Search in sources :

Example 6 with IamAuthenticator

use of com.ibm.cloud.sdk.core.security.IamAuthenticator in project java-sdk by watson-developer-cloud.

the class RecognizeUsingWebSocketsExample method main.

public static void main(String[] args) throws FileNotFoundException, InterruptedException {
    Authenticator authenticator = new IamAuthenticator("<iam_api_key>");
    SpeechToText service = new SpeechToText(authenticator);
    FileInputStream audio = new FileInputStream("src/test/resources/speech_to_text/sample1.wav");
    RecognizeWithWebsocketsOptions options = new RecognizeWithWebsocketsOptions.Builder().audio(audio).interimResults(true).contentType(HttpMediaType.AUDIO_WAV).build();
    service.recognizeUsingWebSocket(options, new BaseRecognizeCallback() {

        @Override
        public void onTranscription(SpeechRecognitionResults speechResults) {
            System.out.println(speechResults);
        }

        @Override
        public void onDisconnected() {
            lock.countDown();
        }
    });
    lock.await(1, TimeUnit.MINUTES);
}
Also used : IamAuthenticator(com.ibm.cloud.sdk.core.security.IamAuthenticator) BaseRecognizeCallback(com.ibm.watson.speech_to_text.v1.websocket.BaseRecognizeCallback) RecognizeWithWebsocketsOptions(com.ibm.watson.speech_to_text.v1.model.RecognizeWithWebsocketsOptions) Authenticator(com.ibm.cloud.sdk.core.security.Authenticator) IamAuthenticator(com.ibm.cloud.sdk.core.security.IamAuthenticator) FileInputStream(java.io.FileInputStream) SpeechRecognitionResults(com.ibm.watson.speech_to_text.v1.model.SpeechRecognitionResults)

Example 7 with IamAuthenticator

use of com.ibm.cloud.sdk.core.security.IamAuthenticator in project java-sdk by watson-developer-cloud.

the class CustomizationExample method main.

