Adding a Deployment Endpoint
To deploy an endpoint for a custom speech model, sign in to the Azure AI Foundry portal and navigate to Fine-tuning. Select the AI Service fine-tuning option and choose the custom model you wish to manage. Once you are satisfied with the test results, go to the left menu and select Deploy models, then click on + Deploy model. In the Deploy a new model wizard, select the model you want to deploy, provide a name and description for the deployment, agree to the terms of use, and click Deploy.
Changing Model and Redeploying Endpoint
You can update an endpoint to use a different model from the same Speech resource. It is crucial to update the endpoint's model before it expires. The redeployment process may take a few minutes to complete. Meanwhile, your endpoint will continue to use the previous model without any service interruption.
Viewing Logging Data
If you configured logging data while creating the endpoint, it is available for export. The logging data remains on Microsoft-owned storage for 30 days before it is deleted. If your Azure AI services subscription is linked to your own storage account, the logging data will not be automatically deleted.
Stay Ahead in Today’s Competitive Market!
Unlock your company’s full potential with a Virtual Delivery Center (VDC). Gain specialized expertise, drive
seamless operations, and scale effortlessly for long-term success.
Book a Meeting to Avail the Services of Azure Custom Speech Service