Skip to content

Commit c4087d1

Browse files
eric-urbaneric-urban
committed
initial stub saving progress
1 parent b1e4e11 commit c4087d1

File tree

7 files changed

+137
-131
lines changed

7 files changed

+137
-131
lines changed

‎articles/cognitive-services/Speech-Service/language-support.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -24,7 +24,7 @@ You can also get a list of locales and voices supported for each specific region
2424
Language support varies by Speech service functionality.
2525

2626
> [!NOTE]
27-
> See [Speech Containers](speech-container-howto.md#available-speech-containers) and [Embedded Speech](embedded-speech.md#models-and-voices) separately for their supported languages.
27+
> See [Speech Containers](speech-container-overview.md#available-speech-containers) and [Embedded Speech](embedded-speech.md#models-and-voices) separately for their supported languages.
2828
2929
**Choose a Speech feature**
3030

‎articles/cognitive-services/Speech-Service/speech-container-cstt.md

Lines changed: 2 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -39,7 +39,7 @@ The fully qualified container image name is, `mcr.microsoft.com/azure-cognitive-
3939
All tags, except for `latest`, are in the following format and are case sensitive:
4040

4141
```
42-
<major>.<minor>.<patch>-<platform>
42+
<major>.<minor>.<patch>-<platform>-<prerelease>
4343
```
4444

4545
> [!NOTE]
@@ -211,8 +211,7 @@ ApiKey={API_KEY}
211211

212212
You can get custom pronunciation results in the output. All you need to do is have your own custom pronunciation rules set up in your custom model and mount the model to a custom-speech-to-text container.
213213

214-
> [!IMPORTANT]
215-
> The `Eula`, `Billing`, and `ApiKey` options must be specified to run the container. Otherwise, the container won't start. For more information, see [billing arguments](speech-container-howto.md#billing-arguments).
214+
216215

217216

218217
## Use the container

‎articles/cognitive-services/Speech-Service/speech-container-howto.md

Lines changed: 12 additions & 41 deletions
Original file line numberDiff line numberDiff line change
@@ -20,22 +20,6 @@ By using containers, you can use a subset of the Speech service features in your
2020
> [!NOTE]
2121
> Connected and disconnected container pricing and commitment tiers vary. For more information, see [Speech Services pricing](https://azure.microsoft.com/pricing/details/cognitive-services/speech-services/).
2222
23-
## Available Speech containers
24-
25-
The following table lists the Speech containers available in the Microsoft Container Registry (MCR). The table also lists the features supported by each container and the latest version of the container.
26-
27-
> [!NOTE]
28-
> You must [request and get approval](speech-container-overview.md#request-approval-to-run-the-container) to use a Speech container.
29-
30-
| Container | Features | Supported versions and locales |
31-
|--|--|--|
32-
| [Speech-to-text](speech-container-stt.md) | Analyzes sentiment and transcribes continuous real-time speech or batch audio recordings with intermediate results. | Latest: 3.12.0<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).|
33-
| [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: 3.12.0<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). |
34-
| [Speech language identification](speech-container-lid.md)<sup>1, 2</sup> | Detects the language spoken in audio files. | Latest: 1.11.0<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). |
35-
| [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: 2.11.0<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). |
36-
37-
<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.
38-
<sup>2</sup> Only available as a connected container. A disconnected container isn't generally available.
3923

4024
## Prerequisites
4125

@@ -51,8 +35,6 @@ You must meet the following prerequisites before you use Speech service containe
5135

5236
Speech containers aren't licensed to run without being connected to Azure for metering. You must configure your container to communicate billing information with the metering service at all times.
5337

54-
55-
5638
Three primary parameters for all Cognitive Services containers are required. The Microsoft Software License Terms must be present with a value of **accept**. An Endpoint URI and API key are also needed.
5739

5840
Queries to the container are billed at the pricing tier of the Azure resource that's used for the `ApiKey` parameter.
@@ -119,39 +101,30 @@ grep -q avx2 /proc/cpuinfo && echo AVX2 supported || echo No AVX2 support detect
119101

120102
## Run the container
121103

122-
> [!IMPORTANT]
123-
> The `Eula`, `Billing`, and `ApiKey` options must be specified to run the container; otherwise, the container won't start. For more information, see [Billing](speech-container-configuration.md#billing-configuration-setting).
124-
> The ApiKey value is the **Key** from the Azure Speech Resource keys page.
104+
Use the [docker run](https://docs.docker.com/engine/reference/commandline/run/) command to run the container. Once running, the container continues to run until you [stop the container](#stop-the-container).
125105