public static void main(String[] args) throws IOException {
    Authenticator authenticator = new IamAuthenticator("<iam_api_key>");
    TextToSpeech service = new TextToSpeech(authenticator);
    // create custom voice model.
    CreateCustomModelOptions createOptions = new CreateCustomModelOptions.Builder().name("my model").language("en-US").description("the model for testing").build();
    CustomModel customVoiceModel = service.createCustomModel(createOptions).execute().getResult();
    System.out.println(customVoiceModel);
    // list custom voice models for US English.
    ListCustomModelsOptions listOptions = new ListCustomModelsOptions.Builder().language("en-US").build();
    CustomModels customVoiceModels = service.listCustomModels(listOptions).execute().getResult();
    System.out.println(customVoiceModels);
    // update custom voice model.
    String newName = "my updated model";
    UpdateCustomModelOptions updateOptions = new UpdateCustomModelOptions.Builder().customizationId(customVoiceModel.getCustomizationId()).name(newName).description("the updated model for testing").build();
    service.updateCustomModel(updateOptions).execute();
    // list custom voice models regardless of language.
    customVoiceModels = service.listCustomModels().execute().getResult();
    System.out.println(customVoiceModels);
    // create multiple custom word translations
    Word word1 = new Word.Builder().word("hodor").translation("hold the door").build();
    Word word2 = new Word.Builder().word("plz").translation("please").build();
    List<Word> words = Arrays.asList(word1, word2);
    AddWordsOptions addOptions = new AddWordsOptions.Builder().customizationId(customVoiceModel.getCustomizationId()).words(words).build();
    service.addWords(addOptions).execute();
    // create a single custom word translation
    AddWordOptions addWordOptions = new AddWordOptions.Builder().word("nat").translation("and that").customizationId(customVoiceModel.getCustomizationId()).build();
    service.addWord(addWordOptions).execute();
    // get custom word translations
    ListWordsOptions listWordsOptions = new ListWordsOptions.Builder().customizationId(customVoiceModel.getCustomizationId()).build();
    Words customWords = service.listWords(listWordsOptions).execute().getResult();
    System.out.println(customWords);
    // get custom word translation
    GetWordOptions getOptions = new GetWordOptions.Builder().customizationId(customVoiceModel.getCustomizationId()).word("hodor").build();
    Translation translation = service.getWord(getOptions).execute().getResult();
    System.out.println(translation);
    // synthesize with custom voice model
    String text = "plz hodor";
    SynthesizeOptions synthesizeOptions = new SynthesizeOptions.Builder().text(text).voice(SynthesizeOptions.Voice.EN_US_MICHAELVOICE).accept(HttpMediaType.AUDIO_WAV).customizationId(customVoiceModel.getCustomizationId()).build();
    InputStream in = service.synthesize(synthesizeOptions).execute().getResult();
    writeToFile(WaveUtils.reWriteWaveHeader(in), new File("output.wav"));
    // delete custom words with object and string
    DeleteWordOptions deleteOptions1 = new DeleteWordOptions.Builder().customizationId(customVoiceModel.getCustomizationId()).word(word1.word()).build();
    service.deleteWord(deleteOptions1).execute();
    DeleteWordOptions deleteOptions2 = new DeleteWordOptions.Builder().customizationId(customVoiceModel.getCustomizationId()).word(word2.word()).build();
    service.deleteWord(deleteOptions2).execute();
    // delete custom voice model
    DeleteCustomModelOptions deleteOptions = new DeleteCustomModelOptions.Builder().customizationId(customVoiceModel.getCustomizationId()).build();
    service.deleteCustomModel(deleteOptions).execute();
    // list custom voice models regardless of language.
    customVoiceModels = service.listCustomModels().execute().getResult();
    System.out.println(customVoiceModels);
}
Also used : CreateCustomModelOptions(com.ibm.watson.text_to_speech.v1.model.CreateCustomModelOptions) Word(com.ibm.watson.text_to_speech.v1.model.Word) CustomModels(com.ibm.watson.text_to_speech.v1.model.CustomModels) IamAuthenticator(com.ibm.cloud.sdk.core.security.IamAuthenticator) AddWordOptions(com.ibm.watson.text_to_speech.v1.model.AddWordOptions) DeleteWordOptions(com.ibm.watson.text_to_speech.v1.model.DeleteWordOptions) ListCustomModelsOptions(com.ibm.watson.text_to_speech.v1.model.ListCustomModelsOptions) IamAuthenticator(com.ibm.cloud.sdk.core.security.IamAuthenticator) Authenticator(com.ibm.cloud.sdk.core.security.Authenticator) SynthesizeOptions(com.ibm.watson.text_to_speech.v1.model.SynthesizeOptions) Translation(com.ibm.watson.text_to_speech.v1.model.Translation) InputStream(java.io.InputStream) GetWordOptions(com.ibm.watson.text_to_speech.v1.model.GetWordOptions) CustomModel(com.ibm.watson.text_to_speech.v1.model.CustomModel) AddWordsOptions(com.ibm.watson.text_to_speech.v1.model.AddWordsOptions) Words(com.ibm.watson.text_to_speech.v1.model.Words) ListWordsOptions(com.ibm.watson.text_to_speech.v1.model.ListWordsOptions) UpdateCustomModelOptions(com.ibm.watson.text_to_speech.v1.model.UpdateCustomModelOptions) DeleteCustomModelOptions(com.ibm.watson.text_to_speech.v1.model.DeleteCustomModelOptions) File(java.io.File)

Example 8 with IamAuthenticator

use of com.ibm.cloud.sdk.core.security.IamAuthenticator in project java-sdk by watson-developer-cloud.

the class AssistantExample method main.

public static void main(String[] args) throws Exception {
    Authenticator authenticator = new IamAuthenticator("<iam_api_key>");
    Assistant service = new Assistant("2019-02-28", authenticator);
    MessageInput input = new MessageInput();
    input.setText("Hi");
    MessageOptions options = new MessageOptions.Builder("<workspaceId>").input(input).build();
    // sync
    MessageResponse response = service.message(options).execute().getResult();
    System.out.println(response);
    // async
    service.message(options).enqueue(new ServiceCallback<MessageResponse>() {

        @Override
        public void onResponse(Response<MessageResponse> response) {
            System.out.println(response.getResult());
        }

