refresh custom speech in ai foundry

Author: eric-urban

articles/ai-services/speech-service/how-to-custom-speech-create-project.md

@@ -6,7 +6,7 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: how-to
-ms.date: 2/25/2025
+ms.date: 5/19/2025
 ms.author: eur
 zone_pivot_groups: foundry-speech-studio
 #Customer intent: As a developer, I want to learn how to customize speech models with fine-tuning so that I can train and deploy a custom model.
@@ -37,17 +37,7 @@ In the [Azure AI Foundry portal](https://ai.azure.com), you can fine-tune some A
 
     :::image type="content" source="./media/custom-speech/ai-foundry/fine-tune-azure-ai-services.png" alt-text="Screenshot of the page to select fine-tuning of Azure AI Services models." lightbox="./media/custom-speech/ai-foundry/fine-tune-azure-ai-services.png":::
 
-1. In the wizard, select **Speech to text (speech recognition)** for custom speech. Then select **Next**.
-1. Select the connected service resource that you want to use for fine-tuning. 
-
-    :::image type="content" source="./media/custom-speech/ai-foundry/new-fine-tune-select-connection.png" alt-text="Screenshot of the page to select the connected service resource that you want to use for fine-tuning." lightbox="./media/custom-speech/ai-foundry/new-fine-tune-select-connection.png":::
-
-    > [!IMPORTANT]
-    > If you train a custom model with audio data, select a service resource in a region with dedicated hardware for training audio data. See footnotes in the [regions](regions.md#regions) table for more information.
-
-    You can choose from the following connected resource types:
-    - **AI Service**: The Azure AI Services multi-service resource that [came with the Azure AI Foundry project](../../ai-services/connect-services-ai-foundry-portal.md#connect-azure-ai-services-when-you-create-a-project-for-the-first-time).
-    - **Speech Service**: An Azure AI Speech resource that was [connected after the project was created](../../ai-services/connect-services-ai-foundry-portal.md#connect-azure-ai-services-after-you-create-a-project). 
+1. In the wizard, select **Custom Speech (speech to text fine-tuning)** for custom speech. Then select **Next**.
 
 1. Enter the language, name, and description for the fine-tuning job. Then select **Create**.
 

articles/ai-services/speech-service/how-to-custom-speech-deploy-model.md

@@ -6,7 +6,7 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: how-to
-ms.date: 2/25/2025
+ms.date: 5/19/2025
 ms.author: eur
 zone_pivot_groups: foundry-speech-studio-cli-rest
 #Customer intent: As a developer, I want to learn how to deploy a custom speech model so that I can use it in my applications.
@@ -29,10 +29,9 @@ You can deploy an endpoint for a base or custom model, and then [update](#change
 ::: zone pivot="ai-foundry-portal"
 
 1. Sign in to the [Azure AI Foundry portal](https://ai.azure.com).
-1. Select **Fine-tuning** from the left pane.
-1. Select **AI Service fine-tuning**.
-1. Select the custom model that you want to manage from the **Model name** column.
-1. After you're satisfied with the test results, select **Deploy models** from the left menu. Then select **+ Deploy model**.
+1. Select **Fine-tuning** from the left pane and then select **AI Service fine-tuning**.
+1. Select the custom speech fine-tuning task (by model name) that you [started as described in the how to start custom speech fine-tuning article](./how-to-custom-speech-create-project.md).
+1. Select **Deploy models** > **+ Deploy models**. 
 
