In JAVA code, not running in the Google environment, how does one use a trained translation model? - translation

Question

I seem to be missing something obvious, I think. We've been using the Google Translation API for a while now, and now we want to "upgrade" to a custom trained model instead of the default nmt.
We've uploaded our texts, trained it, and now have a model. In the predict tab on the Google console, it works great. so, now what?
This is the code that we use today:
translate = TranslateOptions
.newBuilder()
.setCredentials(ServiceAccountCredentials.fromStream(googleCredentials))
.build()
.getService();
translate.translate(
text,
TranslateOption.sourceLanguage(fromLng),
TranslateOption.targetLanguage(toLng),
TranslateOption.model(model));
where model is "nmt" (or "base")... should I just be able to drop in my newly trained model code that was created when the training finished? When I try, it comes back with a 400 error and the message:
"code" : 400,
"errors" : [ {
"domain" : "global",
"message" : "Invalid Value",
"reason" : "invalid"
} ],
"message" : "Invalid Value"
Trying different code as documented here: https://cloud.google.com/translate/docs/quickstart-client-libraries-v3
yields other errors like: "INFO: Failed to detect whether we are running on Google Compute Engine."
Where am I going wrong?

Answer 1

here we go... for the next person looking to do this:
<dependency>
<groupId>com.google.cloud</groupId>
<artifactId>google-cloud-automl</artifactId>
<version>0.97.0-beta</version>
</dependency>
code:
private PredictionServiceClient predictionClient;
private ModelName modelName;
public GoogleTranslationServiceTrained(final byte[] googleCredentials) throws IOException {
super();
PredictionServiceSettings settings = PredictionServiceSettings
.newBuilder()
.setCredentialsProvider(new CredentialsProvider() {
#Override
public Credentials getCredentials() throws IOException {
return ServiceAccountCredentials.fromStream(new ByteArrayInputStream(googleCredentials));
}
}).build();
// Instantiate client for prediction service.
predictionClient = PredictionServiceClient.create(settings);
// Get the full path of the model.
modelName = ModelName.of("xxxx", "us-central1", "yyy");
}
public String getRemoteTranslate(String text) {
TextSnippet textSnippet = TextSnippet.newBuilder().setContent(text).build();
// Set the payload by giving the content of the file.
ExamplePayload payload = ExamplePayload.newBuilder().setTextSnippet(textSnippet).build();
// Additional parameters that can be provided for prediction
Map<String, String> params = new HashMap<>();
PredictResponse response = predictionClient.predict(modelName, payload, params);
TextSnippet translatedContent = response.getPayload(0).getTranslation().getTranslatedContent();
return StringEscapeUtils.unescapeHtml4(translatedContent.getContent());
}