        @Override
        public void onFailure(Exception e) {
        }
    });
    // RxJava
    Single<Response<MessageResponse>> observableRequest = service.message(options).reactiveRequest();
    observableRequest.subscribeOn(Schedulers.single()).subscribe(new Consumer<Response<MessageResponse>>() {

        @Override
        public void accept(Response<MessageResponse> response) throws Exception {
            System.out.println(response.getResult());
        }
    });
    Thread.sleep(5000);
}
Also used : IamAuthenticator(com.ibm.cloud.sdk.core.security.IamAuthenticator) MessageResponse(com.ibm.watson.assistant.v1.model.MessageResponse) MessageInput(com.ibm.watson.assistant.v1.model.MessageInput) MessageResponse(com.ibm.watson.assistant.v1.model.MessageResponse) Response(com.ibm.cloud.sdk.core.http.Response) MessageOptions(com.ibm.watson.assistant.v1.model.MessageOptions) Authenticator(com.ibm.cloud.sdk.core.security.Authenticator) IamAuthenticator(com.ibm.cloud.sdk.core.security.IamAuthenticator)

Example 9 with IamAuthenticator

use of com.ibm.cloud.sdk.core.security.IamAuthenticator in project java-sdk by watson-developer-cloud.

the class CustomizationExample method main.

