Skip to content

Commit 1aa9126

Browse files
authored
Add 2024-05-15-preview of SpeechToText API (CognitiveServices) (Azure#29804)
* Add preview GA as base * Updates for new preview version * Update readme.md * Added required ttl to examples * Add description * Add missing example * Keep latest GA latest
1 parent 3bcdb0e commit 1aa9126

File tree

93 files changed

+11417
-1
lines changed

Some content is hidden

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

93 files changed

+11417
-1
lines changed
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,27 @@
1+
{
2+
"parameters": {
3+
"Endpoint": "https://westus.api.cognitive.microsoft.com/",
4+
"Ocp-Apim-Subscription-Key": "{API Key}",
5+
"api-version": "2024-05-15-preview",
6+
"id": "9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1",
7+
"blockList": [
8+
{
9+
"kind": "Uncommitted",
10+
"id": "AAA="
11+
},
12+
{
13+
"kind": "Uncommitted",
14+
"id": "AAE="
15+
},
16+
{
17+
"kind": "Uncommitted",
18+
"id": "AAI="
19+
}
20+
]
21+
},
22+
"responses": {
23+
"200": {
24+
"headers": {}
25+
}
26+
}
27+
}
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,31 @@
1+
{
2+
"parameters": {
3+
"Endpoint": "https://westus.api.cognitive.microsoft.com/",
4+
"Ocp-Apim-Subscription-Key": "{API Key}",
5+
"api-version": "2024-05-15-preview",
6+
"id": "827712a5-f942-4997-91c3-7c6cde35600b",
7+
"modelCopyAuthorization": {
8+
"targetResourceRegion": "westus2",
9+
"targetResourceId": "/subscriptions/targetSubscriptionId/resourceGroups/targetResourceGroupName/providers/Microsoft.CognitiveServices/accounts/targetSpeechResourceName",
10+
"targetResourceEndpoint": "https://westus.api.cognitive.microsoft.com/speechtotext/models?api-version=2024-05-15-preview",
11+
"sourceResourceId": "/subscriptions/sourceSubscriptionId/resourceGroups/sourceResourceGroupName/providers/Microsoft.CognitiveServices/accounts/sourceSpeechResourceName",
12+
"expirationDateTime": "2019-01-07T11:34:12Z",
13+
"id": "d61573c6-788b-4eff-b3f5-38a1c7a9585b"
14+
},
15+
"Content-Type": "application/json"
16+
},
17+
"responses": {
18+
"202": {
19+
"headers": {
20+
"Operation-Location": "https://westus.api.cognitive.microsoft.com/speechtotext/operations/models/copy/E30F6A27-82BE-4CCA-9258-0399C70489FF?api-version=2024-05-15-preview"
21+
},
22+
"body": {
23+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/operations/models/copy/E30F6A27-82BE-4CCA-9258-0399C70489FF?api-version=2024-05-15-preview",
24+
"createdDateTime": "2019-01-07T11:34:12Z",
25+
"lastActionDateTime": "2019-01-07T11:34:12Z",
26+
"status": "NotStarted",
27+
"id": "e30f6a27-82be-4cca-9258-0399c70489ff"
28+
}
29+
}
30+
}
31+
}
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,58 @@
1+
{
2+
"parameters": {
3+
"Endpoint": "https://westus.api.cognitive.microsoft.com/",
4+
"Ocp-Apim-Subscription-Key": "{API Key}",
5+
"api-version": "2024-05-15-preview",
6+
"transcription": {
7+
"contentContainerUrl": "https://customspeech-usw.blob.core.windows.net/artifacts/audiofiles/",
8+
"properties": {
9+
"diarizationEnabled": false,
10+
"wordLevelTimestampsEnabled": false,
11+
"displayFormWordLevelTimestampsEnabled": false,
12+
"punctuationMode": "DictatedAndAutomatic",
13+
"profanityFilterMode": "Masked",
14+
"timeToLive": "P2D"
15+
},
16+
"locale": "en-US",
17+
"displayName": "Transcription of storage container using default model for en-US"
18+
},
19+
"Content-Type": "application/json"
20+
},
21+
"responses": {
22+
"201": {
23+
"headers": {
24+
"Location": "https://westus.api.cognitive.microsoft.com/speechtotext/transcriptions/ba7ea6f5-3065-40b7-b49a-a90f48584683?api-version=2024-05-15-preview"
25+
},
26+
"body": {
27+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/transcriptions/ba7ea6f5-3065-40b7-b49a-a90f48584683?api-version=2024-05-15-preview",
28+
"model": {