     :::image type="content" source="./media/custom-speech/ai-foundry/new-fine-tune-deploy-model.png" alt-text="Screenshot of the page with an option to deploy the custom speech model." lightbox="./media/custom-speech/ai-foundry/new-fine-tune-deploy-model.png":::
 

articles/ai-services/speech-service/how-to-custom-speech-display-text-format.md

@@ -6,7 +6,7 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: how-to
-ms.date: 2/25/2025
+ms.date: 5/19/2025
 ms.author: eur
 #Customer intent: As a developer, I want to learn how to prepare display text format training data for custom speech so that I can customize the display text formatting pipeline for my specific scenarios.
 ---

articles/ai-services/speech-service/how-to-custom-speech-evaluate-data.md

@@ -6,7 +6,7 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: how-to
-ms.date: 2/25/2025
+ms.date: 5/19/2025
 ms.author: eur
 zone_pivot_groups: foundry-speech-studio-cli-rest
 show_latex: true
@@ -24,13 +24,16 @@ In this article, you learn how to quantitatively measure and improve the accurac
 
 You can test the accuracy of your custom model by creating a test. A test requires a collection of audio files and their corresponding transcriptions. You can compare a custom model's accuracy with a speech to text base model or another custom model. After you [get](#get-test-results) the test results, [evaluate the word error rate (WER)](#evaluate-word-error-rate-wer) compared to speech recognition results.
 
+After you [upload training and testing datasets](how-to-custom-speech-upload-data.md), you can create a test.
+
 ::: zone pivot="ai-foundry-portal"
 
+To test your fine-tuned custom speech model, follow these steps:
+
 1. Sign in to the [Azure AI Foundry portal](https://ai.azure.com).
-1. Select **Fine-tuning** from the left pane.
-1. Select **AI Service fine-tuning**.
-1. Select the custom model that you want to manage from the **Model name** column.
-1. After the model is trained, select **Test models** from the left menu. Then select **+ Create test**.
+1. Select **Fine-tuning** from the left pane and then select **AI Service fine-tuning**.
+1. Select the custom speech fine-tuning task (by model name) that you [started as described in the how to start custom speech fine-tuning article](./how-to-custom-speech-create-project.md).
+1. Select **Test models** > **+ Create test**. 
 
     :::image type="content" source="./media/custom-speech/ai-foundry/new-fine-tune-test-model.png" alt-text="Screenshot of the page with an option to test your custom speech model." lightbox="./media/custom-speech/ai-foundry/new-fine-tune-test-model.png":::
 

articles/ai-services/speech-service/how-to-custom-speech-human-labeled-transcriptions.md

@@ -6,7 +6,7 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: how-to
-ms.date: 2/25/2025
+ms.date: 5/19/2025
 ms.author: eur
 #Customer intent: As a developer, I need to understand how to create human-labeled transcriptions for my audio data so that I can improve speech recognition accuracy.
 ---

articles/ai-services/speech-service/how-to-custom-speech-inspect-data.md

@@ -6,7 +6,7 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: how-to
-ms.date: 2/25/2025
+ms.date: 5/19/2025
 ms.author: eur
 zone_pivot_groups: foundry-speech-studio-cli-rest
 #Customer intent: As a developer, I want to test the recognition quality of a custom speech model so that I can determine if the provided recognition result is correct.
@@ -22,13 +22,16 @@ Side-by-side model testing is useful to validate which speech recognition model
 
 ## Create a test
 
+After you [upload training and testing datasets](how-to-custom-speech-upload-data.md), you can create a test.
+
 ::: zone pivot="ai-foundry-portal"
 
+To test your fine-tuned custom speech model, follow these steps:
+
 1. Sign in to the [Azure AI Foundry portal](https://ai.azure.com).
-1. Select **Fine-tuning** from the left pane.
-1. Select **AI Service fine-tuning**.
-1. Select the custom model that you want to manage from the **Model name** column.
-1. After the model is trained, select **Test models** from the left menu. Then select **+ Create test**.
+1. Select **Fine-tuning** from the left pane and then select **AI Service fine-tuning**.
+1. Select the custom speech fine-tuning task (by model name) that you [started as described in the how to start custom speech fine-tuning article](./how-to-custom-speech-create-project.md).
+1. Select **Test models** > **+ Create test**. 
 
