Merge pull request #2418 from MicrosoftDocs/main

1/22/2025 11:00 AM IST Publish

Author: PhilKang0704

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

@@ -1,11 +1,23 @@
----
 author: eric-urban
 ms.service: azure-ai-speech
 ms.topic: include
-ms.date: 11/19/2024
+ms.date: 1/21/2025
 ms.author: eur
 ---
 
+### January 2025 release
+
+#### Real-time speech to text - New English model release
+
+Announcing the release of the latest English speech model (en-US, en-CA), which brings substantial improvements across various performance metrics. Below are the key highlights of this release:
+- Accessibility Enhancements: Achieved a 36% reduction in Word Error Rate (WER) on Microsoft internal accessibility test sets, making speech recognition more accurate and reliable for recognizing speech from individuals with speech disabilities.
+- 
+- Ghost Word Reduction: A remarkable 90% reduction in ghost words on the ghost word development set and reductions range from 63% to 100% across other ghost word datasets, significantly enhancing the clarity and accuracy of transcriptions.
+- 
+The new model also improved the overall performance, including entity recognition and better recognition of spelled-out letters.
+
+These advancements are expected to provide a more accurate, efficient, and satisfying experience for all users. The new model is available through the API and Azure AI Foundry playground. Feedback is encouraged to further refine its capabilities.
+
 ### November 2024 release
 
 #### Speech to text REST API version 2024-11-15

articles/machine-learning/media/how-to-configure-environment/amlsdk-withoutautoml.jpg

@@ -8,7 +8,7 @@ ms.author: manashg
 ms.reviewer: ssalgado
 ms.service: azure-machine-learning
 ms.subservice: automl
-ms.date: 10/21/2021
+ms.date: 01/21/2025
 ms.topic: how-to
 ms.custom: UpdateFrequency5
 monikerRange: 'azureml-api-1'
@@ -18,7 +18,7 @@ monikerRange: 'azureml-api-1'
 
 Learn how to configure a development environment in Azure Machine Learning that uses Azure Databricks and automated ML.
 
-Azure Databricks is ideal for running large-scale intensive machine learning workflows on the scalable Apache Spark platform in the Azure cloud. It provides a collaborative Notebook-based environment with a CPU or GPU-based compute cluster.
+Azure Databricks is ideal for running large-scale intensive machine learning workflows on the scalable Apache Spark platform in the Azure cloud. It provides a collaborative Notebook-based environment with a CPU or GPU-based compute resource.
 
 For information on other machine learning development environments, see [Set up Python development environment](how-to-configure-environment.md).
 
@@ -38,36 +38,36 @@ You can use Azure Databricks:
 + With [automated machine learning](concept-automated-ml.md) capabilities using an Azure Machine Learning SDK.
 + As a compute target from an [Azure Machine Learning pipeline](../concept-ml-pipelines.md).
 
-## Set up a Databricks cluster
+## Set up Databricks compute
 
-Create a [Databricks cluster](/azure/databricks/scenarios/quickstart-create-databricks-workspace-portal). Some settings apply only if you install the SDK for automated machine learning on Databricks.
+Create a [Databricks compute resource](/azure/databricks/compute/configure#create-a-new-all-purpose-compute-resource). Some settings apply only if you install the SDK for automated machine learning on Databricks.
 
-**It takes few minutes to create the cluster.**
+**It takes few minutes to create the compute resource.**
 
 Use these settings:
 
 | Setting |Applies to| Value |
 |----|---|---|
-| Cluster Name |always| yourclustername |
+| Compute Name |always| yourcomputename |
 | Databricks Runtime Version |always| 9.1 LTS|
 | Python version |always| 3 |
 | Worker Type <br>(determines max # of concurrent iterations) |Automated ML<br>only| Memory optimized VM preferred |
 | Workers |always| 2 or higher |
 | Enable Autoscaling |Automated ML<br>only| Uncheck |
 
-Wait until the cluster is running before proceeding further.
+Wait until the compute is running before proceeding further.
 
 ## Add the Azure Machine Learning SDK to Databricks
 
-Once the cluster is running, [create a library](https://docs.databricks.com/user-guide/libraries.html#create-a-library) to attach the appropriate Azure Machine Learning SDK package to your cluster. 
+Once the compute is running, [create a library](https://docs.databricks.com/user-guide/libraries.html#create-a-library) to attach the appropriate Azure Machine Learning SDK package to your compute. 
 
 To use automated ML, skip to [Add the Azure Machine Learning SDK with AutoML](#add-the-azure-machine-learning-sdk-with-automl-to-databricks).
 
