Merge pull request #284421 from cdpark/refresh-ai-whisper

Feature 294024: Q&M: AI Services freshness for 180d target - Whisper model

Author: v-dirichards

articles/ai-services/openai/includes/whisper-powershell.md

@@ -36,10 +36,10 @@ $response = Invoke-RestMethod -Uri $url -Headers $headers -Form $form -Method Po
 return $response.text
 ```
 
-You can get sample audio files from the [Azure AI Speech SDK repository at GitHub](https://github.com/Azure-Samples/cognitive-services-speech-sdk/tree/master/sampledata/audiofiles).
+You can get sample audio files, such as *wikipediaOcelot.wav*, from the [Azure AI Speech SDK repository at GitHub](https://github.com/Azure-Samples/cognitive-services-speech-sdk/tree/master/sampledata/audiofiles).
 
 > [!IMPORTANT]
-> For production, use a secure way of storing and accessing your credentials like [The PowerShell Secret Management with Azure Key Vault](/powershell/utility-modules/secretmanagement/how-to/using-azure-keyvault). For more information about credential security, see the Azure AI services [security](../../security-features.md) article.
+> For production, store and access your credentials using a secure method, such as [The PowerShell Secret Management with Azure Key Vault](/powershell/utility-modules/secretmanagement/how-to/using-azure-keyvault). For more information about credential security, see [Azure AI services security](../../security-features.md).
 
 ## Output
 

articles/ai-services/openai/includes/whisper-python.md

@@ -11,8 +11,8 @@ ms.date: 3/19/2024
 
 ### Prerequisites
 
-- <a href="https://www.python.org/" target="_blank">Python 3.8 or later version</a>
-- The following Python libraries: os
+- [Python 3.8 or later](https://www.python.org)
+- The following Python library: os
 
 ### Set up
 
@@ -34,9 +34,9 @@ pip install openai==0.28.1
 
 ---
 
-1. Create a new Python file called quickstart.py. Then open it up in your preferred editor or IDE.
+1. Create a new Python file called *quickstart.py*. Then open it up in your preferred editor or IDE.
 
-1. Replace the contents of quickstart.py with the following code. Modify the code to add your deployment name:
+1. Replace the contents of *quickstart.py* with the following code. Modify the code to add your deployment name:
 
 # [OpenAI Python 1.x](#tab/python-new)
 
@@ -63,8 +63,6 @@ pip install openai==0.28.1
 
 # [OpenAI Python 0.28.1](#tab/python)
 
-
-
 ```python
     import openai
     import time
@@ -92,13 +90,16 @@ pip install openai==0.28.1
 
 ---
 
-Run the application with the python command on your quickstart file:
+Run the application using the `python` command on your quickstart file:
 
+```python
+python quickstart.py
+```
 
-You can get sample audio files from the [Azure AI Speech SDK repository at GitHub](https://github.com/Azure-Samples/cognitive-services-speech-sdk/tree/master/sampledata/audiofiles).
+You can get sample audio files, such as *wikipediaOcelot.wav*, from the [Azure AI Speech SDK repository at GitHub](https://github.com/Azure-Samples/cognitive-services-speech-sdk/tree/master/sampledata/audiofiles).
 
 > [!IMPORTANT]
-> For production, use a secure way of storing and accessing your credentials like [Azure Key Vault](/azure/key-vault/general/overview). For more information about credential security, see the Azure AI services [security](../../security-features.md) article.
+> For production, store and access your credentials using a secure method, such as [Azure Key Vault](/azure/key-vault/general/overview). For more information about credential security, see [Azure AI services security](../../security-features.md).
 
