Add v3.2 for Speech to text (3.2p2 as base) (Azure#28664)

* Add v3.2 for Speech to text (3.2p2 as base) * Update swagger with new changes and updated version number * Update readme.md with new version * Added evaluation token errors * Revert ttl changes for transcriptions * Finalized api changes for GA * Try fix avocado error
markcowl · Jun 7, 2024 · 86de0c6 · 86de0c6
1 parent 86d08cb
commit 86de0c6
Show file tree

Hide file tree

Showing 93 changed files with 10,989 additions and 8 deletions.
diff --git a/specification/cognitiveservices/data-plane/Speech/SpeechToText/readme.md b/specification/cognitiveservices/data-plane/Speech/SpeechToText/readme.md
@@ -4,17 +4,17 @@
 
 Configuration for generating SpeechToText SDK.
 
-The current release for the SpeechToText is `release_3_1`.
+The current release for the SpeechToText is `release_3_2`.
 
 ``` yaml
-tag: release_3_1
+tag: release_3_2
 add-credentials: true
 openapi-type: data-plane
 ```
 
 # Releases
 
-## SpeechToText 2.0
+## Tag: release_2_0
 These settings apply only when `--tag=release_2_0` is specified on the command line.
 
 ``` yaml $(tag) == 'release_2_0'
@@ -34,7 +34,7 @@ directive:
 
 ---
 
-## SpeechToText 3.0
+## Tag: release_3_0
 These settings apply only when `--tag=release_3_0` is specified on the command line.
 
 ``` yaml $(tag) == 'release_3_0'
@@ -52,7 +52,7 @@ directive:
 
 ---
 
-## SpeechToText 3.1-preview.1
+## Tag: release_3_1_preview_1
 These settings apply only when `--tag=release_3_1_preview_1` is specified on the command line.
 
 ``` yaml $(tag) == 'release_3_1_preview_1'
@@ -70,7 +70,7 @@ directive:
 
 ---
 
-## SpeechToText 3.1
+## Tag: release_3_1
 
 These settings apply only when `--tag=release_3_1` is specified on the command line.
 
@@ -95,7 +95,7 @@ directive:
 
 ---
 
-## SpeechToText 3.2-preview.1
+## Tag: release_3_2_preview_1
 
 These settings apply only when `--tag=release_3_2_preview_1` is specified on the command line.
 
@@ -118,7 +118,7 @@ directive:
     reason: Existing API, change would potentially be breaking.
 ```
 
-## SpeechToText 3.2-preview.2
+## Tag: release_3_2_preview_2
 
 These settings apply only when `--tag=release_3_2_preview_2` is specified on the command line.
 
@@ -129,6 +129,29 @@ input-file:
 
