本頁面由 Cloud Translation API 翻譯而成。

在 Android 上使用機器學習套件翻譯文字

您可以使用機器學習套件在不同語言之間翻譯文本。 ML Kit 目前支持59 種語言之間的翻譯。

在你開始之前

如果您還沒有，請將 Firebase 添加到您的 Android 項目中。

將 ML Kit Android 庫的依賴項添加到您的模塊（應用程序級）Gradle 文件（通常app/build.gradle ）：

apply plugin: 'com.android.application'
apply plugin: 'com.google.gms.google-services'

dependencies {
  // ...

  implementation 'com.google.firebase:firebase-ml-natural-language:22.0.0'
  implementation 'com.google.firebase:firebase-ml-natural-language-translate-model:20.0.8'
}

翻譯一串文本

要在兩種語言之間翻譯字符串：

創建一個FirebaseTranslator對象，使用源語言和目標語言對其進行配置：

Java

// Create an English-German translator:
FirebaseTranslatorOptions options =
        new FirebaseTranslatorOptions.Builder()
                .setSourceLanguage(FirebaseTranslateLanguage.EN)
                .setTargetLanguage(FirebaseTranslateLanguage.DE)
                .build();
final FirebaseTranslator englishGermanTranslator =
        FirebaseNaturalLanguage.getInstance().getTranslator(options);

Kotlin+KTX

// Create an English-German translator:
val options = FirebaseTranslatorOptions.Builder()
        .setSourceLanguage(FirebaseTranslateLanguage.EN)
        .setTargetLanguage(FirebaseTranslateLanguage.DE)
        .build()
val englishGermanTranslator = FirebaseNaturalLanguage.getInstance().getTranslator(options)

如果您不知道輸入文本的語言，可以先使用語言識別API 。（但請確保您不要一次在設備上保留太多語言模型。）

確保所需的翻譯模型已下載到設備。在知道模型可用之前不要調用translate() 。

Java

FirebaseModelDownloadConditions conditions = new FirebaseModelDownloadConditions.Builder()
    .requireWifi()
    .build();
englishGermanTranslator.downloadModelIfNeeded(conditions)
      .addOnSuccessListener(
          new OnSuccessListener<Void>() {
            @Override
            public void onSuccess(Void v) {
              // Model downloaded successfully. Okay to start translating.
              // (Set a flag, unhide the translation UI, etc.)
            }
          })
      .addOnFailureListener(
          new OnFailureListener() {
            @Override
            public void onFailure(@NonNull Exception e) {
              // Model couldn’t be downloaded or other internal error.
              // ...
            }
          });

Kotlin+KTX

englishGermanTranslator.downloadModelIfNeeded()
        .addOnSuccessListener {
            // Model downloaded successfully. Okay to start translating.
            // (Set a flag, unhide the translation UI, etc.)
        }
        .addOnFailureListener { exception ->
            // Model couldn’t be downloaded or other internal error.
            // ...
        }

語言模型有30MB左右，沒必要不要下載，只能用WiFi下載，除非用戶另有說明。您還應該刪除不需要的模型。請參閱顯式管理翻譯模型。

確認模型已下載後，將源語言的文本字符串傳遞給translate() ：

Java

englishGermanTranslator.translate(text)
      .addOnSuccessListener(
          new OnSuccessListener<String>() {
            @Override
            public void onSuccess(@NonNull String translatedText) {
              // Translation successful.
            }
          })
      .addOnFailureListener(
          new OnFailureListener() {
            @Override
            public void onFailure(@NonNull Exception e) {
              // Error.
              // ...
            }
          });

Kotlin+KTX

englishGermanTranslator.translate(text)
        .addOnSuccessListener { translatedText ->
            // Translation successful.
        }
        .addOnFailureListener { exception ->
             // Error.
             // ...
        }

使用您配置的目標語言的翻譯文本將傳遞給成功偵聽器。

明確管理翻譯模型

當您如上所述使用翻譯 API 時，ML Kit 會根據需要自動將特定於語言的翻譯模型下載到設備。您還可以使用 ML Kit 的翻譯模型管理 API 明確管理您希望在設備上可用的翻譯模型。如果您想提前下載模型或從設備中刪除不需要的模型，這會很有用。

Java

FirebaseModelManager modelManager = FirebaseModelManager.getInstance();

// Get translation models stored on the device.
modelManager.getDownloadedModels(FirebaseTranslateRemoteModel.class)
        .addOnSuccessListener(new OnSuccessListener<Set<FirebaseTranslateRemoteModel>>() {
            @Override
            public void onSuccess(Set<FirebaseTranslateRemoteModel> models) {
                // ...
            }
        })
        .addOnFailureListener(new OnFailureListener() {
            @Override
            public void onFailure(@NonNull Exception e) {
                // Error.
            }
        });

// Delete the German model if it's on the device.
FirebaseTranslateRemoteModel deModel =
        new FirebaseTranslateRemoteModel.Builder(FirebaseTranslateLanguage.DE).build();
modelManager.deleteDownloadedModel(deModel)
        .addOnSuccessListener(new OnSuccessListener<Void>() {
            @Override
            public void onSuccess(Void v) {
                // Model deleted.
            }
        })
        .addOnFailureListener(new OnFailureListener() {
            @Override
            public void onFailure(@NonNull Exception e) {
                // Error.
            }
        });

// Download the French model.
FirebaseTranslateRemoteModel frModel =
        new FirebaseTranslateRemoteModel.Builder(FirebaseTranslateLanguage.FR).build();
FirebaseModelDownloadConditions conditions = new FirebaseModelDownloadConditions.Builder()
        .requireWifi()
        .build();
modelManager.download(frModel, conditions)
        .addOnSuccessListener(new OnSuccessListener<Void>() {
            @Override
            public void onSuccess(Void v) {
                // Model downloaded.
            }
        })
        .addOnFailureListener(new OnFailureListener() {
            @Override
            public void onFailure(@NonNull Exception e) {
                // Error.
            }
        });

Kotlin+KTX

val modelManager = FirebaseModelManager.getInstance()

// Get translation models stored on the device.
modelManager.getDownloadedModels(FirebaseTranslateRemoteModel::class.java)
    .addOnSuccessListener { models ->
        // ...
    }
    .addOnFailureListener {
        // Error.
    }

// Delete the German model if it's on the device.
val deModel = FirebaseTranslateRemoteModel.Builder(FirebaseTranslateLanguage.DE).build()
modelManager.deleteDownloadedModel(deModel)
    .addOnSuccessListener {
        // Model deleted.
    }
    .addOnFailureListener {
        // Error.
    }

// Download the French model.
val frModel = FirebaseTranslateRemoteModel.Builder(FirebaseTranslateLanguage.FR).build()
val conditions = FirebaseModelDownloadConditions.Builder()
    .requireWifi()
    .build()
modelManager.download(frModel, conditions)
    .addOnSuccessListener {
        // Model downloaded.
    }
    .addOnFailureListener {
        // Error.
    }