Skip to content

Commit f947d94

Browse files
eric-urbaneric-urban
committed
speech containers release notes
1 parent 2313b9f commit f947d94

File tree

6 files changed

+50
-34
lines changed

6 files changed

+50
-34
lines changed

‎articles/ai-services/speech-service/includes/release-notes/release-notes-containers.md‎

Lines changed: 16 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -2,17 +2,31 @@
22
author: eric-urban
33
ms.service: azure-ai-speech
44
ms.topic: include
5-
ms.date: 9/17/2024
5+
ms.date: 10/21/2024
66
ms.author: eur
77
---
88

9+
10+
### 2024-October release
11+
12+
Add support for the latest model versions:
13+
- Speech language identification 1.16.0
14+
- Neural text to speech 3.5.0
15+
- Make `en-us-ariacpuneural` an alias to `en-us-jessacpuneural`
16+
- Update the text to speech backend engine version
17+
- Speech to text 4.10.0
18+
- Restore support for locale `uk-UA`
19+
- Fix silence settings to work with long periods of silence in the audio
20+
- Replace deprecated models: `cs-CZ`, `da-DK`, `en-GB`, `fr-CA`, `hu-HU`, `it-CH`, `tr-TR`, `zh-CN-sichuan`
21+
- Custom speech to text 4.10.0
22+
923
### 2024-September release
1024

1125
Add support for the latest model versions:
1226
- Speech language identification 1.15.0
1327
- Mitigate Vulnerabilities
1428
- Neural text to speech 3.4.0
15-
- New voices: `en-us-andrewmultilingualneural`, `en-us-jessaneural`, `es-us-alonsoneural`, `es-us-palomaneural`, `it-it-isabellamultilingualneural`
29+
- New voices: `en-us-andrewmultilingualneural`, `en-us-jessaneural`, `es-us-alonsoneural`, `es-us-palomaneural`, `it-it-isabellamultilingualneural`
1630
- Mitigate Vulnerabilities
1731
- Speech to text 4.9.0
1832
- New Locales: `ar-YE`, `af-ZA`, `am-ET`, `ar-MA`, `ar-TN`, `sw-KE`, `sw-TZ`, `zu-ZA`

‎articles/ai-services/speech-service/speech-container-cstt.md‎

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -30,7 +30,7 @@ The fully qualified container image name is, `mcr.microsoft.com/azure-cognitive-
3030
| Version | Path |
3131
|-----------|------------|
3232
| Latest | `mcr.microsoft.com/azure-cognitive-services/speechservices/custom-speech-to-text:latest` |
33-
| 4.9.0 | `mcr.microsoft.com/azure-cognitive-services/speechservices/custom-speech-to-text:4.9.0-amd64` |
33+
| 4.10.0 | `mcr.microsoft.com/azure-cognitive-services/speechservices/custom-speech-to-text:4.10.0-amd64` |
3434

3535
All tags, except for `latest`, are in the following format and are case sensitive:
3636

@@ -54,6 +54,7 @@ The tags are also available [in JSON format](https://mcr.microsoft.com/v2/azure-
5454
"4.7.0-amd64",
5555
"4.8.0-amd64",
5656
"4.9.0-amd64",
57+
"4.10.0-amd64",
5758
"latest"
5859
]
5960
}

‎articles/ai-services/speech-service/speech-container-lid.md‎

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -37,7 +37,7 @@ The fully qualified container image name is, `mcr.microsoft.com/azure-cognitive-
3737
| Version | Path |
3838
|-----------|------------|
3939
| Latest | `mcr.microsoft.com/azure-cognitive-services/speechservices/language-detection:latest` |
40-
| 1.15.0 | `mcr.microsoft.com/azure-cognitive-services/speechservices/language-detection:1.15.0-amd64-preview` |
40+
| 1.16.0 | `mcr.microsoft.com/azure-cognitive-services/speechservices/language-detection:1.16.0-amd64-preview` |
4141

4242
All tags, except for `latest`, are in the following format and are case sensitive:
4343

@@ -57,6 +57,7 @@ The tags are also available [in JSON format](https://mcr.microsoft.com/v2/azure-
5757
"1.13.0-amd64-preview",
5858
"1.14.0-amd64-preview",
5959
"1.15.0-amd64-preview",
60+
"1.16.0-amd64-preview",
6061
"1.3.0-amd64-preview",
6162
"1.5.0-amd64-preview",
6263
"1.6.1-amd64-preview",

