Merge pull request #196800 from sanjeev3/main

Computer Vision Read 3.2 Model GA release

Author: laurabren

articles/applied-ai-services/form-recognizer/language-support.md

@@ -13,7 +13,7 @@ ms.author: lajanuar
 
 # Language support for Form Recognizer
 
- This table lists the written languages supported by each Form Recognizer service.
+This article covers the supported languages for text and field **extraction (by feature)** and **[detection (Read only)](#detected-languages-read-api)**. Both groups are mutually exclusive.
 
 <!-- markdownlint-disable MD001 -->
 <!-- markdownlint-disable MD024 -->
@@ -29,7 +29,7 @@ The following lists include the currently GA languages in for the v2.1 version a
 
 To use the preview languages, refer to the [v3.0 REST API migration guide](/rest/api/media/#changes-to-the-rest-api-endpoints) to understand the differences from the v2.1 GA API and explore the [v3.0 preview SDK quickstarts](quickstarts/try-v3-python-sdk.md).
 
-### Handwritten languages (preview and GA)
+### Handwritten text (preview and GA)
 
 The following table lists the supported languages for extracting handwritten texts.
 
@@ -41,7 +41,7 @@ The following table lists the supported languages for extracting handwritten tex
 |German (preview) |`de`|Spanish (preview) |`es`|
 |Italian (preview) |`it`|
 
-### Print languages (preview)
+### Print text (preview)
 
 This section lists the supported languages for extracting printed texts in the latest preview.
 
@@ -94,7 +94,7 @@ This section lists the supported languages for extracting printed texts in the l
 |Kurukh (Devanagari) | `kru`|Welsh | `cy`
 |Kyrgyz (Cyrillic)  | `ky`
 
-### Print languages (GA)
+### Print text (GA)
 
 This section lists the supported languages for extracting printed texts in the latest GA version.
 
@@ -178,14 +178,14 @@ Language| Locale code |
 
 ## Detected languages: Read API
 
-The [Read API](concept-read.md) supports language detection for the following languages:
+The [Read API](concept-read.md) supports detecting the following languages in your documents. This list may include languages not currently supported for text extraction.
 
 > [!NOTE]
 > **Language detection**
 >
-> Form Recognizer read model can _detect_ a wide range of languages, variants, dialects, and some regional/cultural languages and return a language code.
->
-> This section lists the languages that can be detected using the Read API. To determine if text can also be _extracted_ for a given language, see [handwritten](#handwritten-languages-preview-and-ga), [print preview](#print-languages-preview), and [print GA](#print-languages-ga) language extraction lists (above).
+> Form Recognizer read model can _detect_ possible presence of languages and returns language codes for detected languages. To determine if text can also be 
+> extracted for a given language, see previous sections.
+
 
 | Language            | Code |
 |---------------------|---------------|

articles/cognitive-services/Computer-vision/Vision-API-How-to-Topics/call-read-api.md

@@ -23,17 +23,18 @@ This guide assumes you have already <a href="https://portal.azure.com/#create/Mi
 
 ### Specify the OCR model
 
-By default, the service will use the latest GA model to extract text. Starting with Read 3.2, a `model-version` parameter allows choosing between the GA and preview models for a given API version. The model you specify will be used to extract text with the Read operation.
+By default, the service will use the latest generally available (GA) model to extract text. Starting with Read 3.2, a `model-version` parameter allows choosing between the GA and preview models for a given API version. The model you specify will be used to extract text with the Read operation.
 
 When using the Read operation, use the following values for the optional `model-version` parameter.
 
 |Value| Model used |
 |:-----|:----|
-| 2022-01-30-preview | Latest preview model with additonal Hindi, Arabic and other Devanagari and Arabic script languages and enhancements to the previous preview.
-| 2021-09-30-preview | Previous preview model with addiitonal Russian and Cyrillic languages and enhancements to the GA previous model.
-| 2021-04-12 | most recent GA model |
-| Not provided | most recent GA model |
-| latest | most recent GA model|
+| Not provided | Latest GA model |
+| latest | Latest GA model|
+| [2022-04-30](../whats-new.md#may-2022) | Latest GA model. 164 languages for print text and 9 languages for handwritten text along with several enhancements on quality and performance |
+| [2022-01-30-preview](../whats-new.md#february-2022) | Preview model adds print text support for Hindi, Arabic and related languages. For handwriitten text, adds support for Japanese and Korean. |
+| [2021-09-30-preview](../whats-new.md#september-2021) | Preview model adds print text support for Russian and other Cyrillic languages, For handwriitten text,  adds support for Chinese Simplified, French, German, Italian, Portuguese, and Spanish. |
+| 2021-04-12 | 2021 GA model |
 
 ### Input language
 

articles/cognitive-services/Computer-vision/computer-vision-how-to-install-containers.md

@@ -23,14 +23,14 @@ Containers enable you to run the Computer Vision APIs in your own environment. C
 The *Read* OCR container allows you to extract printed and handwritten text from images and documents with support for JPEG, PNG, BMP, PDF, and TIFF file formats. For more information, see the [Read API how-to guide](Vision-API-How-to-Topics/call-read-api.md).
 
 ## What's new
-For existing users of the Read containers, a new `3.2-model-2021-09-30-preview` version of the Read container is available with support for 122 languages and general performance and AI enhancements. Please follow the [download instructions](#docker-pull-for-the-read-ocr-container) to get started.
+The `3.2-model-2022-04-30` GA version of the Read container is available with support for [164 languages and other enhancements](./whats-new.md#may-2022). If you are an existing customer, please follow the [download instructions](#docker-pull-for-the-read-ocr-container) to get started.
 
 ## Read 3.2 container
 
-The Read 3.2 OCR container provides:
+The Read 3.2 OCR container latest GA model provides:
 * New models for enhanced accuracy.
 * Support for multiple languages within the same document.
-* Support for a total of 73 languages. See the full list of [OCR-supported languages](./language-support.md#optical-character-recognition-ocr).
+* Support for a total of 164 languages. See the full list of [OCR-supported languages](./language-support.md#optical-character-recognition-ocr).
 * A single operation for both documents and images.
 * Support for larger documents and images.
 * Confidence scores.
@@ -84,29 +84,22 @@ grep -q avx2 /proc/cpuinfo && echo AVX2 supported || echo No AVX2 support detect
 
 Container images for Read are available.
 
-| Container | Container Registry / Repository / Image Name |
-|-----------|------------|
-| Read 3.2 model-2021-09-30-preview | `mcr.microsoft.com/azure-cognitive-services/vision/read:3.2-model-2021-09-30-preview` |
-| Read 3.2 | `mcr.microsoft.com/azure-cognitive-services/vision/read:3.2` |
-| Read 2.0-preview | `mcr.microsoft.com/azure-cognitive-services/vision/read:2.0-preview` |
+| Container | Container Registry / Repository / Image Name | Tags |
+|-----------|------------|-----------------------------------------|
+| Read 3.2 GA | `mcr.microsoft.com/azure-cognitive-services/vision/read:3.2-model-2022-04-30` | 	latest, 3.2, 3.2-model-2022-04-30 |
+| Read 2.0-preview | `mcr.microsoft.com/azure-cognitive-services/vision/read:2.0-preview` |2.0.019300020-amd64-preview |
 
 Use the [`docker pull`](https://docs.docker.com/engine/reference/commandline/pull/) command to download a container image.
 
 ### Docker pull for the Read OCR container
 
-For the latest preview:
+# [Version 3.2 GA](#tab/version-3-2)
 
 ```bash
-docker pull mcr.microsoft.com/azure-cognitive-services/vision/read:3.2-model-2021-09-30-preview
+docker pull mcr.microsoft.com/azure-cognitive-services/vision/read:3.2-model-2022-04-30
 ```
 
