Skip to content

Commit c3070bd

Browse files
authored
Merge pull request #1542 from MicrosoftDocs/release-ignite-ai-studio
[Ignite 2024] ship room - azure-ai-studio
2 parents 98445c7 + ea11894 commit c3070bd

File tree

349 files changed

+7284
-3028
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

349 files changed

+7284
-3028
lines changed

.openpublishing.publish.config.json

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -104,6 +104,12 @@
104104
"branch": "master",
105105
"branch_mapping": {}
106106
},
107+
{
108+
"path_to_root": "azureai-samples-nov2024",
109+
"url": "https://github.com/Azure-Samples/azureai-samples",
110+
"branch": "dantaylo/nov2024",
111+
"branch_mapping": {}
112+
},
107113
{
108114
"path_to_root": "azureml-examples-main",
109115
"url": "https://github.com/azure/azureml-examples",

articles/ai-services/document-intelligence/studio-overview.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -206,7 +206,7 @@ Share custom extraction projects with ease. For more information, see [Project s
206206

207207
Document Intelligence is part of the Azure AI services offerings in the Azure AI Studio. Each of the Azure AI services helps developers and organizations rapidly create intelligent, cutting-edge, market-ready, and responsible applications with out-of-the-box and prebuilt and customizable APIs and models.
208208

209-
Learn how to [connect your AI services hub](../../ai-studio/ai-services/connect-ai-services.md) with AI services and get started using Document Intelligence.
209+
Learn how to [connect your AI services hub](../../ai-studio/ai-services/how-to/connect-ai-services.md) with AI services and get started using Document Intelligence.
210210

211211
## Next steps
212212

articles/ai-services/includes/quickstarts/ai-studio-prerequisites.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -10,4 +10,4 @@ ms.author: eur
1010

1111
> [!div class="checklist"]
1212
> - Azure subscription - [Create one for free](https://azure.microsoft.com/free/cognitive-services).
13-
> - Some AI services features are free to try in AI Studio. For access to all capabilities described in this article, you need to [connect AI services to your hub in AI Studio](../../../ai-studio/ai-services/connect-ai-services.md#connect-to-ai-services).
13+
> - Some Azure AI services features are free to try in Azure AI Studio. For access to all capabilities described in this article, you need to [connect AI services in AI Studio](../../../ai-studio/ai-services/how-to/connect-ai-services.md).

articles/ai-services/multi-service-resource.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -72,4 +72,4 @@ The multi-service resource enables access to the following Azure AI services wit
7272
## Related content
7373

7474
- Go to the [Azure AI services hub](../ai-services/index.yml).
75-
- Try AI services in the [Azure AI Studio](../ai-studio/ai-services/connect-ai-services.md).
75+
- Try AI services in the [Azure AI Studio](../ai-studio/ai-services/how-to/connect-ai-services.md).

articles/ai-services/openai/includes/gpt-v-studio.md

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
---
22
title: 'Quickstart: Use GPT-4 Turbo with Vision on your images and videos with the Azure OpenAI Service'
33
titleSuffix: Azure OpenAI
4-
description: Use this article to get started using Azure OpenAI Studio to deploy and use the GPT-4 Turbo with Vision model.
4+
description: Use this article to get started using Azure AI Studio to deploy and use the GPT-4 Turbo with Vision model.
55
services: cognitive-services
66
manager: nitinme
77
ms.service: azure-ai-openai
@@ -10,7 +10,7 @@ ms.custom: references_regions
1010
ms.date: 10/03/2024
1111
---
1212

13-
Start exploring GPT-4 Turbo with Vision capabilities with a no-code approach through Azure OpenAI Studio.
13+
Start exploring GPT-4 Turbo with Vision capabilities with a no-code approach through Azure AI Studio.
1414

