Merge pull request #301 from MicrosoftDocs/main

9/16/2024 PM Publish

Author: Albertyang0

articles/ai-services/language-service/conversational-language-understanding/concepts/best-practices.md

@@ -47,7 +47,7 @@ You also want to avoid mixing different schema designs. Don't build half of your
 
 ## Use standard training before advanced training
 
-[Standard training](../how-to/train-model.md#training-modes) is free and faster than advanced training. It can help you quickly understand the effect of changing your training set or schema while you build the model. After you're satisfied with the schema, consider using advanced training to get the best AIQ out of your model.
+[Standard training](../how-to/train-model.md#training-modes) is free and faster than advanced training. It can help you quickly understand the effect of changing your training set or schema while you build the model. After you're satisfied with the schema, consider using advanced training to get the best model quality.
 
 ## Use the evaluation feature
 
@@ -113,7 +113,7 @@ If you enable this feature, the utterance count of your training set increases.
 
 ## Address model overconfidence
 
-Customers can use the LoraNorm recipe version if the model is being incorrectly overconfident. An example of this behavior can be like the following scenario where the model predicts the incorrect intent with 100% confidence. This score makes the confidence threshold project setting unusable.
+Customers can use the LoraNorm traning configuration version if the model is being incorrectly overconfident. An example of this behavior can be like the following scenario where the model predicts the incorrect intent with 100% confidence. This score makes the confidence threshold project setting unusable.
 
 | Text |	Predicted intent |	Confidence score |
 |----|----|----|
@@ -243,7 +243,7 @@ curl --request POST \
 
 ## Address out-of-domain utterances
 
-Customers can use the newly updated recipe version `2024-08-01-preview` (previously `2024-06-01-preview`) if the model has poor AIQ on out-of-domain utterances. An example of this scenario with the default recipe can be like the following example where the model has three intents: `Sports`, `QueryWeather`, and `Alarm`. The test utterances are out-of-domain utterances and the model classifies them as `InDomain` with a relatively high confidence score.
+Customers can use the newly updated training configuration version `2024-08-01-preview` (previously `2024-06-01-preview`) if the model has poor quality on out-of-domain utterances. An example of this scenario with the default training configuration can be like the following example where the model has three intents: `Sports`, `QueryWeather`, and `Alarm`. The test utterances are out-of-domain utterances and the model classifies them as `InDomain` with a relatively high confidence score.
 
 | Text |	Predicted intent |	Confidence score |
 |----|----|----|
@@ -273,6 +273,6 @@ After the request is sent, you can track the progress of the training job in Lan
 
 Caveats:
 
-- The None score threshold for the app (confidence threshold below which `topIntent` is marked as `None`) when you use this recipe should be set to 0. This setting is used because this new recipe attributes a certain portion of the in-domain probabilities to out of domain so that the model isn't incorrectly overconfident about in-domain utterances. As a result, users might see slightly reduced confidence scores for in-domain utterances as compared to the prod recipe.
-- We don't recommend this recipe for apps with only two intents, such as `IntentA` and `None`, for example.
-- We don't recommend this recipe for apps with a low number of utterances per intent. We highly recommend a minimum of 25 utterances per intent.
+- The None score threshold for the app (confidence threshold below which `topIntent` is marked as `None`) when you use this training configuration should be set to 0. This setting is used because this new training configuration attributes a certain portion of the in-domain probabilities to out of domain so that the model isn't incorrectly overconfident about in-domain utterances. As a result, users might see slightly reduced confidence scores for in-domain utterances as compared to the prod training configuration.
+- We don't recommend this training configuration for apps with only two intents, such as `IntentA` and `None`, for example.
+- We don't recommend this training configuration for apps with a low number of utterances per intent. We highly recommend a minimum of 25 utterances per intent.

