) Here's an example docker run command with placeholder values. … This command: • Runs a custom speech to text container from the container image. • Allocates 4 CPU cores and 8 GB of memory. • Loads the custom speech to text model from the volume input mount, for example, C:\CustomSpeech. • Exposes TCP port 5000 and allocates a pseudo-TTY for the container. • Downloads the model given the ModelId (if not found on the volume mount).