 AutoRest-Linter Suppressions
 
+``` yaml
+# Ignore autorest-linter issues that cannot be resolve without updates to the API implementation
+directive:
+  - suppress: LongRunningOperationsWithLongRunningExtension
+    reason: Does not apply in those two places. The method is a DELETE which lazily deletes blobs, so it's Accepted, not NoContent. 
+  - suppress: OperationIdNounVerb
+    where: $..paths[($..operationId["Models_*"])]
+    reason: There is a sub-route called /models/base/ that refers to the base models. Therefore, the correct operation ID seems to be "Models_GetBaseModel", for example.
+  - suppress: HostParametersValidation
+    reason: Existing API, change would potentially be breaking.
+```
+
+## Tag: release_3_2
+
+These settings apply only when `--tag=release_3_2` is specified on the command line.
+
+```yaml $(tag) == 'release_3_2'
+input-file:
+  - stable/v3.2/speechtotext.json
+```
+
+AutoRest-Linter Suppressions
+
 ``` yaml
 # Ignore autorest-linter issues that cannot be resolve without updates to the API implementation
 directive:

diff --git a/...nitiveservices/data-plane/Speech/SpeechToText/stable/v3.2/examples/commit_block_list.json b/...nitiveservices/data-plane/Speech/SpeechToText/stable/v3.2/examples/commit_block_list.json
@@ -0,0 +1,26 @@
+{
+  "parameters": {
+    "Endpoint": "https://westus.api.cognitive.microsoft.com/",
+    "Ocp-Apim-Subscription-Key": "{API Key}",
+    "id": "9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1",
+    "blockList": [
+      {
+        "kind": "Uncommitted",
+        "id": "AAA="
+      },
+      {
+        "kind": "Uncommitted",
+        "id": "AAE="
+      },
+      {
+        "kind": "Uncommitted",
+        "id": "AAI="
+      }
+    ]
+  },
+  "responses": {
+    "200": {
+      "headers": {}
+    }
+  }
+}
diff --git a/...es/data-plane/Speech/SpeechToText/stable/v3.2/examples/copy_model_with_authorization.json b/...es/data-plane/Speech/SpeechToText/stable/v3.2/examples/copy_model_with_authorization.json
@@ -0,0 +1,30 @@
+{
+  "parameters": {
+    "Endpoint": "https://westus.api.cognitive.microsoft.com/",
+    "Ocp-Apim-Subscription-Key": "{API Key}",
+    "id": "827712a5-f942-4997-91c3-7c6cde35600b",
+    "modelCopyAuthorization": {
+      "targetResourceRegion": "westus2",
+      "targetResourceId": "/subscriptions/targetSubscriptionId/resourceGroups/targetResourceGroupName/providers/Microsoft.CognitiveServices/accounts/targetSpeechResourceName",
+      "targetResourceEndpoint": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/models",
+      "sourceResourceId": "/subscriptions/sourceSubscriptionId/resourceGroups/sourceResourceGroupName/providers/Microsoft.CognitiveServices/accounts/sourceSpeechResourceName",
+      "expirationDateTime": "2019-01-07T11:34:12Z",
+      "id": "d61573c6-788b-4eff-b3f5-38a1c7a9585b"
+    },
+    "Content-Type": "application/json"
+  },
+  "responses": {
+    "202": {
+      "headers": {
+        "Operation-Location": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/operations/models/copy/E30F6A27-82BE-4CCA-9258-0399C70489FF"
+      },
+      "body": {
+        "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/operations/models/copy/E30F6A27-82BE-4CCA-9258-0399C70489FF",
+        "createdDateTime": "2019-01-07T11:34:12Z",
+        "lastActionDateTime": "2019-01-07T11:34:12Z",
+        "status": "NotStarted",
+        "id": "e30f6a27-82be-4cca-9258-0399c70489ff"
+      }
+    }
+  }
+}
diff --git a/...s/data-plane/Speech/SpeechToText/stable/v3.2/examples/create_container_transcription.json b/...s/data-plane/Speech/SpeechToText/stable/v3.2/examples/create_container_transcription.json
@@ -0,0 +1,55 @@
+{
+  "parameters": {
+    "Endpoint": "https://westus.api.cognitive.microsoft.com/",
+    "Ocp-Apim-Subscription-Key": "{API Key}",
+    "transcription": {
+      "contentContainerUrl": "https://customspeech-usw.blob.core.windows.net/artifacts/audiofiles/",
+      "properties": {
+        "diarizationEnabled": false,
+        "wordLevelTimestampsEnabled": false,
+        "displayFormWordLevelTimestampsEnabled": false,
+        "punctuationMode": "DictatedAndAutomatic",
+        "profanityFilterMode": "Masked"
+      },