articles/ai-services/speech-service/fast-transcription-create.md

@@ -40,6 +40,7 @@ Construct the request body according to the following instructions:
 - Set the required `locales` property. This value should match the expected locale of the audio data to transcribe. The supported locales are: en-US, es-ES, es-MX, fr-FR, hi-IN, it-IT, ja-JP, ko-KR, pt-BR, and zh-CN. You can only specify one locale per transcription request.
 - Optionally, set the `profanityFilterMode` property to specify how to handle profanity in recognition results. Accepted values are `None` to disable profanity filtering, `Masked` to replace profanity with asterisks, `Removed` to remove all profanity from the result, or `Tags` to add profanity tags. The default value is `Masked`. The `profanityFilterMode` property works the same way as via the [batch transcription API](./batch-transcription.md).
 - Optionally, set the `channels` property to specify the zero-based indices of the channels to be transcribed separately. If not specified, multiple channels are merged and transcribed jointly. Only up to two channels are supported. If you want to transcribe the channels from a stereo audio file separately, you need to specify `[0,1]` here. Otherwise, stereo audio will be merged to mono, mono audio will be left as is, and only a single channel will be transcribed. In either of the latter cases, the output has no channel indices for the transcribed text, since only a single audio stream is transcribed.
+- Optionally, set the `diarizationSettings` to recognize and separate multiple speakers on mono channel audio file. You need to specify the minimum and maximum number of people who might be speaking in the audio file (for example, specify `"diarizationSettings": {"minSpeakers": 1, "maxSpeakers": 4}`). Then the transcription file will contain a `speaker` entry for each transcribed phrase. The feature isn't available with stereo audio when you set the `channels` property as `[0,1]`.
 
 Make a multipart/form-data POST request to the `transcriptions` endpoint with the audio file and the request body properties. The following example shows how to create a transcription using the fast transcription API.
 
@@ -263,4 +264,4 @@ The response will include `duration`, `channel`, and more. The `combinedPhrases`
 
 - [Fast transcription REST API reference](/rest/api/speechtotext/transcriptions/transcribe)
 - [Speech to text supported languages](./language-support.md?tabs=stt)
-- [Batch transcription](./batch-transcription.md)
+- [Batch transcription](./batch-transcription.md)

articles/ai-services/speech-service/includes/release-notes/release-notes-stt.md

@@ -6,6 +6,11 @@ ms.date: 7/12/2024
 ms.author: eur
 ---
 
+### September 2024 release
+
+#### Fast transcription (Preview)
+Fast transcription now supports Diarization to recognize and separate multiple speakers on mono channel audio file. For more information, see [fast transcription API guide](../../fast-transcription-create.md#use-the-fast-transcription-api).
+
 ### August 2024 release
 
 #### Language learning (Preview)

articles/ai-services/translator/document-translation/reference/start-batch-translation.md

@@ -77,7 +77,7 @@ Request headers are:
           "language": "fr",
           "glossaries": [
             {
-              "glossaryUrl": "https://myblob.blob.core.windows.net/Container/myglossary.tsv",
+              "glossaryUrl": "https://myblob.blob.core.windows.net/Container/myglossary.xlf",
               "format": "XLIFF",
               "version": "2.0",
               "storageSource": "AzureBlob"

articles/ai-studio/how-to/configure-private-link.md

@@ -26,7 +26,6 @@ You get several hub default resources in your resource group. You need to config
 - Disable public network access of hub default resources such as Azure Storage, Azure Key Vault, and Azure Container Registry.
 - Establish private endpoint connection to hub default resources. You need to have both a blob and file private endpoint for the default storage account.
 - [Managed identity configurations](#managed-identity-configuration) to allow hubs access your storage account if it's private.
-- Azure AI Search should be public.
 
 
 ## Prerequisites
@@ -280,7 +279,6 @@ To check AI-PROJECT-GUID, go to the Azure portal, select your project, settings,
 
 ## Limitations
 
-* Private Azure AI Services and Azure AI Search aren't supported.
 * The "Add your data" feature in the Azure AI Studio playground doesn't support private storage account.
 * You might encounter problems trying to access the private endpoint for your hub if you're using Mozilla Firefox. This problem might be related to DNS over HTTPS in Mozilla Firefox. We recommend using Microsoft Edge or Google Chrome.
 

articles/ai-studio/how-to/create-azure-ai-resource.md

@@ -12,13 +12,14 @@ ms.date: 5/21/2024
 ms.reviewer: deeikele
 ms.author: larryfr
 author: Blackmist
+# Customer Intent: As an admin, I need to create and manage an Azure AI Studio hub so that my team can use it to create projects for collaboration.
 ---
 
 # How to create and manage an Azure AI Studio hub
 
 In AI Studio, hubs provide the environment for a team to collaborate and organize work, and help you as a team lead or IT admin centrally set up security settings and govern usage and spend. You can create and manage a hub from the Azure portal or from the AI Studio. 
 