1515
## Prerequisites
1616

@@ -20,9 +20,9 @@ Start exploring GPT-4 Turbo with Vision capabilities with a no-code approach thr
2020
> [!NOTE]
2121
> It is currently not supported to turn off content filtering for the GPT-4 Turbo with Vision model.
2222
23-
## Go to Azure OpenAI Studio
23+
## Go to Azure AI Studio
2424

25-
Browse to [Azure OpenAI Studio](https://oai.azure.com/) and sign in with the credentials associated with your Azure OpenAI resource. During or after the sign-in workflow, select the appropriate directory, Azure subscription, and Azure OpenAI resource.
25+
Browse to [Azure AI Studio](https://ai.azure.com/) and sign in with the credentials associated with your Azure OpenAI resource. During or after the sign-in workflow, select the appropriate directory, Azure subscription, and Azure OpenAI resource.
2626

2727
Under **Management** select **Deployments** and **Create** a GPT-4 Turbo with Vision deployment by selecting model name: **"gpt-4"** and model version **"vision-preview"**. For more information about model deployment, see the [resource deployment guide](/azure/ai-services/openai/how-to/create-resource).
2828

@@ -50,7 +50,7 @@ In this chat session, you're instructing the assistant to aid in understanding i
5050
1. In the **Chat session** pane, enter a text prompt like "Describe this image," and upload an image with the attachment button. You can use a different text prompt for your use case. Then select **Send**.
5151
1. Observe the output provided. Consider asking follow-up questions related to the analysis of your image to learn more.
5252

53-
:::image type="content" source="../media/quickstarts/studio-vision.png" lightbox="../media/quickstarts/studio-vision.png" alt-text="Screenshot of OpenAI studio chat playground.":::
53+
:::image type="content" source="../media/quickstarts/studio-vision.png" lightbox="../media/quickstarts/studio-vision.png" alt-text="Screenshot of AI studio chat playground.":::
5454

5555

5656
## Clean up resources
-135 KB
Loading
186 KB
Loading

articles/ai-services/openai/realtime-audio-quickstart.md

Lines changed: 9 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -44,18 +44,14 @@ Support for the Realtime API was first added in API version `2024-10-01-preview`
4444

4545
Before you can use GPT-4o real-time audio, you need a deployment of the `gpt-4o-realtime-preview` model in a supported region as described in the [supported models](#supported-models) section.
4646

47-
You can deploy the model from the [Azure AI Studio model catalog](../../ai-studio/how-to/model-catalog-overview.md) or from your project in AI Studio. Follow these steps to deploy a `gpt-4o-realtime-preview` model from the model catalog:
47+
1. Go to the [AI Studio home page](https://ai.azure.com) and make sure you're signed in with the Azure subscription that has your Azure OpenAI Service resource (with or without model deployments.)
48+
1. Select the **Real-time audio** playground from under **Resource playground** in the left pane.
49+
1. Select **+ Create a deployment** to open the deployment window.
50+
1. Search for and select the `gpt-4o-realtime-preview` model and then select **Confirm**.
51+
1. In the deployment wizard, make sure to select the `2024-10-01` model version.
52+
1. Follow the wizard to deploy the model.
4853

49-
1. Sign in to [AI Studio](https://ai.azure.com) and go to the **Home** page.
50-
1. Select **Model catalog** from the left sidebar.
51-
1. Search for and select the `gpt-4o-realtime-preview` model from the Azure OpenAI collection.
52-
1. Select **Deploy** to open the deployment window.
53-
1. Enter a deployment name and select an Azure OpenAI resource.
54-
1. Select `2024-10-01` from the **Model version** dropdown.
55-
1. Modify other default settings depending on your requirements.
56-
1. Select **Deploy**. You land on the deployment details page.
57-
58-
Now that you have a deployment of the `gpt-4o-realtime-preview` model, you can use the AI Studio **Real-time audio** playground or Realtime API to interact with it in real time.
54+
Now that you have a deployment of the `gpt-4o-realtime-preview` model, you can interact with it in real time in the AI Studio **Real-time audio** playground or Realtime API.
5955