126-
The following examples use the configuration settings to illustrate how to write and use `docker run` commands. Once running, the container continues to run until you [stop the container](#stop-the-container).
106+
Take note the following best practices with the `docker run` command:
127107

128108
- **Line-continuation character**: The Docker commands in the following sections use the back slash, `\`, as a line continuation character. Replace or remove this based on your host operating system's requirements.
129109
- **Argument order**: Do not change the order of the arguments unless you are familiar with Docker containers.
130110

131-
Replace {_argument_name_} with your own values:
132-
133-
| Placeholder | Value | Format or example |
134-
| ----------- | ----- | ----------------- |
135-
| **{API_KEY}** | The endpoint key of the `Speech` resource on the Azure `Speech` Keys page. | `xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx`|
136-
| **{ENDPOINT_URI}** | The billing endpoint value is available on the Azure `Speech` Overview page. | See [gather required parameters](speech-container-howto.md#gather-required-parameters) for explicit examples. |
137-
111+
You can use the [docker images](https://docs.docker.com/engine/reference/commandline/images/) command to list your downloaded container images. The following command lists the ID, repository, and tag of each downloaded container image, formatted as a table:
138112

139-
> [!TIP]
140-
> You can use the [docker images](https://docs.docker.com/engine/reference/commandline/images/) command to list your downloaded container images.
141-
142-
The following command lists the ID, repository, and tag of each downloaded container image, formatted as a table:
143-
144-
```
113+
```bash
145114
docker images --format "table {{.ID}}\t{{.Repository}}\t{{.Tag}}"
115+
```
146116

117+
Here's an example result:
118+
```
147119
IMAGE ID REPOSITORY TAG
148120
<image-id> <repository-path/name> <tag-name>
149121
```
150122

151-
152123
## Validate that a container is running
153124

154-
There are several ways to validate that the container is running. Locate the *External IP* address and exposed port of the container in question, and open your favorite web browser. Use the various request URLs that follow to validate the container is running. The example request URLs listed here are `http://localhost:5000`, but your specific container might vary. Make sure to rely on your container's *External IP* address and exposed port.
125+
There are several ways to validate that the container is running. Locate the *External IP* address and exposed port of the container in question, and open your favorite web browser. Use the various request URLs that follow to validate the container is running.
126+
127+
The example request URLs listed here are `http://localhost:5000`, but your specific container might vary. Make sure to rely on your container's *External IP* address and exposed port.
155128

156129
| Request URL | Purpose |
157130
|--|--|
@@ -160,13 +133,11 @@ There are several ways to validate that the container is running. Locate the *Ex
160133
| `http://localhost:5000/status` | Also requested with GET, this URL verifies if the api-key used to start the container is valid without causing an endpoint query. This request can be used for Kubernetes [liveness and readiness probes](https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-probes/). |
161134
| `http://localhost:5000/swagger` | The container provides a full set of documentation for the endpoints and a **Try it out** feature. With this feature, you can enter your settings into a web-based HTML form and make the query without having to write any code. After the query returns, an example CURL command is provided to demonstrate the HTTP headers and body format that's required. |
162135

163-
164136
## Stop the container
165137

166138
To shut down the container, in the command-line environment where the container is running, select <kbd>Ctrl+C</kbd>.
167139

168-
169-
### Run multiple containers on the same host
140+
## Run multiple containers on the same host
170141

171142
If you intend to run multiple containers with exposed ports, make sure to run each container with a different exposed port. For example, run the first container on port 5000 and the second container on port 5001.
172143

@@ -228,7 +199,7 @@ ApiKey={API_KEY}
228199

229200
The container will test for network connectivity to the billing endpoint.
230201

231-
## Run the container disconnected from the internet
202+
## Run disconnected containers
232203

233204
Tu run disconnected containers (not connected to the internet), you must submit [this request form](https://aka.ms/csdisconnectedcontainers) and wait for approval. For more information about applying and purchasing a commitment plan to use containers in disconnected environments, see [Use containers in disconnected environments](../containers/disconnected-containers.md#request-access-to-use-containers-in-disconnected-environments).
234205

‎articles/cognitive-services/Speech-Service/speech-container-lid.md

Lines changed: 52 additions & 31 deletions
Original file line numberDiff line numberDiff line change
@@ -16,59 +16,80 @@ keywords: on-premises, Docker, container
1616

1717
# Language identification containers with Docker
1818

19-
By using containers, you can run _some_ of the Azure Cognitive Services Speech service APIs in your own environment. Containers are great for specific security and data governance requirements. In this article, you'll learn how to download, install, and run a Speech container.
19+
The Speech language identification container detects the language spoken in audio files. You can get real-time speech or batch audio recordings with intermediate results. In this article, you'll learn how to download, install, and run a language identification container.
2020

2121
> [!NOTE]
22-
> You must [request and get approval](speech-container-overview.md#request-approval-to-run-the-container) to use a Speech container.
22+
> The Speech language identification container is available in public preview. Containers in preview are still under development and don't meet Microsoft's stability and support requirements.
2323
24-
## Available Speech containers
24+
> [!TIP]
25+
> To get the most useful results, use the Speech language identification container with the [speech-to-text](speech-container-stt.md) or [custom speech-to-text](speech-container-cstt.md) containers.
2526