/**
 * The main method.
 *
 * @param args the arguments
 * @throws InterruptedException the interrupted exception
 */
public static void main(String[] args) throws InterruptedException, FileNotFoundException {
    Authenticator authenticator = new IamAuthenticator("<iam_api_key>");
    SpeechToText service = new SpeechToText(authenticator);
    // Create language model
    CreateLanguageModelOptions createOptions = new CreateLanguageModelOptions.Builder().name("IEEE-permanent").baseModelName("en-US_BroadbandModel").description("My customization").build();
    LanguageModel myModel = service.createLanguageModel(createOptions).execute().getResult();
    String id = myModel.getCustomizationId();
    try {
        // Add a corpus file to the model
        AddCorpusOptions addOptions = new AddCorpusOptions.Builder().customizationId(id).corpusName("corpus-1").corpusFile(new File(CORPUS_FILE)).allowOverwrite(false).build();
        service.addCorpus(addOptions).execute().getResult();
        // Get corpus status
        GetCorpusOptions getOptions = new GetCorpusOptions.Builder().customizationId(id).corpusName("corpus-1").build();
        for (int x = 0; x < 30 && !service.getCorpus(getOptions).execute().getResult().getStatus().equals(Corpus.Status.ANALYZED); x++) {
            Thread.sleep(5000);
        }
        // Get all corpora
        ListCorporaOptions listCorporaOptions = new ListCorporaOptions.Builder().customizationId(id).build();
        Corpora corpora = service.listCorpora(listCorporaOptions).execute().getResult();
        System.out.println(corpora);
        // Get specific corpus
        Corpus corpus = service.getCorpus(getOptions).execute().getResult();
        System.out.println(corpus);
        // Now add some user words to the custom model
        service.addWord(new AddWordOptions.Builder().customizationId(id).wordName("IEEE").word("IEEE").displayAs("IEEE").addSoundsLike("I. triple E.").build()).execute();
        service.addWord(new AddWordOptions.Builder().customizationId(id).wordName("hhonors").word("hhonors").displayAs("IEEE").addSoundsLike("H. honors").addSoundsLike("Hilton honors").build()).execute();
        // Display all words in the words resource (OOVs from the corpus and
        // new words just added) in ascending alphabetical order
        ListWordsOptions listWordsAlphabeticalOptions = new ListWordsOptions.Builder().customizationId(id).wordType(ListWordsOptions.WordType.ALL).build();
        Words words = service.listWords(listWordsAlphabeticalOptions).execute().getResult();
        System.out.println("\nASCENDING ALPHABETICAL ORDER:");
        System.out.println(words);
        // Then display all words in the words resource in descending order
        // by count
        ListWordsOptions listWordsCountOptions = new ListWordsOptions.Builder().customizationId(id).wordType(ListWordsOptions.WordType.ALL).sort("-" + ListWordsOptions.Sort.COUNT).build();
        words = service.listWords(listWordsCountOptions).execute().getResult();
        System.out.println("\nDESCENDING ORDER BY COUNT:");
        System.out.println(words);
        // Now start training of the model
        TrainLanguageModelOptions trainOptions = new TrainLanguageModelOptions.Builder().customizationId(id).wordTypeToAdd(TrainLanguageModelOptions.WordTypeToAdd.ALL).build();
        service.trainLanguageModel(trainOptions).execute();
        for (int x = 0; x < 30 && !myModel.getStatus().equals(LanguageModel.Status.AVAILABLE); x++) {
            GetLanguageModelOptions getLanguageModelOptions = new GetLanguageModelOptions.Builder().customizationId(id).build();
            myModel = service.getLanguageModel(getLanguageModelOptions).execute().getResult();
            Thread.sleep(10000);
        }
        File audio = new File(AUDIO_FILE);
        RecognizeOptions recognizeOptionsWithModel = new RecognizeOptions.Builder().model(RecognizeOptions.Model.EN_US_BROADBANDMODEL).customizationId(id).audio(audio).contentType(HttpMediaType.AUDIO_WAV).build();
        RecognizeOptions recognizeOptionsWithoutModel = new RecognizeOptions.Builder().model(RecognizeOptions.Model.EN_US_BROADBANDMODEL).audio(audio).contentType(HttpMediaType.AUDIO_WAV).build();
        // First decode WITHOUT the custom model
        SpeechRecognitionResults transcript = service.recognize(recognizeOptionsWithoutModel).execute().getResult();
        System.out.println(transcript);
        // Now decode with the custom model
        transcript = service.recognize(recognizeOptionsWithModel).execute().getResult();
        System.out.println(transcript);
    } finally {
        DeleteLanguageModelOptions deleteOptions = new DeleteLanguageModelOptions.Builder().customizationId(id).build();
        service.deleteLanguageModel(deleteOptions).execute();
    }
}
Also used : IamAuthenticator(com.ibm.cloud.sdk.core.security.IamAuthenticator) CreateLanguageModelOptions(com.ibm.watson.speech_to_text.v1.model.CreateLanguageModelOptions) Corpus(com.ibm.watson.speech_to_text.v1.model.Corpus) DeleteLanguageModelOptions(com.ibm.watson.speech_to_text.v1.model.DeleteLanguageModelOptions) AddWordOptions(com.ibm.watson.speech_to_text.v1.model.AddWordOptions) LanguageModel(com.ibm.watson.speech_to_text.v1.model.LanguageModel) GetCorpusOptions(com.ibm.watson.speech_to_text.v1.model.GetCorpusOptions) IamAuthenticator(com.ibm.cloud.sdk.core.security.IamAuthenticator) Authenticator(com.ibm.cloud.sdk.core.security.Authenticator) AddCorpusOptions(com.ibm.watson.speech_to_text.v1.model.AddCorpusOptions) Corpora(com.ibm.watson.speech_to_text.v1.model.Corpora) GetLanguageModelOptions(com.ibm.watson.speech_to_text.v1.model.GetLanguageModelOptions) Words(com.ibm.watson.speech_to_text.v1.model.Words) ListWordsOptions(com.ibm.watson.speech_to_text.v1.model.ListWordsOptions) TrainLanguageModelOptions(com.ibm.watson.speech_to_text.v1.model.TrainLanguageModelOptions) File(java.io.File) ListCorporaOptions(com.ibm.watson.speech_to_text.v1.model.ListCorporaOptions) SpeechRecognitionResults(com.ibm.watson.speech_to_text.v1.model.SpeechRecognitionResults) RecognizeOptions(com.ibm.watson.speech_to_text.v1.model.RecognizeOptions)

Example 10 with IamAuthenticator

use of com.ibm.cloud.sdk.core.security.IamAuthenticator in project java-sdk by watson-developer-cloud.

the class MicrophoneWithWebSocketsExample method main.

