Accessing the files
The IBM Entitled Registry provides access to the IBM Watson Speech to Text Library for Embed images. Once you've obtained the entitlement key from the container software library, you can login to the registry with the key to pull the images.
Prerequisites
- Docker version 18.06.0 or greater
Getting the Docker image
Once you have obtained your IBM Entitled Registry entitlement key, run the following command to allow Docker to access the images.
docker login cp.icr.io --username cp --password <entitlement_key>
Watson Speech to Text for Embed images
The Speech to Text runtime images are:
| Container Image | Image Digest |
|---|---|
| cp.icr.io/cp/ai/watson-stt-runtime:1.12.0 | sha256: digest: sha256:7d1dc56ccaf38b73d57e25430515b869c8435fa81fa0db28576f5ccb465a64b0 |
| cp.icr.io/cp/ai/watson-stt-haproxy:1.12.0 | sha256:99cd91f0633e3e583eebb53126f39d4fddfec33efe6a808d5c207d34fcd76cd0 |
| cp.icr.io/cp/ai/watson-stt-customization:1.12.0 | sha256:3703139fd7992c767d3e06a63d3a3f02d9ff62a8a8cd35222dc5c1d03579a4c6 |
| cp.icr.io/cp/ai/watson-stt-utils:1.12.0 | sha256:061ee1a19ab3bb1052a7f59e224541dbd304b86780c1ab44b81d6f47deba59c3 |
The Watson Speech to Text runtime requires additional model files to function. Pretrained models are also available as container images from the IBM Entitled Registry. The available model images are listed in the models catalog.
Next steps
Deploy the runtime container image using one of several available options. See Running the containers for details.