6056
## Use the GPT-4o real-time audio
6157

@@ -66,8 +62,8 @@ Now that you have a deployment of the `gpt-4o-realtime-preview` model, you can u
6662

6763
To chat with your deployed `gpt-4o-realtime-preview` model in the [Azure AI Studio](https://ai.azure.com) **Real-time audio** playground, follow these steps:
6864

69-
1. Go to your project in [Azure AI Studio](https://ai.azure.com).
70-
1. Select **Playgrounds** > **Real-time audio** from the left pane.
65+
1. the [Azure OpenAI Service page](https://ai.azure.com/resource/overview) in AI Studio. Make sure you're signed in with the Azure subscription that has your Azure OpenAI Service resource and the deployed `gpt-4o-realtime-preview` model.
66+
1. Select the **Real-time audio** playground from under **Resource playground** in the left pane.
7167
1. Select your deployed `gpt-4o-realtime-preview` model from the **Deployment** dropdown.
7268
1. Select **Enable microphone** to allow the browser to access your microphone. If you already granted permission, you can skip this step.
7369

Lines changed: 125 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,125 @@
1+
---
2+
title: Customize a speech model with fine-tuning in AI Studio
3+
titleSuffix: Azure AI services
4+
description: Learn about how to customize a speech model with fine-tuning in AI Studio.
5+
author: eric-urban
6+
manager: nitinme
7+
ms.service: azure-ai-speech
8+
ms.topic: how-to
9+
ms.date: 11/19/2024
10+
ms.author: eur
11+
#Customer intent: As a developer, I want to learn how to customize a speech model with fine-tuning in AI Studio so that I can deploy a custom model.
12+
---
13+
14+
# Customize a speech model with fine-tuning in AI Studio
15+
16+
With custom speech, you can enhance speech recognition accuracy for your applications by using a custom model for real-time speech to text, speech translation, and batch transcription. The base model, trained with Microsoft-owned data, handles common spoken language well, but a custom model can improve domain-specific vocabulary and audio conditions by providing text and audio data for training. Additionally, you can train the model with structured text for custom pronunciations, display text formatting, and profanity filtering.
17+
18+
> [!TIP]
19+
> You can bring your custom speech models from [Speech Studio](https://speech.microsoft.com) to [AI Studio](https://ai.azure.com). In AI Studio, you can pick up where you left off by connecting to your existing Speech resource. For more information about connecting to an existing Speech resource, see [Connect to an existing Speech resource](../../ai-studio/ai-services/how-to/connect-ai-services.md#connect-azure-ai-services-after-you-create-a-project).
20+
21+
In [AI Studio](https://ai.azure.com), you create a custom speech model by fine-tuning an Azure AI Speech base model with your own data. You can upload your data, test and train a custom model, compare accuracy between models, and deploy a model to a custom endpoint.
22+
23+
This article shows you how to use fine-tuning in AI Studio to create a custom speech model. For more information about custom speech, see the [custom speech overview](./custom-speech-overview.md) documentation.
24+
25+
## Start fine-tuning a model with your data
26+
27+
In AI Studio, you can fine-tune some Azure AI services models. For example, you can fine-tune a model for custom speech. Each custom model is specific to a [locale](language-support.md?tabs=stt). For example, you might fine-tune a model for English in the United States.
28+
29+
1. Go to your AI Studio project. If you need to create a project, see [Create an AI Studio project](../../ai-studio/how-to/create-projects.md).
30+
1. Select **Fine-tuning** from the left pane.
31+
1. Select **AI Service fine-tuning**.
32+
33+
:::image type="content" source="../../ai-studio/media/ai-services/fine-tune-azure-ai-services.png" alt-text="Screenshot of the page to select fine-tuning of Azure AI Services models." lightbox="../../ai-studio/media/ai-services/fine-tune-azure-ai-services.png":::
34+
35+
1. In the wizard, select **Speech to text (speech recognition)** for custom speech. Then select **Next**.
