[Cognitive - Custom Speech] Review request for Speech/SpeechToText to…

… add version stable/v3.1 (Azure#21165) * Adds base for updating Speech/SpeechToText from version preview/v3.1-preview.1 to version v3.1 * Updates readme * Updates API version in new specs and examples * Modifications for 3.1 GA version * Trying to fix autorest config * Change tag * Model BlockKind as string * Revert doc change * Prettier fix * Trying to fix formatting of docs * Check output * Address Swagger lint issues and update some docs * Run prettier * Fix Swagger * Make same changes also to existing versions * Revert "Make same changes also to existing versions" This reverts commit be557bd. * Add minLength for required strings * Lower-case endpoint parameter * Add suppressions
kayousef-zz · Dec 21, 2022 · d882f98 · d882f98
1 parent 20004ea
commit d882f98
Show file tree

Hide file tree

Showing 91 changed files with 10,246 additions and 3 deletions.
diff --git a/specification/cognitiveservices/data-plane/Speech/SpeechToText/readme.md b/specification/cognitiveservices/data-plane/Speech/SpeechToText/readme.md
@@ -4,10 +4,10 @@
 
 Configuration for generating SpeechToText SDK.
 
-The current release for the SpeechToText is `release_3_0`.
+The current release for the SpeechToText is `release_3_1`.
 
 ``` yaml
-tag: release_3_0
+tag: release_3_1
 add-credentials: true
 openapi-type: data-plane
 ```
@@ -66,4 +66,29 @@ AutoRest-Linter Suppressions
 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. 
-```
+```
+
+---
+
+## SpeechToText 3.1
+
+These settings apply only when `--tag=release_3_1` is specified on the command line.
+
+```yaml $(tag) == 'release_3_1'
+input-file:
+  - stable/v3.1/speechtotext.json
+```
+
+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.
+```
diff --git a/...nitiveservices/data-plane/Speech/SpeechToText/stable/v3.1/examples/commit_block_list.json b/...nitiveservices/data-plane/Speech/SpeechToText/stable/v3.1/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/...ion/cognitiveservices/data-plane/Speech/SpeechToText/stable/v3.1/examples/copy_model.json b/...ion/cognitiveservices/data-plane/Speech/SpeechToText/stable/v3.1/examples/copy_model.json
@@ -0,0 +1,49 @@
+{
+  "parameters": {
+    "Endpoint": "https://westus.api.cognitive.microsoft.com/",
+    "Ocp-Apim-Subscription-Key": "{API Key}",
+    "id": "827712a5-f942-4997-91c3-7c6cde35600b",
+    "modelCopy": {
+      "targetSubscriptionKey": "KeyForTheSubscriptionTheModelIsSupposedToBeCopiedTo"
+    },
+    "Content-Type": "application/json"
+  },
+  "responses": {
+    "201": {
+      "headers": {},
+      "body": {
+        "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/827712a5-f942-4997-91c3-7c6cde35600b",
+        "baseModel": {
+          "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/base/8a043172-65b7-4cf3-a8b5-4449efa5a0f1"
+        },
+        "datasets": [
+          {
+            "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/datasets/cdc91c24-3972-496d-a12f-209c35f4cc6c"
+          }
+        ],
+        "links": {
+          "manifest": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/endpoints/manifest/827712a5-f942-4997-91c3-7c6cde35600b",
+          "copyTo": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/827712a5-f942-4997-91c3-7c6cde35600b:copyto",
+          "files": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/827712a5-f942-4997-91c3-7c6cde35600b/files"
+        },
+        "properties": {
+          "deprecationDates": {
+            "transcriptionDateTime": "2023-05-04T00:00:00Z"
+          },
+          "customModelWeightPercent": 30,
+          "features": {
+            "supportsTranscriptions": true,
+            "supportsEndpoints": true,
+            "supportsTranscriptionsOnSpeechContainers": false
+          }
+        },
+        "lastActionDateTime": "2019-01-07T11:36:07Z",
+        "status": "Running",
+        "createdDateTime": "2019-01-07T11:34:12Z",
+        "locale": "en-US",
+        "displayName": "Language model",
+        "description": "This is a language model"
+      }
+    }
+  }
+}
diff --git a/...s/data-plane/Speech/SpeechToText/stable/v3.1/examples/create_container_transcription.json b/...s/data-plane/Speech/SpeechToText/stable/v3.1/examples/create_container_transcription.json
@@ -0,0 +1,54 @@
+{
+  "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,
+        "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/v3.1/transcriptions/ba7ea6f5-3065-40b7-b49a-a90f48584683"
+      },
+      "body": {
+        "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/transcriptions/ba7ea6f5-3065-40b7-b49a-a90f48584683",
+        "model": {
+          "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/827712a5-f942-4997-91c3-7c6cde35600b"
+        },
+        "links": {
+          "files": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/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/...vices/data-plane/Speech/SpeechToText/stable/v3.1/examples/create_dataset_with_blocks.json b/...vices/data-plane/Speech/SpeechToText/stable/v3.1/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/v3.1/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1",
+        "kind": "Acoustic",
+        "links": {
+          "files": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1/files",
+          "commitBlocks": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1/blocks:commit",
+          "listBlocks": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1/blocks",
+          "uploadBlocks": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/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/v3.1/examples/create_dataset_with_content_url.json b/.../data-plane/Speech/SpeechToText/stable/v3.1/examples/create_dataset_with_content_url.json
@@ -0,0 +1,39 @@
+{
+  "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/v3.1/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1"
+      },
+      "body": {
+        "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1",
+        "kind": "Acoustic",
+        "contentUrl": "https://www.contoso.com/acousticdata/sourcelocation",
+        "links": {
+          "files": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1/files"
+        },
+        "properties": {
+          "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/v3.1/examples/create_endpoint.json b/...ognitiveservices/data-plane/Speech/SpeechToText/stable/v3.1/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/v3.1/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/v3.1/endpoints/afa0669c-a01e-4693-ae3a-93baf40f26d6"
+      },
+      "body": {
+        "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/endpoints/afa0669c-a01e-4693-ae3a-93baf40f26d6",
+        "model": {
+          "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/827712a5-f942-4997-91c3-7c6cde35600b"
+        },
+        "links": {
+          "logs": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/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"
+      }
+    }
+  }
+}
diff --git a/...nitiveservices/data-plane/Speech/SpeechToText/stable/v3.1/examples/create_evaluation.json b/...nitiveservices/data-plane/Speech/SpeechToText/stable/v3.1/examples/create_evaluation.json
@@ -0,0 +1,72 @@
+{
+  "parameters": {
+    "Endpoint": "https://westus.api.cognitive.microsoft.com/",
+    "Ocp-Apim-Subscription-Key": "{API Key}",
+    "evaluation": {
+      "model1": {
+        "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/base/8a043172-65b7-4cf3-a8b5-4449efa5a0f1"
+      },
+      "model2": {
+        "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/827712a5-f942-4997-91c3-7c6cde35600b"
+      },
+      "dataset": {
+        "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1"
+      },
+      "locale": "en-US",
+      "displayName": "My new evaluation",
+      "description": "The description of the evaluation"
+    },
+    "Content-Type": "application/json"
+  },
+  "responses": {
+    "201": {
+      "headers": {
+        "Location": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/evaluations/1c50ce42-6ab7-454f-8c39-54a752d1a5b6"
+      },
+      "body": {
+        "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/evaluations/1c50ce42-6ab7-454f-8c39-54a752d1a5b6",
+        "model1": {
+          "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/base/8a043172-65b7-4cf3-a8b5-4449efa5a0f1"
+        },
+        "model2": {
+          "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/827712a5-f942-4997-91c3-7c6cde35600b"
+        },
+        "dataset": {
+          "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1"
+        },
+        "transcription2": {
+          "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/transcriptions/ad86d0c9-af6d-4d14-a621-c60d7d65b74f"
+        },
+        "transcription1": {
+          "self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/transcriptions/ba7ea6f5-3065-40b7-b49a-a90f48584683"
+        },
+        "links": {
+          "files": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/evaluations/00000000-0000-0000-0000-000000000000/files"
+        },
+        "properties": {
+          "wordErrorRate2": 0.065,
+          "wordErrorRate1": 0.065,
+          "sentenceErrorRate2": 0.375,
+          "sentenceCount2": 8,
+          "wordCount2": 46,
+          "correctWordCount2": 43,
+          "wordSubstitutionCount2": 3,
+          "wordDeletionCount2": 0,
+          "wordInsertionCount2": 0,
+          "sentenceErrorRate1": 0.375,
+          "sentenceCount1": 8,
+          "wordCount1": 46,
+          "correctWordCount1": 43,
+          "wordSubstitutionCount1": 3,
+          "wordDeletionCount1": 0,
+          "wordInsertionCount1": 0
+        },
+        "lastActionDateTime": "2019-01-07T11:36:07Z",
+        "status": "Succeeded",
+        "createdDateTime": "2019-01-07T11:34:12Z",
+        "locale": "en-US",
+        "displayName": "Evalution of one model against another model"
+      }
+    }
+  }
+}