-# [Version 3.2](#tab/version-3-2)
-
-```bash
-docker pull mcr.microsoft.com/azure-cognitive-services/vision/read:3.2
-```
-
-# [Version 2.0-preview](#tab/version-2)
+# [Version 2.0 preview](#tab/version-2)
 
 ```bash
 docker pull mcr.microsoft.com/azure-cognitive-services/vision/read:2.0-preview
@@ -129,37 +122,31 @@ Use the [docker run](https://docs.docker.com/engine/reference/commandline/run/)
 
 [Examples](computer-vision-resource-container-config.md#example-docker-run-commands) of the `docker run` command are available.
 
-For the latest preview, replace 3.2 path with:
-
-```
-mcr.microsoft.com/azure-cognitive-services/vision/read:3.2-model-2021-09-30-preview
-```
-
 # [Version 3.2](#tab/version-3-2)
 
 ```bash
-docker run --rm -it -p 5000:5000 --memory 18g --cpus 8 \
-mcr.microsoft.com/azure-cognitive-services/vision/read:3.2 \
+docker run --rm -it -p 5000:5000 --memory 16g --cpus 8 \
+mcr.microsoft.com/azure-cognitive-services/vision/read:3.2-model-2022-04-30 \
 Eula=accept \
 Billing={ENDPOINT_URI} \
 ApiKey={API_KEY}
 ```
 
 This command:
 
-* Runs the Read OCR container from the container image.
-* Allocates 8 CPU core and 18 gigabytes (GB) of memory.
+* Runs the Read OCR latest GA container from the container image.
+* Allocates 8 CPU core and 16 gigabytes (GB) of memory.
 * Exposes TCP port 5000 and allocates a pseudo-TTY for the container.
 * Automatically removes the container after it exits. The container image is still available on the host computer.
 
 You can alternatively run the container using environment variables:
 
 ```bash
-docker run --rm -it -p 5000:5000 --memory 18g --cpus 8 \
+docker run --rm -it -p 5000:5000 --memory 16g --cpus 8 \
 --env Eula=accept \
 --env Billing={ENDPOINT_URI} \
 --env ApiKey={API_KEY} \
-mcr.microsoft.com/azure-cognitive-services/vision/read:3.2
+mcr.microsoft.com/azure-cognitive-services/vision/read:3.2-model-2022-04-30
 ```
 
 # [Version 2.0-preview](#tab/version-2)
@@ -216,18 +203,12 @@ To find your connection string:
 
 The container provides REST-based query prediction endpoint APIs. 
 
-For the latest preview:
-
-Use the same Swagger path as 3.2 but a different port if you have already deployed 3.2 at the 5000 port.
-
 Use the host, `http://localhost:5000`, for container APIs. You can view the Swagger path at: `http://localhost:5000/swagger/`.
 
 ---
 
 ### Asynchronous Read
 
-For the latest preview, everything is the same as 3.2 except for the additional `"modelVersion": "2021-09-30-preview"`.
-
 # [Version 3.2](#tab/version-3-2)
 
 You can use the `POST /vision/v3.2/read/analyze` and `GET /vision/v3.2/read/operations/{operationId}` operations in concert to asynchronously read an image, similar to how the Computer Vision service uses those corresponding REST operations. The asynchronous POST method will return an `operationId` that is used as the identifer to the HTTP GET request.

articles/cognitive-services/Computer-vision/computer-vision-resource-container-config.md

@@ -126,8 +126,8 @@ The following Docker examples are for the Read OCR container.
 ### Basic example
 
 ```bash
-docker run --rm -it -p 5000:5000 --memory 18g --cpus 8 \
-mcr.microsoft.com/azure-cognitive-services/vision/read:3.2 \
+docker run --rm -it -p 5000:5000 --memory 16g --cpus 8 \
+mcr.microsoft.com/azure-cognitive-services/vision/read:3.2-model-2022-04-30 \
 Eula=accept \
 Billing={ENDPOINT_URI} \
 ApiKey={API_KEY}
@@ -137,8 +137,8 @@ ApiKey={API_KEY}
 ### Logging example 
 
 ```bash
-docker run --rm -it -p 5000:5000 --memory 18g --cpus 8 \
-mcr.microsoft.com/azure-cognitive-services/vision/read:3.2 \
+docker run --rm -it -p 5000:5000 --memory 16g --cpus 8 \
+mcr.microsoft.com/azure-cognitive-services/vision/read:3.2-model-2022-04-30 \
 Eula=accept \
 Billing={ENDPOINT_URI} \
 ApiKey={API_KEY}
@@ -150,7 +150,7 @@ Logging:Console:LogLevel:Default=Information
 ### Basic example
 