26-
Detects the language spoken in audio files.
27+
> [!NOTE]
28+
> You must [request and get approval](speech-container-overview.md#request-approval-to-run-the-container) to use a Speech container.
2729
28-
Latest: 1.11.0. 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).
30+
For more information about prerequisites, validating that a container is running, running multiple containers on the same host, and running disconnected containers, see [Install and run Speech containers with Docker](speech-container-howto.md).
2931

30-
The container is available in public preview. Containers in preview are still under development and don't meet Microsoft's stability and support requirements.
32+
## Container images
3133

32-
You need the [prerequisites](speech-container-howto.md#prerequisites).
34+
The Speech language identification container image for all supported versions and locales can be found on the [Microsoft Container Registry (MCR)](https://mcr.microsoft.com/product/azure-cognitive-services/speechservices/language-detection/tags) syndicate. It resides within the `azure-cognitive-services/speechservices/` repository and is named `language-detection`.
3335

36+
:::image type="content" source="./media/containers/mcr-tags-language-detection.png" alt-text="A screenshot of the search connectors and triggers dialog." lightbox="./media/containers/mcr-tags-language-detection.png":::
3437

35-
## Speech container images
38+
The fully qualified container image name is, `mcr.microsoft.com/azure-cognitive-services/speechservices/language-detection`. Either append a specific version or append `:latest` to get the most recent version.
3639

37-
The Speech language detection container image can be found on the `mcr.microsoft.com` container registry syndicate. It resides within the `azure-cognitive-services/speechservices/` repository and is named `language-detection`. The fully qualified container image name is, `mcr.microsoft.com/azure-cognitive-services/speechservices/language-detection`.
40+
| Version | Path |
41+
|-----------|------------|
42+
| Latest | `mcr.microsoft.com/azure-cognitive-services/speechservices/language-detection:latest` |
43+
| 3.12.0 | `mcr.microsoft.com/azure-cognitive-services/speechservices/language-detection:1.11.0-amd64-preview` |
3844

39-
To use the latest version of the container, you can use the `latest` tag. You can also find a full list of [tags on the MCR](https://mcr.microsoft.com/product/azure-cognitive-services/speechservices/language-detection/tags).
45+
All tags, except for `latest`, are in the following format and are case sensitive:
4046

41-
> [!TIP]
42-
> To get the most useful results, use the Speech language identification container with the speech-to-text or custom speech-to-text containers.
47+
```
48+
<major>.<minor>.<patch>-<platform>-<prerelease>
49+
```
4350

44-
| Container | Repository |
45-
|-----------|------------|
46-
| Speech language identification | `mcr.microsoft.com/azure-cognitive-services/speechservices/language-detection:latest` |
51+
The tags are also available [in JSON format](https://mcr.microsoft.com/v2/azure-cognitive-services/speechservices/language-detection/tags/list) for your convenience. The body includes the container path and list of tags. The tags aren't sorted by version, but `"latest"` is always included at the end of the list as shown in this snippet:
52+
53+
```json
54+
{
55+
"name": "azure-cognitive-services/speechservices/language-detection",
56+
"tags": [
57+
"1.1.0-amd64-preview",
58+
"1.11.0-amd64-preview",
59+
"1.3.0-amd64-preview",
60+
"1.5.0-amd64-preview",
61+
<--redacted for brevity-->
62+
"1.8.0-amd64-preview",
63+
"latest"
64+
]
65+
}
66+
```
4767

68+
## Get the container image with docker pull
4869

49-
### Get the container image with docker pull
70+
You need the [prerequisites](speech-container-howto.md#prerequisites).
5071

5172
Use the [docker pull](https://docs.docker.com/engine/reference/commandline/pull/) command to download a container image from Microsoft Container Registry:
5273

5374
```bash
5475
docker pull mcr.microsoft.com/azure-cognitive-services/speechservices/language-detection:latest
5576
```
5677

57-
## Use the container
5878

59-
After the container is on the [host computer](#host-computer-requirements-and-recommendations), use the following process to work with the container.
79+
## Run the container with docker run
6080

61-
1. [Run the container](#run-the-container-with-docker-run) with the required billing settings. More [examples](speech-container-configuration.md#example-docker-run-commands) of the `docker run` command are available.
62-
1. [Query the container's prediction endpoint](#query-the-containers-prediction-endpoint).
81+
Use the [docker run](https://docs.docker.com/engine/reference/commandline/run/) command to run the container.
6382

64-
## Run the container with docker run
83+
The following table represents the various `docker run` parameters and their corresponding descriptions:
6584

66-
Use the [docker run](https://docs.docker.com/engine/reference/commandline/run/) command to run the container. For more information on how to get the `{Endpoint_URI}` and `{API_Key}` values, see [Gather required parameters](#gather-required-parameters). More [examples](speech-container-configuration.md#example-docker-run-commands) of the `docker run` command are also available.
85+
| Parameter | Description |
86+
|---------|---------|
87+
| `{ENDPOINT_URI}` | The endpoint is required for metering and billing. For more information, see [billing arguments](speech-container-howto.md#billing-arguments). |
88+
| `{API_KEY}` | The API key is required. For more information, see [billing arguments](speech-container-howto.md#billing-arguments). |
6789

68-
> [!NOTE]
69-
> For general container requirements, see [Container requirements and recommendations](#container-requirements-and-recommendations).
90+
When you run the Speech language identification container, configure the port, memory, and CPU according to the language identification container [requirements and recommendations](speech-container-howto.md#container-requirements-and-recommendations).
7091

71-
To run the Speech language identification container, execute the following `docker run` command:
92+
Here's an example `docker run` command with placeholder values. You must specify the `ENDPOINT_URI` and `API_KEY` values:
7293

7394
```bash
7495
docker run --rm -it -p 5003:5003 --memory 1g --cpus 1 \
@@ -80,23 +101,23 @@ ApiKey={API_KEY}
80101

