Antes de começar

Antes de usar o AutoML Translation, é preciso ativá-lo no projeto. Abra a IU do AutoML Translation e selecione o projeto na lista suspensa, na parte superior direita da barra de título. No aplicativo, você recebe instruções por meio das etapas necessários, que também estão descritas a seguir.

Crie o projeto

1. Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.
2. Install the Google Cloud CLI.

3. To initialize the gcloud CLI, run the following command:

   gcloud init

4. Create or select a Google Cloud project.

   Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

   • Create a Google Cloud project:

     gcloud projects create PROJECT_ID

     Replace PROJECT_ID with a name for the Google Cloud project you are creating.

   • Select the Google Cloud project that you created:

     gcloud config set project PROJECT_ID

     Replace PROJECT_ID with your Google Cloud project name.

5. Make sure that billing is enabled for your Google Cloud project.

6. Enable the AutoML and Cloud Storage APIs:

   gcloud services enable storage-component.googleapis.com automl.googleapis.com storage-api.googleapis.com

7. Install the Google Cloud CLI.

8. To initialize the gcloud CLI, run the following command:

   gcloud init

9. Create or select a Google Cloud project.

   Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

   • Create a Google Cloud project:

     gcloud projects create PROJECT_ID

     Replace PROJECT_ID with a name for the Google Cloud project you are creating.

   • Select the Google Cloud project that you created:

     gcloud config set project PROJECT_ID

     Replace PROJECT_ID with your Google Cloud project name.

10. Make sure that billing is enabled for your Google Cloud project.

11. Enable the AutoML and Cloud Storage APIs:

    gcloud services enable storage-component.googleapis.com automl.googleapis.com storage-api.googleapis.com

12. Defina a variável de ambiente PROJECT_ID como seu ID do projeto.

    export PROJECT_ID=PROJECT_ID

    As chamadas da API AutoML e os nomes dos recursos incluem seu ID do projeto. A variável de ambiente PROJECT_ID é uma maneira conveniente de especificar o ID.

Criar um bucket do Cloud Storage

Crie um bucket do Google Cloud Storage para armazenar os pares de frases que você vai usar para treinar seu modelo personalizado. O nome do bucket precisa estar no formato: project-id-vcm. O comando a seguir cria um bucket de armazenamento denominado project-id-vcm na região us-central1.

gcloud storage buckets create gs://project-id-vcm/ --project=project-id --location=us-central1

Recomendamos a seguinte estrutura para os arquivos do Cloud Storage: gs://project-id-vcm/dataset-name/documents/document-name.txt