‎articles/ai-services/speech-service/speech-container-ntts.md‎

Lines changed: 14 additions & 14 deletions
Original file line numberDiff line numberDiff line change
@@ -31,7 +31,7 @@ The fully qualified container image name is, `mcr.microsoft.com/azure-cognitive-
3131
| Version | Path |
3232
|-----------|------------|
3333
| Latest | `mcr.microsoft.com/azure-cognitive-services/speechservices/neural-text-to-speech:latest`<br/><br/>The `latest` tag pulls the `en-US` locale and `en-us-arianeural` voice. |
34-
| 3.4.0 | `mcr.microsoft.com/azure-cognitive-services/speechservices/neural-text-to-speech:3.4.0-amd64-en-us-arianeural` |
34+
| 3.5.0 | `mcr.microsoft.com/azure-cognitive-services/speechservices/neural-text-to-speech:3.5.0-amd64-en-us-arianeural` |
3535

3636
All tags, except for `latest`, are in the following format and are case sensitive:
3737

@@ -46,19 +46,19 @@ The tags are also available [in JSON format](https://mcr.microsoft.com/v2/azure-
4646
"name": "azure-cognitive-services/speechservices/neural-text-to-speech",
4747
"tags": [
4848
<--redacted for brevity-->
49-
"3.4.0-amd64-uk-ua-ostapneural",
50-
"3.4.0-amd64-zh-cn-xiaochenneural-preview",
51-
"3.4.0-amd64-zh-cn-xiaohanneural",
52-
"3.4.0-amd64-zh-cn-xiaomoneural",
53-
"3.4.0-amd64-zh-cn-xiaoqiuneural-preview",
54-
"3.4.0-amd64-zh-cn-xiaoruineural",
55-
"3.4.0-amd64-zh-cn-xiaoshuangneural-preview",
56-
"3.4.0-amd64-zh-cn-xiaoxiaoneural",
57-
"3.4.0-amd64-zh-cn-xiaoyanneural-preview",
58-
"3.4.0-amd64-zh-cn-xiaoyouneural",
59-
"3.4.0-amd64-zh-cn-yunxineural",
60-
"3.4.0-amd64-zh-cn-yunyangneural",
61-
"3.4.0-amd64-zh-cn-yunyeneural",
49+
"3.5.0-amd64-uk-ua-ostapneural",
50+
"3.5.0-amd64-zh-cn-xiaochenneural-preview",
51+
"3.5.0-amd64-zh-cn-xiaohanneural",
52+
"3.5.0-amd64-zh-cn-xiaomoneural",
53+
"3.5.0-amd64-zh-cn-xiaoqiuneural-preview",
54+
"3.5.0-amd64-zh-cn-xiaoruineural",
55+
"3.5.0-amd64-zh-cn-xiaoshuangneural-preview",
56+
"3.5.0-amd64-zh-cn-xiaoxiaoneural",
57+
"3.5.0-amd64-zh-cn-xiaoyanneural-preview",
58+
"3.5.0-amd64-zh-cn-xiaoyouneural",
59+
"3.5.0-amd64-zh-cn-yunxineural",
60+
"3.5.0-amd64-zh-cn-yunyangneural",
61+
"3.5.0-amd64-zh-cn-yunyeneural",
6262
"latest"
6363
]
6464
}

‎articles/ai-services/speech-service/speech-container-overview.md‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -22,10 +22,10 @@ The following table lists the Speech containers available in the Microsoft Conta
2222