36+
1. Select the connected service resource that you want to use for fine-tuning. Then select **Next**.
37+
38+
:::image type="content" source="./media/ai-studio/custom-speech/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/ai-studio/custom-speech/new-fine-tune-select-connection.png":::
39+
40+
In this example, we can choose from the following options:
41+
- **AI Service**: The Azure AI Services multi-service resource that [came with the AI Studio project](../../ai-studio/ai-services/how-to/connect-ai-services.md#connect-azure-ai-services-when-you-create-a-project-for-the-first-time).
42+
- **Speech Service**: An Azure AI Speech resource that was [connected after the project was created](../../ai-studio/ai-services/how-to/connect-ai-services.md#connect-azure-ai-services-after-you-create-a-project).
43+
44+
1. Enter a name and description for the fine-tuning job. Then select **Next**.
45+
1. From the new left menu in the fine-tuning page, select **Manage data** and then select **Add data**.
46+
47+
:::image type="content" source="./media/ai-studio/custom-speech/new-fine-tune-add-data.png" alt-text="Screenshot of the page with an option to add data to the custom speech project." lightbox="./media/ai-studio/custom-speech/new-fine-tune-add-data.png":::
48+
49+
1. In the **Add data** wizard, select the type of training data you want to add. In this example, we select **Audio + human-labeled transcript**. Then select **Next**.
50+
51+
:::image type="content" source="./media/ai-studio/custom-speech/new-fine-tune-add-data-select-type.png" alt-text="Screenshot of the page with an option to select the type of training data you want to add." lightbox="./media/ai-studio/custom-speech/new-fine-tune-add-data-select-type.png":::
52+
53+
1. On the **Upload your data** page, select local files, Azure Blob Storage, or other shared web locations. Then select **Next**.
54+
1. Enter a name and description for the data. Then select **Next**.
55+
1. Review the data and select **Upload**. You're taken back to the **Manage data** page. The status of the data is **Processing**.
56+
57+
:::image type="content" source="./media/ai-studio/custom-speech/new-fine-tune-add-data-status-processing.png" alt-text="Screenshot of the page that shows the status of the data as processing." lightbox="./media/ai-studio/custom-speech/new-fine-tune-add-data-status-processing.png":::
58+
59+
## Train a custom model from your data
60+
61+
1. After the data is processed, select **Train model** from the left menu. Then select **+ Train model**.
62+
63+
:::image type="content" source="./media/ai-studio/custom-speech/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/ai-studio/custom-speech/new-fine-tune-train-model.png":::
64+
65+
1. In the **Train a new model** wizard, select the base model that you want to fine-tune. Then select **Next**.
66+
67+
:::image type="content" source="./media/ai-studio/custom-speech/new-fine-tune-train-model-select-base.png" alt-text="Screenshot of the page with an option to select the base model that you want to fine-tune." lightbox="./media/ai-studio/custom-speech/new-fine-tune-train-model-select-base.png":::
68+
69+
1. Select the data that you want to use for training. Then select **Next**.
70+
1. Enter a name and description for the model. Then select **Next**.
71+
1. Review the settings and select **Train a new model**. You're taken back to the **Train model** page. The status of the data is **Processing**.
72+
73+
:::image type="content" source="./media/ai-studio/custom-speech/new-fine-tune-train-model-status-processing.png" alt-text="Screenshot of the page that shows the status of the training as processing." lightbox="./media/ai-studio/custom-speech/new-fine-tune-train-model-status-processing.png":::
74+
75+
## Test the custom model
76+
77+
1. After the model is trained, select **Test models** from the left menu. Then select **+ Create test**.
78+
79+
:::image type="content" source="./media/ai-studio/custom-speech/new-fine-tune-test-model.png" alt-text="Screenshot of the page with an option to test your custom speech model." lightbox="./media/ai-studio/custom-speech/new-fine-tune-test-model.png":::