29+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/models/827712a5-f942-4997-91c3-7c6cde35600b?api-version=2024-05-15-preview"
30+
},
31+
"links": {
32+
"files": "https://westus.api.cognitive.microsoft.com/speechtotext/transcriptions/ba7ea6f5-3065-40b7-b49a-a90f48584683/files?api-version=2024-05-15-preview"
33+
},
34+
"properties": {
35+
"diarizationEnabled": false,
36+
"wordLevelTimestampsEnabled": false,
37+
"displayFormWordLevelTimestampsEnabled": false,
38+
"channels": [
39+
0,
40+
1
41+
],
42+
"punctuationMode": "DictatedAndAutomatic",
43+
"profanityFilterMode": "Masked",
44+
"duration": "PT42S",
45+
"timeToLive": "P2D"
46+
},
47+
"lastActionDateTime": "2019-01-07T11:36:07Z",
48+
"status": "Succeeded",
49+
"createdDateTime": "2019-01-07T11:34:12Z",
50+
"locale": "en-US",
51+
"displayName": "Transcription using adapted model en-US",
52+
"customProperties": {
53+
"key": "value"
54+
}
55+
}
56+
}
57+
}
58+
}
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,24 @@
1+
{
2+
"parameters": {
3+
"Endpoint": "https://westus.api.cognitive.microsoft.com/",
4+
"Ocp-Apim-Subscription-Key": "{API Key}",
5+
"api-version": "2024-05-15-preview",
6+
"modelCopyAuthorizationDefinition": {
7+
"sourceResourceId": "/subscriptions/sourceSubscriptionId/resourceGroups/sourceResourceGroupName/providers/Microsoft.CognitiveServices/accounts/sourceSpeechResourceName"
8+
},
9+
"Content-Type": "application/json"
10+
},
11+
"responses": {
12+
"200": {
13+
"headers": {},
14+
"body": {
15+
"targetResourceRegion": "westus2",
16+
"targetResourceId": "/subscriptions/targetSubscriptionId/resourceGroups/targetResourceGroupName/providers/Microsoft.CognitiveServices/accounts/targetSpeechResourceName",
17+
"targetResourceEndpoint": "https://westus.api.cognitive.microsoft.com/speechtotext/models?api-version=2024-05-15-preview",
18+
"sourceResourceId": "/subscriptions/sourceSubscriptionId/resourceGroups/sourceResourceGroupName/providers/Microsoft.CognitiveServices/accounts/sourceSpeechResourceName",
19+
"expirationDateTime": "2019-01-07T11:34:12Z",
20+
"id": "d61573c6-788b-4eff-b3f5-38a1c7a9585b"
21+
}
22+
}
23+
}
24+
}
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,34 @@
1+
{
2+
"parameters": {
3+
"Endpoint": "https://westus.api.cognitive.microsoft.com/",
4+
"Ocp-Apim-Subscription-Key": "{API Key}",
5+
"api-version": "2024-05-15-preview",
6+
"dataset": {
7+
"kind": "Acoustic",
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+
"body": {
18+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1?api-version=2024-05-15-preview",
19+
"kind": "Acoustic",
20+
"links": {
21+
"files": "https://westus.api.cognitive.microsoft.com/speechtotext/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1?api-version=2024-05-15-preview/files?api-version=2024-05-15-preview",
22+
"commitBlocks": "https://westus.api.cognitive.microsoft.com/speechtotext/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1?api-version=2024-05-15-preview/blocks:commit?api-version=2024-05-15-preview",
23+
"listBlocks": "https://westus.api.cognitive.microsoft.com/speechtotext/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1?api-version=2024-05-15-preview/blocks?api-version=2024-05-15-preview",
24+
"uploadBlocks": "https://westus.api.cognitive.microsoft.com/speechtotext/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1?api-version=2024-05-15-preview/blocks?api-version=2024-05-15-preview"
25+
},
26+
"lastActionDateTime": "2019-01-07T11:36:07Z",
27+
"status": "NotStarted",
28+
"createdDateTime": "2019-01-07T11:34:12Z",
29+
"locale": "en-US",
30+
"displayName": "Acoustic dataset"
31+
}
32+
}
33+
}
34+
}
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,41 @@
1+
{
2+
"parameters": {
3+
"Endpoint": "https://westus.api.cognitive.microsoft.com/",
4+
"Ocp-Apim-Subscription-Key": "{API Key}",
5+
"api-version": "2024-05-15-preview",
6+
"dataset": {
7+
"kind": "Acoustic",
8+
"contentUrl": "https://contoso.com/location",
