Skip to main content

Accessing Images

Transcription:BatchReal-TimeDeployments:Container

Prerequisites

The Speechmatics Docker images are obtained from the Speechmatics Docker Repository. If you do not have a Speechmatics Docker Repository account or have lost your details, please reach out to Support.

The latest information about the Containers can be found in the knowledgebase section of the Support Portal. If a support account is not available or the Containers section is not visible in the Support Portal, please reach out to Support for help.

Prior to pulling any Docker images, the following must be known:

  • Speechmatics Docker credentials – provided by the Speechmatics team
  • Language Code – the ISO language code (for example fr for French)
  • LICENSE_TOKEN - The value of the signed claims token which is used to validate the license file. This is required to run the Container. Speechmatics Support will provide this within the license file generated for each customer
  • TAG – which is used to identify the image version

Software Repository Login

Ensure the Speechmatics Docker URL and Software Repository username and password are available. The endpoint being used will require Docker to be installed. For example:

docker login https://speechmatics-docker-public.jfrog.io

You will be prompted for username and password. If successful, you will see the response:

Login Succeeded

If unsuccessful, please verify your credentials and URL. If problems persist, please contact Speechmatics Support.

info

Speechmatics require all customers to cache a copy of the Docker image(s) within their own environment. Please do not pull directly from the Speechmatics Software Repository for each deployment.

Pulling Core Speech CPU Images

Each supported language pack comes as a different Docker image, so the process will need to be repeated for each language pack required using the relevant language code.

# pulling Batch Global English (en) with the 11.0.1 tag:
docker pull speechmatics-docker-public.jfrog.io/batch-asr-transcriber-en:11.0.1

# pulling the Batch Spanish (es) model with the 11.0.1 tag:
docker pull speechmatics-docker-public.jfrog.io/batch-asr-transcriber-es:11.0.1

# pulling Real-Time Global English (en) with the 11.0.1 tag:
docker pull speechmatics-docker-public.jfrog.io/rt-asr-transcriber-en:11.0.1

See how to run the Core Speech CPU container here.

Pulling Transcription GPU Images

Standard Operating Point

The Transcription GPU images are required to use the latest models and provide the highest accuracy transcription.

There is a single image available that supports all languages for the Standard Operating Point. There are language specific images available that support the Enhanced and Standard Operating Point.

info

To access additional language configurations for the Enhanced Operating Point, please reach out to our Support team by raising a ticket

# pulling the Standard operating point Transcription GPU inference server which supports all languages with the 11.0.1 tag:
docker pull speechmatics-docker-public.jfrog.io/sm-gpu-inference-server-standard-all:11.0.1

# pulling language specific Transcription GPU inference servers available for en, es, de, fr. Supports both Enhanced and Standard operating points with the 11.0.1 tag:
docker pull speechmatics-docker-public.jfrog.io/sm-gpu-inference-server-en:11.0.1

Enhanced Operating Point

Depending on which Enhanced Operating Point languages are required, you can pull specific images.

Language Pack 1
Bashkir, Basque, English, Esperanto, Marathi, Mongolian, Tamil, Turkish, Ukrainian, Uyghur, Welsh
docker pull speechmatics-docker-public.jfrog.io/sm-gpu-inference-server-enhanced-recipe1:11.0.1 
Language Pack 2
Bulgarian, Croatian, Estonian, Galician, Indonesian, Interlingua, Latvian, Lithuanian, Persian, Romanian, Slovakian, Slovenian, Spanish
docker pull speechmatics-docker-public.jfrog.io/sm-gpu-inference-server-enhanced-recipe2:11.0.1 
Language Pack 3
Catalan, Czech, Danish, Finnish, German, Greek, Hindi, Hungarian, Italian, Korean, Malay, Swedish
docker pull speechmatics-docker-public.jfrog.io/sm-gpu-inference-server-enhanced-recipe3:11.0.1 
Language Pack 4
Arabic, Cantonese, Dutch, French, Japanese, Mandarin, Norwegian, Polish, Portuguese, Russian, Thai, Vietnamese
docker pull speechmatics-docker-public.jfrog.io/sm-gpu-inference-server-enhanced-recipe4:11.0.1 

See how to run the Transcription GPU container here.

Pulling Translation GPU Image

This GPU image is required to use Translation in Batch or Real-Time.

# pulling the Translation GPU inference server which supports all translation pairs with the 11.0.1 tag:
docker pull speechmatics-docker-public.jfrog.io/sm-translation-inference-server:11.0.1

See how to run the Translation GPU container here.

Pulling Bilingual Images

To use Spanish and English bilingual transcription you need to pull the Core Speech CPU image below for the client and use the Spanish GPU Inference Server.

# pulling Batch bilingual Spanish and English with the 11.0.1 tag:
docker pull speechmatics-docker-public.jfrog.io/batch-asr-transcriber-es-bilingual-en:11.0.1

# pulling Real-Time bilingual Spanish and English with the 11.0.1 tag:
docker pull speechmatics-docker-public.jfrog.io/rt-asr-transcriber-es-bilingual-en:11.0.1
info

Bilingual is only available for GPU deployments. Batch and Real-Time are supported.

Pulling Language ID Image

This image is required to use Language ID.

# pulling the latest Language ID image:
docker pull speechmatics-docker-public.jfrog.io/langid:2.2.1

See how to run the Language ID container here.

As of Feb 2021, all Speechmatics Containers are built using Docker Buildkit. This should not impact your internal management of the Speechmatics Container. If you use JFrog to host the Speechmatics container there may be some UI issues see here, but these are cosmetic and should not impact your ability to pull and run the Container. If your internal registry uses Nexus and self-signed certificates, please make sure you are on Nexus version 3.15 or above or you may encounter errors.