80+
81+
1. In the **Create a new test** wizard, select the test type. In this example, we select **Evaluate accuracy (Audio + transcript data)**. Then select **Next**.
82+
83+
:::image type="content" source="./media/ai-studio/custom-speech/new-fine-tune-test-model-select-type.png" alt-text="Screenshot of the page with an option to select the test type." lightbox="./media/ai-studio/custom-speech/new-fine-tune-test-model-select-type.png":::
84+
85+
1. Select the data that you want to use for testing. Then select **Next**.
86+
1. Select up to two models to evaluate and compare accuracy. In this example, we select the model that we trained and the base model. Then select **Next**.
87+
88+
:::image type="content" source="./media/ai-studio/custom-speech/new-fine-tune-test-model-select-models.png" alt-text="Screenshot of the page with an option to select up to two models to evaluate and compare accuracy." lightbox="./media/ai-studio/custom-speech/new-fine-tune-test-model-select-models.png":::
89+
90+
1. Enter a name and description for the test. Then select **Next**.
91+
1. Review the settings and select **Create test**. You're taken back to the **Test models** page. The status of the data is **Processing**.
92+
93+
:::image type="content" source="./media/ai-studio/custom-speech/new-fine-tune-test-model-status-processing.png" alt-text="Screenshot of the page that shows the status of the test as processing." lightbox="./media/ai-studio/custom-speech/new-fine-tune-test-model-status-processing.png":::
94+
95+
1. When the test status is **Succeeded**, you can view the results. Select the test to view the results.
96+
97+
98+
## Deploy the custom model
99+
100+
1. After you're satisfied with the test results, select **Deploy models** from the left menu. Then select **+ Deploy model**.
101+
102+
:::image type="content" source="./media/ai-studio/custom-speech/new-fine-tune-deploy-model.png" alt-text="Screenshot of the page with an option to deploy the custom speech model." lightbox="./media/ai-studio/custom-speech/new-fine-tune-deploy-model.png":::
103+
104+
1. In the **Deploy a new model** wizard, select the model that you want to deploy.
105+
106+
:::image type="content" source="./media/ai-studio/custom-speech/new-fine-tune-deploy-model-select-and-deploy.png" alt-text="Screenshot of the page with an option to select the model that you want to deploy." lightbox="./media/ai-studio/custom-speech/new-fine-tune-deploy-model-select-and-deploy.png":::
107+
108+
1. Enter a name and description for the deployment. Select the box to agree to the terms of use. Then select **Deploy**.
109+
110+
1. After the deployment status is **Succeeded**, you can view the deployment details. Select the deployment to view the details like the endpoint ID.
111+
112+
:::image type="content" source="./media/ai-studio/custom-speech/new-fine-tune-deploy-model-status-succeeded.png" alt-text="Screenshot of the page with an option to select the deployment to view the details like the endpoint ID." lightbox="./media/ai-studio/custom-speech/new-fine-tune-deploy-model-status-succeeded.png":::
113+
114+
## View fine-tuned models
115+
116+
You can access your custom speech models and deployments from the **Fine-tuning** page.
117+
118+
1. Select **Fine-tuning** from the left pane.
119+
1. Select **AI Service fine-tuning**.
120+
121+
:::image type="content" source="./media/ai-studio/custom-speech/fine-tune-succeeded-list.png" alt-text="Screenshot of the page where you can view fine-tuned AI services models." lightbox="./media/ai-studio/custom-speech/fine-tune-succeeded-list.png":::
122+
123+
## Related content
124+
125+
- [Custom speech overview](./custom-speech-overview.md)

articles/ai-services/speech-service/get-started-speech-to-text.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ author: eric-urban
66
manager: nitinme
77
ms.service: azure-ai-speech
88
ms.topic: quickstart
9-
ms.date: 9/18/2024
9+
ms.date: 11/19/2024
1010
ms.author: eur
1111
ms.reviewer: eur
1212
ms.custom: devx-track-python, devx-track-js, devx-track-csharp, mode-other, devx-track-extended-java, devx-track-go, build-2024

0 commit comments

Comments
 (0)