9+
"locale": "en-US",
10+
"displayName": "My speech dataset name",
11+
"description": "My speech dataset description"
12+
},
13+
"Content-Type": "application/json"
14+
},
15+
"responses": {
16+
"201": {
17+
"headers": {
18+
"Location": "https://westus.api.cognitive.microsoft.com/speechtotext/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1?api-version=2024-05-15-preview"
19+
},
20+
"body": {
21+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1?api-version=2024-05-15-preview",
22+
"kind": "Acoustic",
23+
"contentUrl": "https://www.contoso.com/acousticdata/sourcelocation",
24+
"links": {
25+
"files": "https://westus.api.cognitive.microsoft.com/speechtotext/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1/files?api-version=2024-05-15-preview"
26+
},
27+
"properties": {
28+
"textNormalizationKind": "Default",
29+
"acceptedLineCount": 11,
30+
"rejectedLineCount": 2,
31+
"duration": "PT4M12S"
32+
},
33+
"lastActionDateTime": "2019-01-07T11:36:07Z",
34+
"status": "Succeeded",
35+
"createdDateTime": "2019-01-07T11:34:12Z",
36+
"locale": "en-US",
37+
"displayName": "Acoustic dataset"
38+
}
39+
}
40+
}
41+
}
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,51 @@
1+
{
2+
"parameters": {
3+
"Endpoint": "https://westus.api.cognitive.microsoft.com/",
4+
"Ocp-Apim-Subscription-Key": "{API Key}",
5+
"api-version": "2024-05-15-preview",
6+
"endpoint": {
7+
"model": {
8+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/models/827712a5-f942-4997-91c3-7c6cde35600b?api-version=2024-05-15-preview"
9+
},
10+
"properties": {
11+
"loggingEnabled": true
12+
},
13+
"locale": "en-US",
14+
"displayName": "Speech endpoint definition",
15+
"description": "This is a speech endpoint"
16+
},
17+
"Content-Type": "application/json"
18+
},
19+
"responses": {
20+
"201": {
21+
"headers": {
22+
"Location": "https://westus.api.cognitive.microsoft.com/speechtotext/endpoints/afa0669c-a01e-4693-ae3a-93baf40f26d6?api-version=2024-05-15-preview"
23+
},
24+
"body": {
25+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/endpoints/afa0669c-a01e-4693-ae3a-93baf40f26d6?api-version=2024-05-15-preview",
26+
"model": {
27+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/models/827712a5-f942-4997-91c3-7c6cde35600b?api-version=2024-05-15-preview"
28+
},
29+
"links": {
30+
"logs": "https://westus.api.cognitive.microsoft.com/speechtotext/endpoints/afa0669c-a01e-4693-ae3a-93baf40f26d6/files/logs?api-version=2024-05-15-preview",
31+
"restInteractive": "https://westus.stt.speech.microsoft.com/speech/recognition/interactive/cognitiveservices/v1?cid=afa0669c-a01e-4693-ae3a-93baf40f26d6",
32+
"restConversation": "https://westus.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1?cid=afa0669c-a01e-4693-ae3a-93baf40f26d6",
33+
"restDictation": "https://westus.stt.speech.microsoft.com/speech/recognition/dictation/cognitiveservices/v1?cid=afa0669c-a01e-4693-ae3a-93baf40f26d6",
34+
"webSocketInteractive": "wss://westus.stt.speech.microsoft.com/speech/recognition/interactive/cognitiveservices/v1?cid=afa0669c-a01e-4693-ae3a-93baf40f26d6",
35+
"webSocketConversation": "wss://westus.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1?cid=afa0669c-a01e-4693-ae3a-93baf40f26d6",
36+
"webSocketDictation": "wss://westus.stt.speech.microsoft.com/speech/recognition/dictation/cognitiveservices/v1?cid=afa0669c-a01e-4693-ae3a-93baf40f26d6"
37+
},
38+
"properties": {
39+
"timeToLive": "PT30M",
40+
"loggingEnabled": true
41+
},
42+
"lastActionDateTime": "2019-01-07T11:36:07Z",
43+
"status": "Succeeded",
44+
"createdDateTime": "2019-01-07T11:34:12Z",
45+
"locale": "en-US",
46+
"displayName": "Speech endpoint",
47+
"description": "Example for speech endpoint"
48+
}
49+
}
50+
}
51+
}
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,117 @@
1+
{
2+
"parameters": {
3+
"Endpoint": "https://westus.api.cognitive.microsoft.com/",
4+
