You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@@ -23,7 +23,7 @@ Containers enable you to host the Azure AI Translator API on your own infrastruc
23
23
24
24
In this article, learn how to install and run the Translator container online with Docker API. The Azure AI Translator container supports the following operations:
25
25
26
-
***Text Translation**. Translate the contextual meaning of words or phrases from supported `source` to supported `target` language in real time. For more information, *see*[**Container: translate text**](translator-container-supported-parameters.md).
26
+
***Text translation**. Translate the contextual meaning of words or phrases from supported `source` to supported `target` language in real time. For more information, *see*[**Container: translate text**](translator-container-supported-parameters.md).
27
27
28
28
***🆕 Text Transliteration**. Convert text from one language script or writing system to another language script or writing system in real time. For more information, *see*[Container: transliterate text](transliterate-text-parameters.md).
29
29
@@ -155,7 +155,7 @@ All Azure AI containers require the following input values:
155
155
156
156
The Azure AI services container images can be found in the [**Microsoft Artifact Registry**](https://mcr.microsoft.com/catalog?page=3) catalog. Azure AI Translator container resides within the azure-cognitive-services/translator repository and is named `text-translation`. The fully qualified container image name is `mcr.microsoft.com/azure-cognitive-services/translator/text-translation:latest`.
157
157
158
-
To use the latest version of the container, use the latest tag. You can view the full list of [Azure AI services Text Translation](https://mcr.microsoft.com/product/azure-cognitive-services/translator/text-translation/tags) version tags on MCR.
158
+
To use the latest version of the container, use the latest tag. You can view the full list of [Azure AI services Text translation](https://mcr.microsoft.com/product/azure-cognitive-services/translator/text-translation/tags) version tags on MCR.
159
159
160
160
## Use containers
161
161
@@ -324,7 +324,7 @@ The following example shows the formatting for the `docker run` command with pla
324
324
| `{LICENSE_MOUNT}` | The path where the license is downloaded, and mounted. | `/host/license:/path/to/license/directory` |
325
325
| `{MODEL_MOUNT_PATH}`| The path where the machine translation models are downloaded, and mounted. Your directory structure must be formatted as **/usr/local/models** | `/host/translator/models:/usr/local/models`|
326
326
| `{ENDPOINT_URI}` | The endpoint for authenticating your service request. You can find it on your resource's **Key and endpoint** page, in the Azure portal. | `https://<your-custom-subdomain>.cognitiveservices.azure.com` |
327
-
| `{API_KEY}` | The key for your Text Translation resource. You can find it on your resource's **Key and endpoint** page, in the Azure portal. |`{string}`|
327
+
| `{API_KEY}` | The key for your Text translation resource. You can find it on your resource's **Key and endpoint** page, in the Azure portal. |`{string}`|
328
328
| `{LANGUAGES_LIST}` | List of language codes separated by commas. It's mandatory to have English (en) language as part of the list.| `en`, `fr`, `it`, `zu`, `uk` |
329
329
| `{CONTAINER_LICENSE_DIRECTORY}` | Location of the license folder on the container's local filesystem. | `/path/to/license/directory` |
330
330
@@ -446,10 +446,10 @@ The following table lists the required supporting containers for your text and d
|• Text translation<br>• Document Translation|`from` specified. |Office documents| None|
450
-
|• Text translation<br>• Document Translation|`from` not specified. Requires automatic language detection to determine the source language. |Office documents |✔️ [**Text analytics:language**](../../language-service/language-detection/how-to/use-containers.md) container|
451
-
|• Text translation<br>• Document Translation|`from` specified. |Scanned PDF documents| ✔️ [**Vision:read**](../../computer-vision/computer-vision-how-to-install-containers.md) container|
452
-
|• Text translation<br>• Document Translation|`from` not specified requiring automatic language detection to determine source language.|Scanned PDF documents| ✔️ [**Text analytics:language**](../../language-service/language-detection/how-to/use-containers.md) container<br><br>✔️ [**Vision:read**](../../computer-vision/computer-vision-how-to-install-containers.md) container|