 ## Output
 

articles/ai-services/openai/includes/whisper-rest.md

@@ -20,12 +20,16 @@ curl $AZURE_OPENAI_ENDPOINT/openai/deployments/YourDeploymentName/audio/transcri
  -F file="@./wikipediaOcelot.wav"
 ```
 
-The format of your first line of the command with an example endpoint would appear as follows `curl https://aoai-docs.openai.azure.com/openai/deployments/{YourDeploymentName}/audio/transcriptions?api-version=2024-02-01 \`.
+The first line of the preceding command with an example endpoint would appear as follows:
 
-You can get sample audio files from the [Azure AI Speech SDK repository at GitHub](https://github.com/Azure-Samples/cognitive-services-speech-sdk/tree/master/sampledata/audiofiles).
+```bash
+curl https://aoai-docs.openai.azure.com/openai/deployments/{YourDeploymentName}/audio/transcriptions?api-version=2024-02-01 \
+```
+
+You can get sample audio files, such as *wikipediaOcelot.wav*, from the [Azure AI Speech SDK repository at GitHub](https://github.com/Azure-Samples/cognitive-services-speech-sdk/tree/master/sampledata/audiofiles).
 
 > [!IMPORTANT]
-> For production, use a secure way of storing and accessing your credentials like [Azure Key Vault](/azure/key-vault/general/overview). For more information about credential security, see the Azure AI services [security](../../security-features.md) article.
+> For production, store and access your credentials using a secure method, such as [Azure Key Vault](/azure/key-vault/general/overview). For more information about credential security, see [Azure AI services security](../../security-features.md).
 
 ## Output
 

articles/ai-services/openai/media/quickstarts/endpoint.png

@@ -38,7 +38,7 @@ items:
       href: dall-e-quickstart.md
     - name: Use your data
       href: use-your-data-quickstart.md
-    - name: Whisper 
+    - name: Whisper model
       href: whisper-quickstart.md
     - name: Text to speech (preview)
       href: text-to-speech-quickstart.md

articles/ai-services/openai/toc.yml

@@ -1,12 +1,12 @@
 ---
-title: 'Speech to text with Azure OpenAI Service'
+title: Convert speech to text with Azure OpenAI Service
 titleSuffix: Azure OpenAI
-description: Use the Azure OpenAI Whisper model for speech to text.
+description: Learn how to use the Azure OpenAI Whisper model for speech to text conversion.
 manager: nitinme
 ms.service: azure-ai-openai
 ms.custom: devx-track-python
 ms.topic: quickstart
-ms.date: 3/19/2024
+ms.date: 8/09/2024
 ms.reviewer: v-baolianzou
 ms.author: eur
 author: eric-urban
@@ -16,20 +16,23 @@ zone_pivot_groups: openai-whisper
 
 # Quickstart: Speech to text with the Azure OpenAI Whisper model
 
-In this quickstart, you use the Azure OpenAI Whisper model for speech to text. 
+This quickstart explains how to use the [Azure OpenAI Whisper model](../speech-service/whisper-overview.md) for speech to text conversion. The Whisper model can transcribe human speech in numerous languages, and it can also translate other languages into English.
 
-The file size limit for the Azure OpenAI Whisper model is 25 MB. If you need to transcribe a file larger than 25 MB, you can use the Azure AI Speech [batch transcription](../speech-service/batch-transcription-create.md#use-a-whisper-model) API.
+The file size limit for the Whisper model is 25 MB. If you need to transcribe a file larger than 25 MB, you can use the Azure AI Speech [batch transcription](../speech-service/batch-transcription-create.md#use-a-whisper-model) API.
+
+> [!NOTE]
+> The OpenAI Whisper model is currently in Limited Access Public Preview.
 
 ## Prerequisites
 
-- An Azure subscription - [Create one for free](https://azure.microsoft.com/free/cognitive-services?azure-portal=true).
-- An Azure OpenAI resource with a `whisper` model deployed in a supported region. [Whisper model regional availability](./concepts/models.md#whisper-models). For more information, see [Create a resource and deploy a model with Azure OpenAI](how-to/create-resource.md).
+- An Azure subscription. You can [create one for free](https://azure.microsoft.com/free/cognitive-services?azure-portal=true).
+- An Azure OpenAI resource with a Whisper model deployed in a [supported region](./concepts/models.md#whisper-models). For more information, see [Create a resource and deploy a model with Azure OpenAI](how-to/create-resource.md).
 
 ## Set up
 
 ### Retrieve key and endpoint
 
-To successfully make a call against Azure OpenAI, you'll need an **endpoint** and a **key**.
+To successfully make a call against Azure OpenAI, you need an *endpoint* and a *key*.
 
 |Variable name | Value |
 |--------------------------|-------------|
@@ -105,5 +108,5 @@ If you want to clean up and remove an Azure OpenAI resource, you can delete the
 
 ## Next steps
 
-* Learn more about how to work with Whisper models with the Azure AI Speech [batch transcription](../speech-service/batch-transcription-create.md) API.
-* For more examples, check out the [Azure OpenAI Samples GitHub repository](https://aka.ms/AOAICodeSamples)
+* To learn how to convert audio data to text in batches, see [Create a batch transcription](../speech-service/batch-transcription-create.md).
+* For more examples, check out the [Azure OpenAI Samples GitHub repository](https://aka.ms/AOAICodeSamples).