-In this article, you learn how to create and manage a hub in AI Studio with the default settings so you can get started quickly. Do you need to customize security or the dependent resources of your hub? Then use [Azure Portal](create-secure-ai-hub.md) or [template options](create-azure-ai-hub-template.md). 
+In this article, you learn how to create and manage a hub in AI Studio with the default settings so you can get started quickly. Do you need to customize security or the dependent resources of your hub? Then use [Azure portal](create-secure-ai-hub.md) or [template options](create-azure-ai-hub-template.md). 
 
 > [!TIP]
 > If you'd like to create your Azure AI Studio hub using a template, see the articles on using [Bicep](create-azure-ai-hub-template.md) or [Terraform](create-hub-terraform.md).
@@ -105,7 +106,7 @@ For hubs that use CMK encryption mode, you can update the encryption key to a ne
 
 To use custom environments for Prompt Flow, you're required to configure an Azure Container Registry for your hub. To use Azure Application Insights for Prompt Flow deployments, a configured Azure Application Insights resource is required for your hub. Updating the workspace-attached Azure Container Registry or ApplicationInsights resources may break lineage of previous jobs, deployed inference endpoints, or your ability to rerun earlier jobs in the workspace. 
 
-You can use the Azure Portal, Azure SDK/CLI options, or the infrastructure-as-code templates to update both Azure Application Insights and Azure Container Registry for the hub.
+You can use the Azure portal, Azure SDK/CLI options, or the infrastructure-as-code templates to update both Azure Application Insights and Azure Container Registry for the hub.
 
 # [Azure portal](#tab/portal)
 
@@ -142,7 +143,23 @@ az ml workspace update -n "myexamplehub" -g "{MY_RESOURCE_GROUP}" -a "APPLICATIO
 ```
 ---
 
-## Next steps
+## Delete an Azure AI Studio hub
+
+To delete a hub, use the [Azure portal](https://portal.azure.com). To quickly get to the Azure portal from the Azure AI Studio, go to the **Hub overview** for your hub and then select **Manage in Azure portal**.
+
+:::image type="content" source="../media/how-to/hubs/manage-hub-azure-portal.png" alt-text="Screenshot of the manage in Azure portal link in Azure AI Studio.":::
+
+From the portal page for your hub, select **Overview** along the left side of the page and then select **Delete** from the top of the page.
+
+:::image type="content" source="../media/how-to/hubs/delete-hub-button.png" alt-text="Screenshot of the delete button for the Azure AI Studio hub in the Azure portal.":::
+
+You can also find your hub in the Azure portal by entering the hub name in the search field at the top of the Azure portal. Select the hub from the **Resources** list to navigate to the **Overview** page for the hub.
+
+:::image type="content" source="../media/how-to/hubs/search-in-portal.png" alt-text="Screenshot of using the search field in the Azure portal to find a hub.":::
+
+
+
+## Related content
 
 - [Create a project](create-projects.md)
 - [Learn more about Azure AI Studio](../what-is-ai-studio.md)

articles/ai-studio/media/how-to/hubs/delete-hub-button.png

@@ -51,14 +51,14 @@ items:
       href: concepts/ai-resources.md
     - name: Create your first hub
       href: how-to/create-azure-ai-resource.md
+    - name: Create a hub using the Azure Machine Learning SDK and CLI
+      href: how-to/develop/create-hub-project-sdk.md
     - name: Create a hub with custom security
       items:
       - name: Create a hub in the Azure portal
         href: how-to/create-secure-ai-hub.md
       - name: Create a hub from template
         href: how-to/create-azure-ai-hub-template.md
-      - name: Create a hub using the Azure Machine Learning SDK and CLI
-        href: how-to/develop/create-hub-project-sdk.md
         displayName: code
       - name: Create a hub using Terraform
         href: how-to/create-hub-terraform.md