81102
This command:
82103

83-
* Runs a Speech language-detection container from the container image. Currently, you won't be charged for running this image.
104+
* Runs a Speech language identification container from the container image.
84105
* Allocates 1 CPU core and 1 GB of memory.
85106
* Exposes TCP port 5003 and allocates a pseudo-TTY for the container.
86107
* Automatically removes the container after it exits. The container image is still available on the host computer.
87108

88-
If you want to run this container with the speech-to-text container, you can use this [docker image](https://hub.docker.com/r/antsu/on-prem-client). After both containers have been started, use this `docker run` command to execute `speech-to-text-with-languagedetection-client`:
109+
More [examples](speech-container-configuration.md#example-docker-run-commands) of the `docker run` command are also available.
110+
111+
## Run with the speech-to-text container
112+
113+
If you want to run the language identification container with the [speech-to-text](speech-container-stt.md) container, you can use this [docker image](https://hub.docker.com/r/antsu/on-prem-client). After both containers have been started, use this `docker run` command to execute `speech-to-text-with-languagedetection-client`:
89114

90115
```bash
91116
docker run --rm -v ${HOME}:/root -ti antsu/on-prem-client:latest ./speech-to-text-with-languagedetection-client ./audio/LanguageDetection_en-us.wav --host localhost --lport 5003 --sport 5000
92117
```
93118

94119
Increasing the number of concurrent calls can affect reliability and latency. For language identification, we recommend a maximum of four concurrent calls using 1 CPU with 1 GB of memory. For hosts with 2 CPUs and 2 GB of memory, we recommend a maximum of six concurrent calls.
95120

96-
> [!IMPORTANT]
97-
> The `Eula`, `Billing`, and `ApiKey` options must be specified to run the container. Otherwise, the container won't start. For more information, see [Billing](#billing).
98-
99-
100121

101122
## Use the container
102123

0 commit comments

Comments
 (0)