449
+
|• Text translation<br>• Document translation|`from` specified. |Office documents| None|
450
+
|• Text translation<br>• Document translation|`from` not specified. Requires automatic language detection to determine the source language. |Office documents |✔️ [**Text analytics:language**](../../language-service/language-detection/how-to/use-containers.md) container|
451
+
|• Text translation<br>• Document translation|`from` specified. |Scanned PDF documents| ✔️ [**Vision:read**](../../computer-vision/computer-vision-how-to-install-containers.md) container|
452
+
|• Text translation<br>• Document translation|`from` not specified requiring automatic language detection to determine source language.|Scanned PDF documents| ✔️ [**Text analytics:language**](../../language-service/language-detection/how-to/use-containers.md) container<br><br>✔️ [**Vision:read**](../../computer-vision/computer-vision-how-to-install-containers.md) container|
453
453
454
454
## Operate supporting containers with `docker compose`
455
455
@@ -531,7 +531,7 @@ The Azure AI services container images can be found in the [**Microsoft Artifact
531
531
532
532
|Container|Image location|Notes|
533
533
|--------|-------------|---------------|
534
-
|Translator: Text and document translation| `mcr.microsoft.com/azure-cognitive-services/translator/text-translation:latest`| You can view the full list of [Azure AI services Text Translation](https://mcr.microsoft.com/product/azure-cognitive-services/translator/text-translation/tags) version tags on MCR.|
534
+
|Translator: Text and document translation| `mcr.microsoft.com/azure-cognitive-services/translator/text-translation:latest`| You can view the full list of [Azure AI services Text translation](https://mcr.microsoft.com/product/azure-cognitive-services/translator/text-translation/tags) version tags on MCR.|
535
535
|Text analytics: language|`mcr.microsoft.com/azure-cognitive-services/textanalytics/language:latest` |You can view the full list of [Azure AI services Text Analytics Language](https://mcr.microsoft.com/product/azure-cognitive-services/textanalytics/language/tags) version tags on MCR.|
536
536
|Vision: read|`mcr.microsoft.com/azure-cognitive-services/vision/read:latest`|You can view the full list of [Azure AI services Computer Vision Read `OCR`](https://mcr.microsoft.com/product/azure-cognitive-services/vision/read/tags) version tags on MCR.|
|`-X` or `--request``POST`|The -X flag specifies the request method to access the API.|*Required*|
39
-
|`{endpoint}`|The URL for your Document Translation resource endpoint|*Required*|
39
+
|`{endpoint}`|The URL for your Document translation resource endpoint|*Required*|
40
40
|`targetLanguage`|Specifies the language of the output document. The target language must be one of the supported languages included in the translation scope.|*Required*|
41
41
|`sourceLanguage`|Specifies the language of the input document. If the `sourceLanguage` parameter isn't specified, automatic language detection is applied to determine the source language. |*Optional*|
42
-
|`-H` or `--header``"Ocp-Apim-Subscription-Key:{KEY}`| Request header that specifies the Document Translation resource key authorizing access to the API.|*Required*|
42
+
|`-H` or `--header``"Ocp-Apim-Subscription-Key:{KEY}`| Request header that specifies the Document translation resource key authorizing access to the API.|*Required*|
43
43
|`-F` or `--form`|The filepath to the document that you want to include with your request. Only one source document is allowed.|*Required*|
44
44
|•`document=`<br> •`type={contentType}/fileExtension`|• Path to the file location for your source document.</br> • Content type and file extension.</br></br> Ex: **"document=@C:\Test\test-file.md;type=text/markdown"**|*Required*|
45
45
|`-o` or `--output`|The filepath to the response results.|*Required*|
@@ -54,7 +54,7 @@ Use synchronous translation processing to send a document as part of the HTTP re
54
54
>
55
55
> * Each sample runs on the `localhost` that you specified with the `docker compose up` command.
56
56
> * While your container is running, `localhost` points to the container itself.
57
-
> * You don't have to use `localhost:5000`. You can use any port that is not already in use in your host environment.