/**
 * The main method.
 *
 * @param args the arguments
 * @throws Exception the exception
 */
public static void main(final String[] args) throws Exception {
    Authenticator authenticator = new IamAuthenticator("<iam_api_key>");
    SpeechToText service = new SpeechToText(authenticator);
    // Signed PCM AudioFormat with 16kHz, 16 bit sample size, mono
    int sampleRate = 16000;
    AudioFormat format = new AudioFormat(sampleRate, 16, 1, true, false);
    DataLine.Info info = new DataLine.Info(TargetDataLine.class, format);
    if (!AudioSystem.isLineSupported(info)) {
        System.out.println("Line not supported");
        System.exit(0);
    }
    TargetDataLine line = (TargetDataLine) AudioSystem.getLine(info);
    line.open(format);
    line.start();
    AudioInputStream audio = new AudioInputStream(line);
    RecognizeWithWebsocketsOptions options = new RecognizeWithWebsocketsOptions.Builder().audio(audio).interimResults(true).timestamps(true).wordConfidence(true).contentType(HttpMediaType.AUDIO_RAW + ";rate=" + sampleRate).build();
    service.recognizeUsingWebSocket(options, new BaseRecognizeCallback() {

        @Override
        public void onTranscription(SpeechRecognitionResults speechResults) {
            System.out.println(speechResults);
        }
    });
    System.out.println("Listening to your voice for the next 30s...");
    Thread.sleep(30 * 1000);
    // closing the WebSockets underlying InputStream will close the WebSocket itself.
    line.stop();
    line.close();
    System.out.println("Fin.");
}
Also used : IamAuthenticator(com.ibm.cloud.sdk.core.security.IamAuthenticator) BaseRecognizeCallback(com.ibm.watson.speech_to_text.v1.websocket.BaseRecognizeCallback) TargetDataLine(javax.sound.sampled.TargetDataLine) DataLine(javax.sound.sampled.DataLine) TargetDataLine(javax.sound.sampled.TargetDataLine) AudioInputStream(javax.sound.sampled.AudioInputStream) AudioFormat(javax.sound.sampled.AudioFormat) RecognizeWithWebsocketsOptions(com.ibm.watson.speech_to_text.v1.model.RecognizeWithWebsocketsOptions) Authenticator(com.ibm.cloud.sdk.core.security.Authenticator) IamAuthenticator(com.ibm.cloud.sdk.core.security.IamAuthenticator) SpeechRecognitionResults(com.ibm.watson.speech_to_text.v1.model.SpeechRecognitionResults)

Aggregations

IamAuthenticator (com.ibm.cloud.sdk.core.security.IamAuthenticator)32 Authenticator (com.ibm.cloud.sdk.core.security.Authenticator)30 Before (org.junit.Before)15 SpeechRecognitionResults (com.ibm.watson.speech_to_text.v1.model.SpeechRecognitionResults)5 File (java.io.File)4 Response (com.ibm.cloud.sdk.core.http.Response)2 MessageInput (com.ibm.watson.assistant.v1.model.MessageInput)2 MessageOptions (com.ibm.watson.assistant.v1.model.MessageOptions)2 MessageResponse (com.ibm.watson.assistant.v1.model.MessageResponse)2 TranslateOptions (com.ibm.watson.language_translator.v3.model.TranslateOptions)2 TranslationResult (com.ibm.watson.language_translator.v3.model.TranslationResult)2 RecognizeWithWebsocketsOptions (com.ibm.watson.speech_to_text.v1.model.RecognizeWithWebsocketsOptions)2 BaseRecognizeCallback (com.ibm.watson.speech_to_text.v1.websocket.BaseRecognizeCallback)2 ToneAnalysis (com.ibm.watson.tone_analyzer.v3.model.ToneAnalysis)2 ToneOptions (com.ibm.watson.tone_analyzer.v3.model.ToneOptions)2 ByteArrayInputStream (java.io.ByteArrayInputStream)2 InputStream (java.io.InputStream)2 JsonObject (com.google.gson.JsonObject)1 HttpConfigOptions (com.ibm.cloud.sdk.core.http.HttpConfigOptions)1 ServiceCallback (com.ibm.cloud.sdk.core.http.ServiceCallback)1