Before you can use AutoML Translation, you must enable it for your project. Open the AutoML Translation UI and select your whitelisted project from the drop-down list in the upper right of the title bar. The application walks you through the necessary steps, which are also described below.
Set up your project
Sign in to your Google Account.
If you don't already have one, sign up for a new account.
In the Cloud Console, on the project selector page, select or create a Cloud project.
Make sure that billing is enabled for your Google Cloud project. Learn how to confirm billing is enabled for your project.
- Enable the AutoML and Cloud Storage APIs.
- Install the
gcloudcommand line tool.
- Follow the instructions to create a service account and download a key file for that account.
- Set the
GOOGLE_APPLICATION_CREDENTIALSenvironment variable to the path to the service account key file that you downloaded when you created the service account.
- Set the
PROJECT_IDenvironment variable to your Project ID.
export PROJECT_ID=your-project-idThe AutoML API calls and resource names include your Project ID in them. The
PROJECT_IDenvironment variable provides a convenient way to specify the ID.
- If you are an owner for your project, add your service account to the AutoML Editor
IAM role, replacing service-account-name with the name of
your new service account. For example,
gcloud auth login gcloud projects add-iam-policy-binding $PROJECT_ID \ --member="serviceAccount:service-account-name" \ --role="roles/automl.editor"
- Otherwise (if you are not a project owner), ask a project owner to add both your user ID and your service account to the AutoML Editor IAM role.
Create a Cloud Storage bucket
Create a Google Cloud Storage bucket to store the sentence pairs that you
will use to train your custom model. The bucket name must be in the format:
The following command creates a storage bucket
us-central1 region named
gsutil mb -p project-id -c regional -l us-central1 gs://project-id-vcm/We recommend the following file structure for your Cloud Storage files: