Skip to content

Commit 773b3e3

Browse files
andreasjlanandanthony
andreasjl
authored and
anandanthony
committed
[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
1 parent 88dbd67 commit 773b3e3

File tree

91 files changed

+10246
-3
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

91 files changed

+10246
-3
lines changed

‎specification/cognitiveservices/data-plane/Speech/SpeechToText/readme.md

Lines changed: 28 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -4,10 +4,10 @@
44
55
Configuration for generating SpeechToText SDK.
66

7-
The current release for the SpeechToText is `release_3_0`.
7+
The current release for the SpeechToText is `release_3_1`.
88

99
``` yaml
10-
tag: release_3_0
10+
tag: release_3_1
1111
add-credentials: true
1212
openapi-type: data-plane
1313
```
@@ -66,4 +66,29 @@ AutoRest-Linter Suppressions
6666
directive:
6767
- suppress: LongRunningOperationsWithLongRunningExtension
6868
reason: Does not apply in those two places. The method is a DELETE which lazily deletes blobs, so it's Accepted, not NoContent.
69-
```
69+
```
70+
71+
---
72+
73+
## SpeechToText 3.1
74+
75+
These settings apply only when `--tag=release_3_1` is specified on the command line.
76+
77+
```yaml $(tag) == 'release_3_1'
78+
input-file:
79+
- stable/v3.1/speechtotext.json
80+
```
81+
82+
AutoRest-Linter Suppressions
83+
84+
``` yaml
85+
# Ignore autorest-linter issues that cannot be resolve without updates to the API implementation
86+
directive:
87+
- suppress: LongRunningOperationsWithLongRunningExtension
88+
reason: Does not apply in those two places. The method is a DELETE which lazily deletes blobs, so it's Accepted, not NoContent.
89+
- suppress: OperationIdNounVerb
90+
where: $..paths[($..operationId["Models_*"])]
91+
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.
92+
- suppress: HostParametersValidation
93+
reason: Existing API, change would potentially be breaking.
94+
```

‎specification/cognitiveservices/data-plane/Speech/SpeechToText/stable/v3.1/examples/commit_block_list.json

Lines changed: 26 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,26 @@
1+
{
2+
"parameters": {
3+
"Endpoint": "https://westus.api.cognitive.microsoft.com/",
4+
"Ocp-Apim-Subscription-Key": "{API Key}",
5+
"id": "9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1",
6+
"blockList": [
7+
{
8+
"kind": "Uncommitted",
9+
"id": "AAA="
10+
},
11+
{
12+
"kind": "Uncommitted",
13+
"id": "AAE="
14+
},
15+
{
16+
"kind": "Uncommitted",
17+
"id": "AAI="
18+
}
19+
]
20+
},
21+
"responses": {
22+
"200": {
23+
"headers": {}
24+
}
25+
}
26+
}

‎specification/cognitiveservices/data-plane/Speech/SpeechToText/stable/v3.1/examples/copy_model.json

Lines changed: 49 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,49 @@
1+
{
2+
"parameters": {
3+
"Endpoint": "https://westus.api.cognitive.microsoft.com/",
4+
"Ocp-Apim-Subscription-Key": "{API Key}",
5+
"id": "827712a5-f942-4997-91c3-7c6cde35600b",
6+
"modelCopy": {
7+
"targetSubscriptionKey": "KeyForTheSubscriptionTheModelIsSupposedToBeCopiedTo"
8+
},
9+
"Content-Type": "application/json"
10+
},
11+
"responses": {
12+
"201": {
13+
"headers": {},
14+
"body": {
15+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/827712a5-f942-4997-91c3-7c6cde35600b",
16+
"baseModel": {
17+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/base/8a043172-65b7-4cf3-a8b5-4449efa5a0f1"
18+
},
19+
"datasets": [
20+
{
21+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/datasets/cdc91c24-3972-496d-a12f-209c35f4cc6c"
22+
}
23+
],
24+
"links": {
25+
"manifest": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/endpoints/manifest/827712a5-f942-4997-91c3-7c6cde35600b",
26+
"copyTo": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/827712a5-f942-4997-91c3-7c6cde35600b:copyto",
27+
"files": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/827712a5-f942-4997-91c3-7c6cde35600b/files"
28+
},
29+
"properties": {
30+
"deprecationDates": {
31+
"transcriptionDateTime": "2023-05-04T00:00:00Z"
32+
},
33+
"customModelWeightPercent": 30,
34+
"features": {
35+
"supportsTranscriptions": true,
36+
"supportsEndpoints": true,
37+
"supportsTranscriptionsOnSpeechContainers": false
38+
}
39+
},
40+
"lastActionDateTime": "2019-01-07T11:36:07Z",
41+
"status": "Running",
42+
"createdDateTime": "2019-01-07T11:34:12Z",
43+
"locale": "en-US",
44+
"displayName": "Language model",
45+
"description": "This is a language model"
46+
}
47+
}
48+
}
49+
}

‎specification/cognitiveservices/data-plane/Speech/SpeechToText/stable/v3.1/examples/create_container_transcription.json

Lines changed: 54 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,54 @@
1+
{
2+
"parameters": {
3+
"Endpoint": "https://westus.api.cognitive.microsoft.com/",
4+
"Ocp-Apim-Subscription-Key": "{API Key}",
5+
"transcription": {
6+
"contentContainerUrl": "https://customspeech-usw.blob.core.windows.net/artifacts/audiofiles/",
7+
"properties": {
8+
"diarizationEnabled": false,
9+
"wordLevelTimestampsEnabled": false,
10+
"punctuationMode": "DictatedAndAutomatic",
11+
"profanityFilterMode": "Masked"
12+
},
13+
"locale": "en-US",
14+
"displayName": "Transcription of storage container using default model for en-US"
15+
},
16+
"Content-Type": "application/json"
17+
},
18+
"responses": {
19+
"201": {
20+
"headers": {
21+
"Location": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/transcriptions/ba7ea6f5-3065-40b7-b49a-a90f48584683"
22+
},
23+
"body": {
24+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/transcriptions/ba7ea6f5-3065-40b7-b49a-a90f48584683",
25+
"model": {
26+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/827712a5-f942-4997-91c3-7c6cde35600b"
27+
},
28+
"links": {
29+
"files": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/transcriptions/ba7ea6f5-3065-40b7-b49a-a90f48584683/files"
30+
},
31+
"properties": {
32+
"diarizationEnabled": false,
33+
"wordLevelTimestampsEnabled": false,
34+
"displayFormWordLevelTimestampsEnabled": false,
35+
"channels": [
36+
0,
37+
1
38+
],
39+
"punctuationMode": "DictatedAndAutomatic",
40+
"profanityFilterMode": "Masked",
41+
"duration": "PT42S"
42+
},
43+
"lastActionDateTime": "2019-01-07T11:36:07Z",
44+
"status": "Succeeded",
45+
"createdDateTime": "2019-01-07T11:34:12Z",
46+
"locale": "en-US",
47+
"displayName": "Transcription using adapted model en-US",
48+
"customProperties": {
49+
"key": "value"
50+
}
51+
}
52+
}
53+
}
54+
}

‎specification/cognitiveservices/data-plane/Speech/SpeechToText/stable/v3.1/examples/create_dataset_with_blocks.json

Lines changed: 33 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,33 @@
1+
{
2+
"parameters": {
3+
"Endpoint": "https://westus.api.cognitive.microsoft.com/",
4+
"Ocp-Apim-Subscription-Key": "{API Key}",
5+
"dataset": {
6+
"kind": "Acoustic",
7+
"locale": "en-US",
8+
"displayName": "My speech dataset name",
9+
"description": "My speech dataset description"
10+
},
11+
"Content-Type": "application/json"
12+
},
13+
"responses": {
14+
"201": {
15+
"headers": {},
16+
"body": {
17+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1",
18+
"kind": "Acoustic",
19+
"links": {
20+
"files": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1/files",
21+
"commitBlocks": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1/blocks:commit",
22+
"listBlocks": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1/blocks",
23+
"uploadBlocks": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1/blocks"
24+
},
25+
"lastActionDateTime": "2019-01-07T11:36:07Z",
26+
"status": "NotStarted",
27+
"createdDateTime": "2019-01-07T11:34:12Z",
28+
"locale": "en-US",
29+
"displayName": "Acoustic dataset"
30+
}
31+
}
32+
}
33+
}

‎specification/cognitiveservices/data-plane/Speech/SpeechToText/stable/v3.1/examples/create_dataset_with_content_url.json

Lines changed: 39 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,39 @@
1+
{
2+
"parameters": {
3+
"Endpoint": "https://westus.api.cognitive.microsoft.com/",
4+
"Ocp-Apim-Subscription-Key": "{API Key}",
5+
"dataset": {
6+
"kind": "Acoustic",
7+
"contentUrl": "https://contoso.com/location",
8+
"locale": "en-US",
9+
"displayName": "My speech dataset name",
10+
"description": "My speech dataset description"
11+
},
12+
"Content-Type": "application/json"
13+
},
14+
"responses": {
15+
"201": {
16+
"headers": {
17+
"Location": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1"
18+
},
19+
"body": {
20+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1",
21+
"kind": "Acoustic",
22+
"contentUrl": "https://www.contoso.com/acousticdata/sourcelocation",
23+
"links": {
24+
"files": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1/files"
25+
},
26+
"properties": {
27+
"acceptedLineCount": 11,
28+
"rejectedLineCount": 2,
29+
"duration": "PT4M12S"
30+
},
31+
"lastActionDateTime": "2019-01-07T11:36:07Z",
32+
"status": "Succeeded",
33+
"createdDateTime": "2019-01-07T11:34:12Z",
34+
"locale": "en-US",
35+
"displayName": "Acoustic dataset"
36+
}
37+
}
38+
}
39+
}

‎specification/cognitiveservices/data-plane/Speech/SpeechToText/stable/v3.1/examples/create_endpoint.json

Lines changed: 50 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,50 @@
1+
{
2+
"parameters": {
3+
"Endpoint": "https://westus.api.cognitive.microsoft.com/",
4+
"Ocp-Apim-Subscription-Key": "{API Key}",
5+
"endpoint": {
6+
"model": {
7+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/827712a5-f942-4997-91c3-7c6cde35600b"
8+
},
9+
"properties": {
10+
"loggingEnabled": true
11+
},
12+
"locale": "en-US",
13+
"displayName": "Speech endpoint definition",
14+
"description": "This is a speech endpoint"
15+
},
16+
"Content-Type": "application/json"
17+
},
18+
"responses": {
19+
"201": {
20+
"headers": {
21+
"Location": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/endpoints/afa0669c-a01e-4693-ae3a-93baf40f26d6"
22+
},
23+
"body": {
24+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/endpoints/afa0669c-a01e-4693-ae3a-93baf40f26d6",
25+
"model": {
26+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/827712a5-f942-4997-91c3-7c6cde35600b"
27+
},
28+
"links": {
29+
"logs": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/endpoints/afa0669c-a01e-4693-ae3a-93baf40f26d6/files/logs",
30+
"restInteractive": "https://westus.stt.speech.microsoft.com/speech/recognition/interactive/cognitiveservices/v1?cid=afa0669c-a01e-4693-ae3a-93baf40f26d6",
31+
"restConversation": "https://westus.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1?cid=afa0669c-a01e-4693-ae3a-93baf40f26d6",
32+
"restDictation": "https://westus.stt.speech.microsoft.com/speech/recognition/dictation/cognitiveservices/v1?cid=afa0669c-a01e-4693-ae3a-93baf40f26d6",
33+
"webSocketInteractive": "wss://westus.stt.speech.microsoft.com/speech/recognition/interactive/cognitiveservices/v1?cid=afa0669c-a01e-4693-ae3a-93baf40f26d6",
34+
"webSocketConversation": "wss://westus.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1?cid=afa0669c-a01e-4693-ae3a-93baf40f26d6",
35+
"webSocketDictation": "wss://westus.stt.speech.microsoft.com/speech/recognition/dictation/cognitiveservices/v1?cid=afa0669c-a01e-4693-ae3a-93baf40f26d6"
36+
},
37+
"properties": {
38+
"timeToLive": "PT30M",
39+
"loggingEnabled": true
40+
},
41+
"lastActionDateTime": "2019-01-07T11:36:07Z",
42+
"status": "Succeeded",
43+
"createdDateTime": "2019-01-07T11:34:12Z",
44+
"locale": "en-US",
45+
"displayName": "Speech endpoint",
46+
"description": "Example for speech endpoint"
47+
}
48+
}
49+
}
50+
}

‎specification/cognitiveservices/data-plane/Speech/SpeechToText/stable/v3.1/examples/create_evaluation.json

Lines changed: 72 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,72 @@
1+
{
2+
"parameters": {
3+
"Endpoint": "https://westus.api.cognitive.microsoft.com/",
4+
"Ocp-Apim-Subscription-Key": "{API Key}",
5+
"evaluation": {
6+
"model1": {
7+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/base/8a043172-65b7-4cf3-a8b5-4449efa5a0f1"
8+
},
9+
"model2": {
10+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/827712a5-f942-4997-91c3-7c6cde35600b"
11+
},
12+
"dataset": {
13+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1"
14+
},
15+
"locale": "en-US",
16+
"displayName": "My new evaluation",
17+
"description": "The description of the evaluation"
18+
},
19+
"Content-Type": "application/json"
20+
},
21+
"responses": {
22+
"201": {
23+
"headers": {
24+
"Location": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/evaluations/1c50ce42-6ab7-454f-8c39-54a752d1a5b6"
25+
},
26+
"body": {
27+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/evaluations/1c50ce42-6ab7-454f-8c39-54a752d1a5b6",
28+
"model1": {
29+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/base/8a043172-65b7-4cf3-a8b5-4449efa5a0f1"
30+
},
31+
"model2": {
32+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/models/827712a5-f942-4997-91c3-7c6cde35600b"
33+
},
34+
"dataset": {
35+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1"
36+
},
37+
"transcription2": {
38+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/transcriptions/ad86d0c9-af6d-4d14-a621-c60d7d65b74f"
39+
},
40+
"transcription1": {
41+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/transcriptions/ba7ea6f5-3065-40b7-b49a-a90f48584683"
42+
},
43+
"links": {
44+
"files": "https://westus.api.cognitive.microsoft.com/speechtotext/v3.1/evaluations/00000000-0000-0000-0000-000000000000/files"
45+
},
46+
"properties": {
47+
"wordErrorRate2": 0.065,
48+
"wordErrorRate1": 0.065,
49+
"sentenceErrorRate2": 0.375,
50+
"sentenceCount2": 8,
51+
"wordCount2": 46,
52+
"correctWordCount2": 43,
53+
"wordSubstitutionCount2": 3,
54+
"wordDeletionCount2": 0,
55+
"wordInsertionCount2": 0,
56+
"sentenceErrorRate1": 0.375,
57+
"sentenceCount1": 8,
58+
"wordCount1": 46,
59+
"correctWordCount1": 43,
60+
"wordSubstitutionCount1": 3,
61+
"wordDeletionCount1": 0,
62+
"wordInsertionCount1": 0
63+
},
64+
"lastActionDateTime": "2019-01-07T11:36:07Z",
65+
"status": "Succeeded",
66+
"createdDateTime": "2019-01-07T11:34:12Z",
67+
"locale": "en-US",
68+
"displayName": "Evalution of one model against another model"
69+
}
70+
}
71+
}
72+
}

0 commit comments

Comments
 (0)