57
+
> * You don't have to use `localhost:5000`. You can use any port that isn't already in use in your host environment.
|• Text translation<br>• Document Translation|`from` specified. |Office documents| None|
402
-
|• Text translation<br>• Document Translation|`from` not specified. Requires automatic language detection to determine the source language. |Office documents |✔️ [**Text analytics:language**](../../language-service/language-detection/how-to/use-containers.md) container|
403
-
|• Text translation<br>• Document Translation|`from` specified. |Scanned PDF documents| ✔️ [**Vision:read**](../../computer-vision/computer-vision-how-to-install-containers.md) container|
404
-
|• Text translation<br>• Document Translation|`from` not specified requiring automatic language detection to determine source language.|Scanned PDF documents| ✔️ [**Text analytics:language**](../../language-service/language-detection/how-to/use-containers.md) container<br><br>✔️ [**Vision:read**](../../computer-vision/computer-vision-how-to-install-containers.md) container|
401
+
|• Text translation<br>• Document translation|`from` specified. |Office documents| None|
402
+
|• Text translation<br>• Document translation|`from` not specified. Requires automatic language detection to determine the source language. |Office documents |✔️ [**Text analytics:language**](../../language-service/language-detection/how-to/use-containers.md) container|
403
+
|• Text translation<br>• Document translation|`from` specified. |Scanned PDF documents| ✔️ [**Vision:read**](../../computer-vision/computer-vision-how-to-install-containers.md) container|
404
+
|• Text translation<br>• Document translation|`from` not specified requiring automatic language detection to determine source language.|Scanned PDF documents| ✔️ [**Text analytics:language**](../../language-service/language-detection/how-to/use-containers.md) container<br><br>✔️ [**Vision:read**](../../computer-vision/computer-vision-how-to-install-containers.md) container|
405
405
406
406
##### Container images and tags
407
407
408
408
The Azure AI services container images can be found in the [**Microsoft Artifact Registry**](https://mcr.microsoft.com/catalog?page=3) catalog. The following table lists the fully qualified image location for text and document translation:
409
409
410
410
|Container|Image location|Notes|
411
411
|--------|-------------|---------------|
412
-
|Translator: Text translation|`mcr.microsoft.com/azure-cognitive-services/translator/text-translation:latest`| You can view the full list of [Azure AI services Text Translation](https://mcr.microsoft.com/product/azure-cognitive-services/translator/text-translation/tags) version tags on MCR.|
412
+
|Translator: Text translation|`mcr.microsoft.com/azure-cognitive-services/translator/text-translation:latest`| You can view the full list of [Azure AI services Text translation](https://mcr.microsoft.com/product/azure-cognitive-services/translator/text-translation/tags) version tags on MCR.|
|Text analytics: language|`mcr.microsoft.com/azure-cognitive-services/textanalytics/language:latest`|You can view the full list of [Azure AI services Text Analytics Language](https://mcr.microsoft.com/product/azure-cognitive-services/textanalytics/language/tags) version tags on MCR.|
415
415
|Vision: read|`mcr.microsoft.com/azure-cognitive-services/vision/read:latest`|You can view the full list of [Azure AI services Computer Vision Read `OCR`](https://mcr.microsoft.com/product/azure-cognitive-services/vision/read/tags) version tags on MCR.|
Copy file name to clipboardExpand all lines: articles/ai-services/translator/custom-translator/beginners-guide.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -6,21 +6,21 @@ author: laujan
6
6
manager: nitinme
7
7
ms.service: azure-ai-translator
8
8
ms.author: lajanuar
9
-
ms.date: 01/27/2025
9
+
ms.date: 04/14/2025
10
10
ms.topic: overview
11
11
---
12
12
13
13
# Azure AI Custom Translator for beginners
14
14
15
-
[Azure AI Custom Translator](overview.md) enables you to a build translation system that reflects your business, industry, and domain-specific terminology and style. Training and deploying a custom system is easy and doesn't require any programming skills. The customized translation system seamlessly integrates into your existing applications, workflows, and websites and is available on Azure through the same cloud-based [Microsoft Text Translation API](../text-translation/reference/v3/translate.md?tabs=curl) service that powers billions of translations every day.