 
 1. Right-click the current Workspace folder where you want to store the library. Select **Create** > **Library**.
 
     > [!TIP]
-    > If you have an old SDK version, deselect it from cluster's installed libraries and move to trash. Install the new SDK version and restart the cluster. If there is an issue after the restart, detach and reattach your cluster.
+    > If you have an old SDK version, deselect it from compute's installed libraries and move to trash. Install the new SDK version and restart the compute. If there is an issue after the restart, detach and reattach your compute.
 
 1. Choose the following option (no other SDK installations are supported)
 
@@ -78,22 +78,20 @@ To use automated ML, skip to [Add the Azure Machine Learning SDK with AutoML](#a
    > [!WARNING]
    > No other SDK extras can be installed. Choose only the [`databricks`] option .
 
-   * Do not select **Attach automatically to all clusters**.
-   * Select  **Attach** next to your cluster name.
+   * Do not select **Attach automatically to all computes**.
+   * Select  **Attach** next to your compute name.
 
 1. Monitor for errors until status changes to **Attached**, which may take several minutes.  If this step fails:
 
-   Try restarting your cluster by:
-   1. In the left pane, select **Clusters**.
-   1. In the table, select your cluster name.
+   Try restarting your compute by:
+   1. In the left pane, select **Compute**.
+   1. In the table, select your compute name.
    1. On the **Libraries** tab, select **Restart**.
-
-   A successful install looks like the following: 
-
-  ![Azure Machine Learning SDK for Databricks](../media/how-to-configure-environment/amlsdk-withoutautoml.jpg) 
+   
+   A successful install will show **Installed** under the status column.
 
 ## Add the Azure Machine Learning SDK with AutoML to Databricks
-If the cluster was created with Databricks Runtime 7.3 LTS (*not* ML), run the following command in the first cell of your notebook to install the Azure Machine Learning SDK.
+If the compute was created with Databricks Runtime 7.3 LTS (*not* ML), run the following command in the first cell of your notebook to install the Azure Machine Learning SDK.
 
 ```
 %pip install --upgrade --force-reinstall -r https://aka.ms/automl_linux_requirements.txt
@@ -103,23 +101,24 @@ If the cluster was created with Databricks Runtime 7.3 LTS (*not* ML), run the f
 
 In AutoML config, when using Azure Databricks add the following parameters:
 
-- ```max_concurrent_iterations``` is based on number of worker nodes in your cluster.
+- ```max_concurrent_iterations``` is based on number of worker nodes in your compute.
 - ```spark_context=sc``` is based on the default spark context.
 
 ## ML notebooks that work with Azure Databricks
 
 Try it out:
 + While many sample notebooks are available, **only [these sample notebooks](https://github.com/Azure/azureml-examples/tree/v1-archive/v1/python-sdk/tutorials/automl-with-databricks) work with Azure Databricks.**
 
-+ Import these samples directly from your workspace. See below:
-![Select Import](../media/how-to-configure-environment/azure-db-screenshot.png)
-![Import Panel](../media/how-to-configure-environment/azure-db-import.png)
++ Import these samples directly from your workspace:
+    1. In your workspace, right-click a folder and select **Import**.
+    1. Specify the URL or browse to a file containing a supported external format or a ZIP archive of notebooks exported from a Databricks workspace.
+    1. Select **Import**.
 
 + Learn how to [create a pipeline with Databricks as the training compute](how-to-create-machine-learning-pipelines.md).
 
 ## Troubleshooting
 
-* **Databricks cancel an automated machine learning run**: When you use automated machine learning capabilities on Azure Databricks, to cancel a run and start a new experiment run, restart your Azure Databricks cluster.
+* **Databricks cancel an automated machine learning run**: When you use automated machine learning capabilities on Azure Databricks, to cancel a run and start a new experiment run, restart your Azure Databricks compute.
 
 * **Databricks >10 iterations for automated machine learning**: In automated machine learning settings, if you have more than 10 iterations, set `show_output` to `False` when you submit the run.
 
@@ -147,18 +146,18 @@ Try it out:
 
 * **Import error: No module named 'pandas.core.indexes'**: If you see this error when you use automated machine learning:
 
-    1. Run this command to install two packages in your Azure Databricks cluster:
+    1. Run this command to install two packages in your Azure Databricks compute:
     
        ```bash
        scikit-learn==0.19.1
        pandas==0.22.0
        ```
     
-    1. Detach and then reattach the cluster to your notebook.
+    1. Detach and then reattach the compute to your notebook.
     
-    If these steps don't solve the issue, try restarting the cluster.
+    If these steps don't solve the issue, try restarting the compute.
 
-* **FailToSendFeather**: If you see a `FailToSendFeather` error when reading data on Azure Databricks cluster, refer to the following solutions:
+* **FailToSendFeather**: If you see a `FailToSendFeather` error when reading data on Azure Databricks compute, refer to the following solutions:
     
     * Upgrade `azureml-sdk[automl]` package to the latest version.
     * Add `azureml-dataprep` version 1.1.8 or above.