+      "locale": "en-US",
+      "displayName": "Transcription of storage container using default model for en-US"
+    },
+    "Content-Type": "application/json"
+  },
+  "responses": {
+    "201": {
+      "headers": {
+        "Location": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/transcriptions/ba7ea6f5-3065-40b7-b49a-a90f48584683"
+      },
+      "body": {
+        "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/transcriptions/ba7ea6f5-3065-40b7-b49a-a90f48584683",
+        "model": {
+          "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/models/827712a5-f942-4997-91c3-7c6cde35600b"
+        },
+        "links": {
+          "files": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/transcriptions/ba7ea6f5-3065-40b7-b49a-a90f48584683/files"
+        },
+        "properties": {
+          "diarizationEnabled": false,
+          "wordLevelTimestampsEnabled": false,
+          "displayFormWordLevelTimestampsEnabled": false,
+          "channels": [
+            0,
+            1
+          ],
+          "punctuationMode": "DictatedAndAutomatic",
+          "profanityFilterMode": "Masked",
+          "duration": "PT42S"
+        },
+        "lastActionDateTime": "2019-01-07T11:36:07Z",
+        "status": "Succeeded",
+        "createdDateTime": "2019-01-07T11:34:12Z",
+        "locale": "en-US",
+        "displayName": "Transcription using adapted model en-US",
+        "customProperties": {
+          "key": "value"
+        }
+      }
+    }
+  }
+}
diff --git a/.../data-plane/Speech/SpeechToText/stable/v3.2/examples/create_copy_model_authorization.json b/.../data-plane/Speech/SpeechToText/stable/v3.2/examples/create_copy_model_authorization.json
@@ -0,0 +1,23 @@
+{
+  "parameters": {
+    "Endpoint": "https://westus.api.cognitive.microsoft.com/",
+    "Ocp-Apim-Subscription-Key": "{API Key}",
+    "modelCopyAuthorizationDefinition": {
+      "sourceResourceId": "/subscriptions/sourceSubscriptionId/resourceGroups/sourceResourceGroupName/providers/Microsoft.CognitiveServices/accounts/sourceSpeechResourceName"
+    },
+    "Content-Type": "application/json"
+  },
+  "responses": {
+    "200": {
+      "headers": {},
+      "body": {
+        "targetResourceRegion": "westus2",
+        "targetResourceId": "/subscriptions/targetSubscriptionId/resourceGroups/targetResourceGroupName/providers/Microsoft.CognitiveServices/accounts/targetSpeechResourceName",
+        "targetResourceEndpoint": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/models",
+        "sourceResourceId": "/subscriptions/sourceSubscriptionId/resourceGroups/sourceResourceGroupName/providers/Microsoft.CognitiveServices/accounts/sourceSpeechResourceName",
+        "expirationDateTime": "2019-01-07T11:34:12Z",
+        "id": "d61573c6-788b-4eff-b3f5-38a1c7a9585b"
+      }
+    }
+  }
+}
diff --git a/...vices/data-plane/Speech/SpeechToText/stable/v3.2/examples/create_dataset_with_blocks.json b/...vices/data-plane/Speech/SpeechToText/stable/v3.2/examples/create_dataset_with_blocks.json
@@ -0,0 +1,33 @@
+{
+  "parameters": {
+    "Endpoint": "https://westus.api.cognitive.microsoft.com/",
+    "Ocp-Apim-Subscription-Key": "{API Key}",
+    "dataset": {
+      "kind": "Acoustic",
+      "locale": "en-US",
+      "displayName": "My speech dataset name",
+      "description": "My speech dataset description"
+    },
+    "Content-Type": "application/json"
+  },
+  "responses": {
+    "201": {
+      "headers": {},
+      "body": {
+        "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1",
+        "kind": "Acoustic",
+        "links": {
+          "files": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1/files",
+          "commitBlocks": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1/blocks:commit",
+          "listBlocks": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1/blocks",
+          "uploadBlocks": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1/blocks"
+        },
+        "lastActionDateTime": "2019-01-07T11:36:07Z",
+        "status": "NotStarted",
+        "createdDateTime": "2019-01-07T11:34:12Z",
+        "locale": "en-US",
+        "displayName": "Acoustic dataset"
+      }
+    }
+  }
+}
diff --git a/.../data-plane/Speech/SpeechToText/stable/v3.2/examples/create_dataset_with_content_url.json b/.../data-plane/Speech/SpeechToText/stable/v3.2/examples/create_dataset_with_content_url.json
@@ -0,0 +1,40 @@
+{
+  "parameters": {
+    "Endpoint": "https://westus.api.cognitive.microsoft.com/",
+    "Ocp-Apim-Subscription-Key": "{API Key}",
+    "dataset": {
+      "kind": "Acoustic",
+      "contentUrl": "https://contoso.com/location",
+      "locale": "en-US",
+      "displayName": "My speech dataset name",
+      "description": "My speech dataset description"
+    },
+    "Content-Type": "application/json"
+  },
+  "responses": {
+    "201": {
+      "headers": {
+        "Location": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1"
+      },
+      "body": {
+        "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1",
+        "kind": "Acoustic",
+        "contentUrl": "https://www.contoso.com/acousticdata/sourcelocation",
+        "links": {
+          "files": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1/files"
+        },
+        "properties": {
+          "textNormalizationKind": "Default",
+          "acceptedLineCount": 11,
+          "rejectedLineCount": 2,
+          "duration": "PT4M12S"
+        },
+        "lastActionDateTime": "2019-01-07T11:36:07Z",
+        "status": "Succeeded",
+        "createdDateTime": "2019-01-07T11:34:12Z",
+        "locale": "en-US",
+        "displayName": "Acoustic dataset"
+      }
+    }
+  }
+}
diff --git a/...ognitiveservices/data-plane/Speech/SpeechToText/stable/v3.2/examples/create_endpoint.json b/...ognitiveservices/data-plane/Speech/SpeechToText/stable/v3.2/examples/create_endpoint.json
@@ -0,0 +1,50 @@
+{
+  "parameters": {
+    "Endpoint": "https://westus.api.cognitive.microsoft.com/",
+    "Ocp-Apim-Subscription-Key": "{API Key}",
+    "endpoint": {
+      "model": {
+        "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/models/827712a5-f942-4997-91c3-7c6cde35600b"
+      },
+      "properties": {
+        "loggingEnabled": true
+      },
+      "locale": "en-US",
+      "displayName": "Speech endpoint definition",
+      "description": "This is a speech endpoint"
+    },
+    "Content-Type": "application/json"
+  },
+  "responses": {
+    "201": {
+      "headers": {
+        "Location": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/endpoints/afa0669c-a01e-4693-ae3a-93baf40f26d6"
+      },
+      "body": {
+        "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/endpoints/afa0669c-a01e-4693-ae3a-93baf40f26d6",
+        "model": {
+          "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/models/827712a5-f942-4997-91c3-7c6cde35600b"
+        },
+        "links": {
+          "logs": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.2/endpoints/afa0669c-a01e-4693-ae3a-93baf40f26d6/files/logs",
+          "restInteractive": "https://westus.stt.speech.microsoft.com/speech/recognition/interactive/cognitiveservices/v1?cid=afa0669c-a01e-4693-ae3a-93baf40f26d6",
+          "restConversation": "https://westus.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1?cid=afa0669c-a01e-4693-ae3a-93baf40f26d6",
+          "restDictation": "https://westus.stt.speech.microsoft.com/speech/recognition/dictation/cognitiveservices/v1?cid=afa0669c-a01e-4693-ae3a-93baf40f26d6",
+          "webSocketInteractive": "wss://westus.stt.speech.microsoft.com/speech/recognition/interactive/cognitiveservices/v1?cid=afa0669c-a01e-4693-ae3a-93baf40f26d6",
+          "webSocketConversation": "wss://westus.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1?cid=afa0669c-a01e-4693-ae3a-93baf40f26d6",
+          "webSocketDictation": "wss://westus.stt.speech.microsoft.com/speech/recognition/dictation/cognitiveservices/v1?cid=afa0669c-a01e-4693-ae3a-93baf40f26d6"
+        },
+        "properties": {
+          "timeToLive": "PT30M",
+          "loggingEnabled": true
+        },
+        "lastActionDateTime": "2019-01-07T11:36:07Z",
+        "status": "Succeeded",
+        "createdDateTime": "2019-01-07T11:34:12Z",
+        "locale": "en-US",
+        "displayName": "Speech endpoint",
+        "description": "Example for speech endpoint"
+      }
+    }
+  }
+}