 ```bash
-docker run --rm -it -p 5000:5000 --memory 18g --cpus 8 \
+docker run --rm -it -p 5000:5000 --memory 16g --cpus 8 \
 mcr.microsoft.com/azure-cognitive-services/vision/read:2.0-preview \
 Eula=accept \
 Billing={ENDPOINT_URI} \
@@ -161,7 +161,7 @@ ApiKey={API_KEY}
 ### Logging example 
 
 ```bash
-docker run --rm -it -p 5000:5000 --memory 18g --cpus 8 \
+docker run --rm -it -p 5000:5000 --memory 16g --cpus 8 \
 mcr.microsoft.com/azure-cognitive-services/vision/read:2.0-preview \
 Eula=accept \
 Billing={ENDPOINT_URI} \

articles/cognitive-services/Computer-vision/includes/container-requirements-and-recommendations.md

@@ -17,8 +17,9 @@ The following table describes the minimum and recommended allocation of resource
 
 | Container | Minimum | Recommended |
 |-----------|---------|-------------|
-| Read 2.0-preview | 1 core, 8-GB memory |    8 cores, 16-GB memory |
-| Read 3.2 | 4 cores, 16-GB memory | 8 cores, 24-GB memory |
+| Read 3.2 2022-04-30 | 4 cores, 8-GB memory  | 8 cores, 16-GB memory |
+| Read 3.2 2021-04-12 | 4 cores, 16-GB memory | 8 cores, 24-GB memory |
+| Read 2.0-preview | 1 core, 8-GB memory | 8 cores, 16-GB memory |
 
 * Each core must be at least 2.6 gigahertz (GHz) or faster.
 

articles/cognitive-services/Computer-vision/includes/curl-quickstart.md

@@ -53,11 +53,9 @@ curl -v -X POST "https://westcentralus.api.cognitive.microsoft.com/vision/v3.2/r
 The response will include an `Operation-Location` header, whose value is a unique URL. You use this URL to query the results of the Read operation. The URL expires in 48 hours.
 
 ### Optionally, specify the model version
-As an optional step, see [How to specify the model version](../Vision-API-How-to-Topics/call-read-api.md#determine-how-to-process-the-data-optional) for the model version parameter values you can use. The most recent model includes any enhancements to the previous GA and preview models.
-
-For example, to use the model-version = `2022-01-30-preview` parameter, use the following command:
+As an optional step, see [How to specify the model version](../Vision-API-How-to-Topics/call-read-api.md#determine-how-to-process-the-data-optional). For example, to explicitly specify the latest GA model, use `model-version=2022-04-30` as the parameter. Skipping the parameter or using `model-version=latest` automatically uses the most recent GA model.
 ```bash
-curl -v -X POST "https://westcentralus.api.cognitive.microsoft.com/vision/v3.2/read/analyze?model-version=2022-01-30-preview" -H "Content-Type: application/json" -H "Ocp-Apim-Subscription-Key: <subscription key>" --data-ascii "{\"url\":\"https://upload.wikimedia.org/wikipedia/commons/thumb/a/af/Atomist_quote_from_Democritus.png/338px-Atomist_quote_from_Democritus.png\"}"
+curl -v -X POST "https://westcentralus.api.cognitive.microsoft.com/vision/v3.2/read/analyze?model-version=2022-04-30" -H "Content-Type: application/json" -H "Ocp-Apim-Subscription-Key: <subscription key>" --data-ascii "{\"url\":\"https://upload.wikimedia.org/wikipedia/commons/thumb/a/af/Atomist_quote_from_Democritus.png/338px-Atomist_quote_from_Democritus.png\"}"
 ```
 
 ### Get Read results

articles/cognitive-services/Computer-vision/includes/quickstarts-sdk/csharp-sdk.md

@@ -88,11 +88,11 @@ Use the OCR client library to read printed and handwritten text from a remote im
    > [!IMPORTANT]
    > Remember to remove the subscription key from your code when you're done, and never post it publicly. For production, consider using a secure way of storing and accessing your credentials. For example, [Azure key vault](../../../../key-vault/general/overview.md).
 
-1. As an optional step, see [How to specify the model version](../../Vision-API-How-to-Topics/call-read-api.md#determine-how-to-process-the-data-optional) for the model version parameter values you can use. The most recent model includes any enhancements to the previous GA and preview models. For example, to use the model-version=`2022-01-30-preview` parameter, edit the ReadAsync call as shown:
+1. As an optional step, see [How to specify the model version](../../Vision-API-How-to-Topics/call-read-api.md#determine-how-to-process-the-data-optional). For example, to explicitly specify the latest GA model, edit the `ReadAsync` call as shown. Skipping the parameter or using `"latest"` automatically uses the most recent GA model.
 
    ```csharp
      // Read text from URL with a specific model version
-     var textHeaders = await client.ReadAsync(urlFile,null,null,"2022-01-30-preview");
+     var textHeaders = await client.ReadAsync(urlFile,null,null,"2022-04-30");
    ```
 
 1. Run the application.

articles/cognitive-services/Computer-vision/includes/quickstarts-sdk/node-sdk.md

@@ -78,11 +78,10 @@ Use the Optical character recognition client library to read printed and handwri
    > [!IMPORTANT]
    > Remember to remove the subscription key from your code when you're done, and never post it publicly. For production, consider using a secure way of storing and accessing your credentials. For example, [Azure key vault](../../../../key-vault/general/overview.md).
 
-
-1. As an optional step, see [How to specify the model version](../../Vision-API-How-to-Topics/call-read-api.md#determine-how-to-process-the-data-optional) for the model version parameter values you can use. The most recent model includes any enhancements to the previous GA and preview models. For example, to use the model version `2022-01-30-preview`, edit the `read` statement as shown:
+1. As an optional step, see [How to specify the model version](../../Vision-API-How-to-Topics/call-read-api.md#determine-how-to-process-the-data-optional). For example, to explicitly specify the latest GA model, edit the `read` statement as shown. Skipping the parameter or using `"latest"` automatically uses the most recent GA model.
 
    ```JS
-     let result = await client.read(url,{modelVersion:"2022-01-30-preview"});
+     let result = await client.read(url,{modelVersion:"2022-04-30"});
    ```
 
 1. Run the application with the `node` command on your quickstart file.

articles/cognitive-services/Computer-vision/includes/quickstarts-sdk/python-sdk.md

@@ -63,11 +63,11 @@ Use the OCR client library to read printed and handwritten text from a remote im
    > [!IMPORTANT]
    > Remember to remove the subscription key from your code when you're done, and never post it publicly. For production, consider using a secure way of storing and accessing your credentials. For example, [Azure key vault](../../../../key-vault/general/overview.md).
 
-1. As an optional step, see [How to specify the model version](../../Vision-API-How-to-Topics/call-read-api.md#determine-how-to-process-the-data-optional) for the model version parameter values you can use. The most recent model includes any enhancements to the previous GA and preview models. For example, to use the model version `2022-01-30-preview`, edit the `read` statement as shown:
+1. As an optional step, see [How to specify the model version](../../Vision-API-How-to-Topics/call-read-api.md#determine-how-to-process-the-data-optional). For example, to explicitly specify the latest GA model, edit the `read` statement as shown. Skipping the parameter or using `"latest"` automatically uses the most recent GA model.
 
    ```python
       # Call API with URL and raw response (allows you to get the operation location)
-      read_response = computervision_client.read(read_image_url,  raw=True, model_version="2022-01-30-preview")
+      read_response = computervision_client.read(read_image_url,  raw=True, model_version="2022-04-30")
    ```
 
 1. Run the application with the `python` command on your quickstart file.