15
+
[Azure AI Custom Translator](overview.md) enables you to a build translation system that reflects your business, industry, and domain-specific terminology and style. Training and deploying a custom system is easy and doesn't require any programming skills. The customized translation system seamlessly integrates into your existing applications, workflows, and websites and is available on Azure through the same cloud-based [Microsoft Text translation API](../text-translation/reference/v3/translate.md?tabs=curl) service that powers billions of translations every day.
16
16
17
17
The platform enables users to build and publish custom translation systems to and from English. The Custom Translator supports more than 60 languages that map directly to the languages available for Neural machine translation (NMT). For a complete list, *see*[Translator language support](../language-support.md).
18
18
19
19
## Is a custom translation model the right choice for me?
20
20
21
21
A well-trained custom translation model provides more accurate domain-specific translations because it relies on previously translated in-domain documents to learn preferred translations. Translator uses these terms and phrases in context to produce fluent translations in the target language while respecting context-dependent grammar.
22
22
23
-
Training a full custom translation model requires a substantial amount of data. If you don't have at least 10,000 sentences of previously trained documents, you can't train a full-language translation model. However, you can either train a dictionary-only model or use the high-quality, out-of-the-box translations available with the Text Translation API.
23
+
Training a full custom translation model requires a substantial amount of data. If you don't have at least 10,000 sentences of previously trained documents, you can't train a full-language translation model. However, you can either train a dictionary-only model or use the high-quality, out-of-the-box translations available with the Text translation API.
24
24
25
25
:::image type="content" source="media/how-to/for-beginners.png" alt-text="Screenshot illustrating the difference between custom and general models.":::
Copy file name to clipboardExpand all lines: articles/ai-services/translator/custom-translator/concepts/sentence-alignment.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -5,7 +5,7 @@ description: During the training execution, sentences present in parallel docume
5
5
author: laujan
6
6
manager: nitinme
7
7
ms.service: azure-ai-translator
8
-
ms.date: 01/28/2025
8
+
ms.date: 04/14/2025
9
9
ms.author: lajanuar
10
10
ms.topic: conceptual
11
11
ms.custom: cogserv-non-critical-translator
@@ -50,7 +50,7 @@ For a training to succeed, the following table shows the minimum number of sente
50
50
> - Training doesn't start and fails if the 10,000 minimum sentence count for training isn't met.
51
51
> - Tuning and testing are optional. If you don't provide them, the system removes an appropriate percentage from training to use for validation and testing.
52
52
> - You can train a model using dictionary data only. For more information, *see*[What is a dictionary](dictionaries.md).
53
-
> - The Document Translation feature is recommended for training with dictionaries that contain more than 250,000 sentences. For more information, *see*[Document Translation](../../document-translation/overview.md).
53
+
> - The Document translation feature is recommended for training with dictionaries that contain more than 250,000 sentences. For more information, *see*[Document translation](../../document-translation/overview.md).
54
54
> - Free (F0) subscription training has a maximum limit of 2,000,000 characters.
Copy file name to clipboardExpand all lines: articles/ai-services/translator/custom-translator/how-to/translate-with-custom-model.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -5,7 +5,7 @@ description: How to make translation requests using custom models published with
5
5
author: laujan
6
6
manager: nitinme
7
7
ms.service: azure-ai-translator
8
-
ms.date: 01/28/2025
8
+
ms.date: 04/14/2025
9
9
ms.author: lajanuar
10
10
ms.topic: how-to
11
11
---
@@ -15,7 +15,7 @@ After you publish your custom model, you can access it with the Azure AI Transla
15
15
16
16
## How to translate
17
17
18
-
1. Use the `Category ID` when making a custom translation request via Microsoft Translator [Text API V3](../../text-translation/reference/v3/translate.md?tabs=curl). The `Category ID` is created by concatenating the WorkspaceID, project label, and category code. Use the `CategoryID` with the Text Translation API to get custom translations.
18
+
1. Use the `Category ID` when making a custom translation request via Microsoft Translator [Text API V3](../../text-translation/reference/v3/translate.md?tabs=curl). The `Category ID` is created by concatenating the WorkspaceID, project label, and category code. Use the `CategoryID` with the Text translation API to get custom translations.
0 commit comments