"Ocp-Apim-Subscription-Key": "{API Key}",
5+
"api-version": "2024-05-15-preview",
6+
"evaluation": {
7+
"model1": {
8+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/models/base/8a043172-65b7-4cf3-a8b5-4449efa5a0f1?api-version=2024-05-15-preview"
9+
},
10+
"model2": {
11+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/models/827712a5-f942-4997-91c3-7c6cde35600b?api-version=2024-05-15-preview"
12+
},
13+
"dataset": {
14+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1?api-version=2024-05-15-preview"
15+
},
16+
"locale": "en-US",
17+
"displayName": "My new evaluation",
18+
"description": "The description of the evaluation"
19+
},
20+
"Content-Type": "application/json"
21+
},
22+
"responses": {
23+
"201": {
24+
"headers": {
25+
"Location": "https://westus.api.cognitive.microsoft.com/speechtotext/evaluations/1c50ce42-6ab7-454f-8c39-54a752d1a5b6?api-version=2024-05-15-preview"
26+
},
27+
"body": {
28+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/evaluations/1c50ce42-6ab7-454f-8c39-54a752d1a5b6?api-version=2024-05-15-preview",
29+
"model1": {
30+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/models/base/8a043172-65b7-4cf3-a8b5-4449efa5a0f1?api-version=2024-05-15-preview"
31+
},
32+
"model2": {
33+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/models/827712a5-f942-4997-91c3-7c6cde35600b?api-version=2024-05-15-preview"
34+
},
35+
"dataset": {
36+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/datasets/9d5f4100-5f8e-4dd6-bd83-9bbbf50d57f1?api-version=2024-05-15-preview"
37+
},
38+
"transcription2": {
39+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/transcriptions/ad86d0c9-af6d-4d14-a621-c60d7d65b74f?api-version=2024-05-15-preview"
40+
},
41+
"transcription1": {
42+
"self": "https://westus.api.cognitive.microsoft.com/speechtotext/transcriptions/ba7ea6f5-3065-40b7-b49a-a90f48584683?api-version=2024-05-15-preview"
43+
},
44+
"links": {
45+
"files": "https://westus.api.cognitive.microsoft.com/speechtotext/evaluations/00000000-0000-0000-0000-000000000000/files?api-version=2024-05-15-preview"
46+
},
47+
"properties": {
48+
"wordErrorRate1": 0.065,
49+
"sentenceErrorRate1": 0.375,
50+
"tokenErrorRate1": 0.125,
51+
"sentenceCount1": 8,
52+
"wordCount1": 46,
53+
"correctWordCount1": 43,
54+
"wordSubstitutionCount1": 3,
55+
"wordDeletionCount1": 0,
56+
"wordInsertionCount1": 0,
57+
"tokenCount1": 48,
58+
"correctTokenCount1": 42,
59+
"tokenSubstitutionCount1": 6,
60+
"tokenDeletionCount1": 0,
61+
"tokenInsertionCount1": 0,
62+
"tokenErrors1": {
63+
"punctuation": {
64+
"numberOfEdits": 2,
65+
"percentageOfAllEdits": 0.66
66+
},
67+
"capitalization": {
68+
"numberOfEdits": 1,
69+
"percentageOfAllEdits": 0.33
70+
}
71+
},
72+
"wordErrorRate2": 0.065,
73+
"sentenceErrorRate2": 0.375,
74+
"tokenErrorRate2": 0.125,
75+
"sentenceCount2": 8,
76+
"wordCount2": 46,
77+
"correctWordCount2": 43,
78+
"wordSubstitutionCount2": 3,
79+
"wordDeletionCount2": 0,
80+
"wordInsertionCount2": 0,
81+
"tokenCount2": 48,
82+
"correctTokenCount2": 42,
83+
"tokenSubstitutionCount2": 6,
84+
"tokenDeletionCount2": 0,
85+
"tokenInsertionCount2": 0,
86+
"tokenErrors2": {
87+
"punctuation": {
88+
"numberOfEdits": 208,
89+
"percentageOfAllEdits": 1.22
90+
},
91+
"capitalization": {
92+
"numberOfEdits": 126,
93+
"percentageOfAllEdits": 0.74
94+
},
95+
"inverseTextNormalization": {
96+
"numberOfEdits": 409,
97+
"percentageOfAllEdits": 2.4
98+
},
99+
"lexical": {
100+
"numberOfEdits": 16284,
101+
"percentageOfAllEdits": 95.41
102+
},
103+
"others": {
104+
"numberOfEdits": 41,
105+
"percentageOfAllEdits": 0.24
106+
}
107+
}
108+
},
109+
"lastActionDateTime": "2019-01-07T11:36:07Z",
110+
"status": "Succeeded",
111+
"createdDateTime": "2019-01-07T11:34:12Z",
112+
"locale": "en-US",
113+
"displayName": "Evalution of one model against another model"
114+
}
115+
}
116+
}
117+
}

0 commit comments

Comments
 (0)