2323
| Container | Features | Supported versions and locales |
2424
|--|--|--|
25-
| [Speech to text](speech-container-stt.md) | Transcribes continuous real-time speech or batch audio recordings with intermediate results. | Latest: 4.9.0<br/><br/>For all supported versions and locales, see the [Microsoft Container Registry (MCR)](https://mcr.microsoft.com/product/azure-cognitive-services/speechservices/speech-to-text/tags) and [JSON tags](https://mcr.microsoft.com/v2/azure-cognitive-services/speechservices/speech-to-text/tags/list).|
25+
| [Speech to text](speech-container-stt.md) | Transcribes continuous real-time speech or batch audio recordings with intermediate results. | Latest: 4.10.0<br/><br/>For all supported versions and locales, see the [Microsoft Container Registry (MCR)](https://mcr.microsoft.com/product/azure-cognitive-services/speechservices/speech-to-text/tags) and [JSON tags](https://mcr.microsoft.com/v2/azure-cognitive-services/speechservices/speech-to-text/tags/list).|
2626
| [Custom speech to text](speech-container-cstt.md) | Using a custom model from the [custom speech portal](https://speech.microsoft.com/customspeech), transcribes continuous real-time speech or batch audio recordings into text with intermediate results. | Latest: 4.8.0<br/><br/>For all supported versions and locales, see the [Microsoft Container Registry (MCR)](https://mcr.microsoft.com/product/azure-cognitive-services/speechservices/custom-speech-to-text/tags) and [JSON tags](https://mcr.microsoft.com/v2/azure-cognitive-services/speechservices/speech-to-text/tags/list). |
27-
| [Speech language identification](speech-container-lid.md)<sup>1, 2</sup> | Detects the language spoken in audio files. | Latest: 1.15.0<br/><br/>For all supported versions and locales, see the [Microsoft Container Registry (MCR)](https://mcr.microsoft.com/product/azure-cognitive-services/speechservices/language-detection/tags) and [JSON tags](https://mcr.microsoft.com/v2/azure-cognitive-services/speechservices/language-detection/tags/list). |
28-
| [Neural text to speech](speech-container-ntts.md) | Converts text to natural-sounding speech by using deep neural network technology, which allows for more natural synthesized speech. | Latest: 3.4.0<br/><br/>For all supported versions and locales, see the [Microsoft Container Registry (MCR)](https://mcr.microsoft.com/product/azure-cognitive-services/speechservices/neural-text-to-speech/tags) and [JSON tags](https://mcr.microsoft.com/v2/azure-cognitive-services/speechservices/neural-text-to-speech/tags/list). |
27+
| [Speech language identification](speech-container-lid.md)<sup>1, 2</sup> | Detects the language spoken in audio files. | Latest: 1.16.0<br/><br/>For all supported versions and locales, see the [Microsoft Container Registry (MCR)](https://mcr.microsoft.com/product/azure-cognitive-services/speechservices/language-detection/tags) and [JSON tags](https://mcr.microsoft.com/v2/azure-cognitive-services/speechservices/language-detection/tags/list). |
28+
| [Neural text to speech](speech-container-ntts.md) | Converts text to natural-sounding speech by using deep neural network technology, which allows for more natural synthesized speech. | Latest: 3.5.0<br/><br/>For all supported versions and locales, see the [Microsoft Container Registry (MCR)](https://mcr.microsoft.com/product/azure-cognitive-services/speechservices/neural-text-to-speech/tags) and [JSON tags](https://mcr.microsoft.com/v2/azure-cognitive-services/speechservices/neural-text-to-speech/tags/list). |
2929

3030
<sup>1</sup> The container is available in public preview. Containers in preview are still under development and don't meet Microsoft's stability and support requirements.
3131
<sup>2</sup> Not available as a disconnected container.

‎articles/ai-services/speech-service/speech-container-stt.md‎

Lines changed: 13 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -31,7 +31,7 @@ The fully qualified container image name is, `mcr.microsoft.com/azure-cognitive-
3131
| Version | Path |
3232
|-----------|------------|
3333
| Latest | `mcr.microsoft.com/azure-cognitive-services/speechservices/speech-to-text:latest`<br/><br/>The `latest` tag pulls the latest image for the `en-US` locale. |
34-
| 4.9.0 | `mcr.microsoft.com/azure-cognitive-services/speechservices/speech-to-text:4.9.0-amd64-mr-in` |
34+
| 4.10.0 | `mcr.microsoft.com/azure-cognitive-services/speechservices/speech-to-text:4.10.0-amd64-mr-in` |
3535

3636
All tags, except for `latest`, are in the following format and are case sensitive:
3737

@@ -46,18 +46,18 @@ The tags are also available [in JSON format](https://mcr.microsoft.com/v2/azure-
4646
"name": "azure-cognitive-services/speechservices/speech-to-text",
4747
"tags": [
4848
<--redacted for brevity-->
49-
"4.9.0-amd64-sw-tz",
50-
"4.9.0-amd64-ta-in",
51-
"4.9.0-amd64-th-th",
52-
"4.9.0-amd64-tr-tr",
53-
"4.9.0-amd64-vi-vn",
54-
"4.9.0-amd64-wuu-cn",
55-
"4.9.0-amd64-yue-cn",
56-
"4.9.0-amd64-zh-cn",
57-
"4.9.0-amd64-zh-cn-sichuan",
58-
"4.9.0-amd64-zh-hk",
59-
"4.9.0-amd64-zh-tw",
60-
"4.9.0-amd64-zu-za",
49+
"4.10.0-amd64-sw-tz",
50+
"4.10.0-amd64-ta-in",
51+
"4.10.0-amd64-th-th",
52+
"4.10.0-amd64-tr-tr",
53+
"4.10.0-amd64-vi-vn",
54+
"4.10.0-amd64-wuu-cn",
55+
"4.10.0-amd64-yue-cn",
56+
"4.10.0-amd64-zh-cn",
57+
"4.10.0-amd64-zh-cn-sichuan",
58+
"4.10.0-amd64-zh-hk",
59+
"4.10.0-amd64-zh-tw",
60+
"4.10.0-amd64-zu-za",
6161
"latest"
6262
]
6363
}

0 commit comments

Comments
 (0)