Merge pull request #4825 from laujan/patch-3

Update translate-api.md

Author: prmerger-automator[bot]

articles/ai-services/translator/text-translation/reference/v4/translate-api.md

@@ -56,19 +56,19 @@ Request parameters passed with the request are as follows:
 | **language** | string | False | Specifies the language code for the `source` text. If not specified, the system autodetects the language of the source text. Accepted values are list of language code supported by the specified model. |
 | **script** | string | False | Specifies the script of the source text. |
 
-#### Targets array (user-specificed values for the translaated text)
+#### Targets array (user-specified values for translated text)
 
 | Parameter | Type | Required? | Description |
 | --- | --- | --- | --- |
 | **targets.language** | string | True |The language code for the translated (`target`) text *specified in the `targets` array*. Accepted values are [supported language](../../../language-support.md) codes for the translation operation.|
 | **targets.script** | string | False | Specify the script of the translated text. |
-|**targets.deploymentName** | string | False | Default is `general`, which uses `NMT` system. `your-model-name-gpt-4o-mini` is an example deployment name for the GPT-4o-mini model. `gpt-4o` uses GPT-4o model.<br> `<custom model id>` uses the custom `NMT` model tuned by customer.<br>  |
-| **targets.allowFallback** | string | False | If the desired model does not support a particular pair of source and target languages, an alternative approach may be employed. In such cases, the service may default to utilizing a general system as a substitute. This action ensures that translations can still be provided even when the preferred model is unavailable. Default is `true`. If `false` system returns an error if language pair isn't supported. |
+|**targets.deploymentName** | string | False | Default is `general`, which uses `NMT` system. `your-model-name-gpt-4o-mini` is an example deployment name for the GPT-4o-mini model. `gpt-4o` uses GPT-4o model.<br> `<categoryID>` uses the custom `NMT` model tuned by customer.<br>  |
+| **targets.allowFallback** | string | False | If the desired model doesn't support a particular pair of source and target languages, an alternative approach may be employed. In such cases, the service may default to utilizing a general system as a substitute. This action ensures that translations can still be provided even when the preferred model is unavailable. Default is `true`. If `false` system returns an error if language pair isn't supported. |
 | **targets.tone** | string | False | Desired tone of target translation. Accepted values are `formal`, `informal`, or `neutral`. |
 | **targets.gender** (For more information, *see* [Gender-specific translations](#gender-specific-translations))| string | False | Desired gender of target translation. Accepted values are `male`, `female`, or `neutral`.|
-| **targets.adaptiveDatasetId** | string | False | Reference dataset ID having sentence pair to generate adaptive customized translation |
-| **targets.referenceTextPairs** | string | False | Reference text pairs to generate adaptive customized translation |
-| **targets.referenceTextPairs.source** | string | False | Source text in reference text pair. If provided, `adaptiveDatasetId` is ignored |
+| **targets.adaptiveDatasetId** | string | False | Reference dataset ID having sentence pair to generate adaptive customized translation. The maximum number of reference text pairs to generate adaptive customized translation is five (5).|
+| **targets.referenceTextPairs** | string | False | Reference text pairs to generate adaptive customized translation. |
+| **targets.referenceTextPairs.source** | string | False | Source text in reference text pair. If provided, `adaptiveDatasetId` is ignored. |
 | **targets.referenceTextPairs.target** | string | False | Target text in reference text pair. |
 | **targets.profanityAction** | string | False | Specifies how profanities should be treated in translations. Accepted values are: `NoAction` (default), `Marked`, or `Deleted`. |
 | **targets.profanityMarker** | string | False | Specifies how profanities should be marked in translations. Accepted values are `Asterisk` (default) or Tag. |
@@ -481,7 +481,7 @@ Adaptive custom translation deploys on Translator service infrastructure. Charge
     "targets": [
       {
         "language": "es",
-        "deploymentName": "CT-model-en-es-hr-020"
+        "deploymentName": "f16e83fb-3af8-4d45-9290-10a516f9dfc4-GENERAL"
       }
     ]
   }
@@ -517,4 +517,4 @@ Adaptive custom translation deploys on Translator service infrastructure. Charge
 ## Next steps
 
 > [!div class="nextstepaction"]
-> [View 2025-05-01-preview migration guide](../../how-to/migrate-to-v4.md)
+> [View 2025-05-01-preview migration guide](../../how-to/migrate-to-v4.md)