     :::image type="content" source="./media/custom-speech/ai-foundry/new-fine-tune-test-model.png" alt-text="Screenshot of the page with an option to test your custom speech model." lightbox="./media/custom-speech/ai-foundry/new-fine-tune-test-model.png":::
 

articles/ai-services/speech-service/how-to-custom-speech-model-and-endpoint-lifecycle.md

@@ -7,7 +7,7 @@ manager: nitinme
 ms.author: eur
 ms.service: azure-ai-speech
 ms.topic: how-to
-ms.date: 2/25/2025
+ms.date: 5/19/2025
 ms.reviewer: heikora
 zone_pivot_groups: foundry-speech-studio-cli-rest
 #Customer intent: As a developer, I want to understand the lifecycle of custom speech models and endpoints so that I can plan for the expiration of my models.
@@ -45,7 +45,6 @@ When a custom model or base model expires, it's no longer available for transcri
 |Custom endpoint|Speech recognition requests fall back to the most recent base model for the same [locale](language-support.md?tabs=stt). You get results, but recognition might not accurately transcribe your domain data.  |Update the endpoint's model as described in the [Deploy a custom speech model](how-to-custom-speech-deploy-model.md) guide. |
 |Batch transcription |[Batch transcription](batch-transcription.md) requests for expired models fail with a 4xx error. |In each [Transcriptions_Create](/rest/api/speechtotext/transcriptions/create) REST API request body, set the `model` property to a base model or custom model that isn't expired. Otherwise don't include the `model` property to always use the latest base model. |
 
-
 ## Get base model expiration dates
 
 The last date that you could use the base model for training was shown when you created the custom model. For more information, see [Train a custom speech model](how-to-custom-speech-train-model.md).

articles/ai-services/speech-service/how-to-custom-speech-test-and-train.md

@@ -6,7 +6,7 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: how-to
-ms.date: 2/25/2025
+ms.date: 5/19/2025
 ms.author: eur
 #Customer intent: As a developer, I need to understand the types of training and testing data that I can use for a custom speech project, along with how to use and manage that data.
 ---

articles/ai-services/speech-service/how-to-custom-speech-train-model.md

@@ -6,7 +6,7 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: how-to
-ms.date: 2/25/2025
+ms.date: 5/19/2025
 ms.author: eur
 zone_pivot_groups: foundry-speech-studio-cli-rest
 #Customer intent: As a developer, I want to train a custom speech model to improve recognition accuracy for the Microsoft base model or a custom model.
@@ -33,10 +33,9 @@ You can use a custom model for a limited time after it was trained. You must per
 ::: zone pivot="ai-foundry-portal"
 
 1. Sign in to the [Azure AI Foundry portal](https://ai.azure.com).
-1. Select **Fine-tuning** from the left pane.
-1. Select **AI Service fine-tuning**.
-1. Select the custom model that you want to manage from the **Model name** column.
-1. After the data is processed, select **Train model** from the left menu. Then select **+ Train model**.
+1. Select **Fine-tuning** from the left pane and then select **AI Service fine-tuning**.
+1. Select the custom speech fine-tuning task (by model name) that you [started as described in the how to start custom speech fine-tuning article](./how-to-custom-speech-create-project.md).
+1. Select **Train model** > **+ Train model**. 
 
     :::image type="content" source="./media/custom-speech/ai-foundry/new-fine-tune-train-model.png" alt-text="Screenshot of the page with an option to start training for a custom speech model." lightbox="./media/custom-speech/ai-foundry/new-fine-tune-train-model.png":::
 

articles/ai-services/speech-service/how-to-custom-speech-transcription-editor.md

@@ -6,7 +6,7 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: how-to
-ms.date: 2/25/2025
+ms.date: 5/19/2025
 ms.author: eur
 #Customer intent: As a developer, I need to understand how to use the online transcription editor for custom speech so that I can create or edit audio + human-labeled transcriptions for custom speech.
 ---