Search in sources :

Example 16 with RecognizeOptions

use of com.ibm.watson.speech_to_text.v1.model.RecognizeOptions in project java-sdk by watson-developer-cloud.

the class SpeechToTextExample method main.

public static void main(String[] args) {
    SpeechToText service = new SpeechToText();
    service.setUsernameAndPassword("<username>", "<password>");
    File audio = new File("src/test/resources/speech_to_text/sample1.wav");
    RecognizeOptions options = new RecognizeOptions.Builder().audio(audio).contentType(RecognizeOptions.ContentType.AUDIO_WAV).build();
    SpeechRecognitionResults transcript = service.recognize(options).execute();
    System.out.println(transcript);
}
Also used : File(java.io.File) SpeechRecognitionResults(com.ibm.watson.developer_cloud.speech_to_text.v1.model.SpeechRecognitionResults) RecognizeOptions(com.ibm.watson.developer_cloud.speech_to_text.v1.model.RecognizeOptions)

Example 17 with RecognizeOptions

use of com.ibm.watson.speech_to_text.v1.model.RecognizeOptions in project java-sdk by watson-developer-cloud.

the class SpeechToTextIT method testRecognizeFileString.

/**
 * Test recognize audio file.
 */
@Test
public void testRecognizeFileString() throws FileNotFoundException {
    Long maxAlternatives = 3L;
    Float wordAlternativesThreshold = 0.8f;
    File audio = new File(SAMPLE_WAV);
    RecognizeOptions options = new RecognizeOptions.Builder().audio(audio).contentType(RecognizeOptions.ContentType.AUDIO_WAV).maxAlternatives(maxAlternatives).wordAlternativesThreshold(wordAlternativesThreshold).smartFormatting(true).build();
    SpeechRecognitionResults results = service.recognize(options).execute();
    assertNotNull(results.getResults().get(0).getAlternatives().get(0).getTranscript());
    assertTrue(results.getResults().get(0).getAlternatives().size() <= maxAlternatives);
    List<WordAlternativeResults> wordAlternatives = results.getResults().get(0).getWordAlternatives();
    for (WordAlternativeResults alternativeResults : wordAlternatives) {
        assertTrue(alternativeResults.getAlternatives().get(0).getConfidence() >= wordAlternativesThreshold);
    }
}
Also used : WordAlternativeResults(com.ibm.watson.developer_cloud.speech_to_text.v1.model.WordAlternativeResults) File(java.io.File) SpeechRecognitionResults(com.ibm.watson.developer_cloud.speech_to_text.v1.model.SpeechRecognitionResults) RecognizeOptions(com.ibm.watson.developer_cloud.speech_to_text.v1.model.RecognizeOptions) WatsonServiceTest(com.ibm.watson.developer_cloud.WatsonServiceTest) Test(org.junit.Test)

Example 18 with RecognizeOptions

use of com.ibm.watson.speech_to_text.v1.model.RecognizeOptions in project java-sdk by watson-developer-cloud.

the class SpeechToTextTest method testRecognizeWithCustomizationWeight.

/**
 * Test recognize with customization weight.
 *
 * @throws FileNotFoundException the file not found exception
 * @throws InterruptedException the interrupted exception
 */
@Test
public void testRecognizeWithCustomizationWeight() throws FileNotFoundException, InterruptedException {
    String id = "foo";
    String recString = getStringFromInputStream(new FileInputStream("src/test/resources/speech_to_text/recognition.json"));
    JsonObject recognition = new JsonParser().parse(recString).getAsJsonObject();
    server.enqueue(new MockResponse().addHeader(CONTENT_TYPE, HttpMediaType.APPLICATION_JSON).setBody(recString));
    RecognizeOptions recognizeOptions = new RecognizeOptions.Builder().audio(SAMPLE_WAV).contentType(RecognizeOptions.ContentType.AUDIO_WAV).customizationId(id).customizationWeight(0.5).build();
    SpeechRecognitionResults result = service.recognize(recognizeOptions).execute();
    final RecordedRequest request = server.takeRequest();
    assertEquals(PATH_RECOGNIZE + "?customization_id=" + id + "&customization_weight=0.5", request.getPath());
    assertEquals(recognition, GSON.toJsonTree(result));
}
Also used : RecordedRequest(okhttp3.mockwebserver.RecordedRequest) MockResponse(okhttp3.mockwebserver.MockResponse) JsonObject(com.google.gson.JsonObject) ByteString(okio.ByteString) FileInputStream(java.io.FileInputStream) SpeechRecognitionResults(com.ibm.watson.developer_cloud.speech_to_text.v1.model.SpeechRecognitionResults) JsonParser(com.google.gson.JsonParser) RecognizeOptions(com.ibm.watson.developer_cloud.speech_to_text.v1.model.RecognizeOptions) WatsonServiceUnitTest(com.ibm.watson.developer_cloud.WatsonServiceUnitTest) Test(org.junit.Test)

Example 19 with RecognizeOptions

use of com.ibm.watson.speech_to_text.v1.model.RecognizeOptions in project java-sdk by watson-developer-cloud.

the class SpeechToTextTest method testRecognizeWebM.

/**
 * Test recognize WebM for WebM audio format.
 *
 * @throws URISyntaxException the URI syntax exception
 * @throws InterruptedException the interrupted exception
 */
@Test
public void testRecognizeWebM() throws URISyntaxException, InterruptedException, FileNotFoundException {
    server.enqueue(new MockResponse().addHeader(CONTENT_TYPE, HttpMediaType.APPLICATION_JSON).setBody(GSON.toJson(recognitionResults)));
    RecognizeOptions recognizeOptions = new RecognizeOptions.Builder().audio(SAMPLE_WEBM).contentType(RecognizeOptions.ContentType.AUDIO_WEBM).build();
    final SpeechRecognitionResults result = service.recognize(recognizeOptions).execute();
    final RecordedRequest request = server.takeRequest();
    assertNotNull(result);
    assertEquals(result, recognitionResults);
    assertEquals("POST", request.getMethod());
    assertEquals(PATH_RECOGNIZE, request.getPath());
    assertEquals(HttpMediaType.AUDIO_WEBM, request.getHeader(CONTENT_TYPE));
}
Also used : RecordedRequest(okhttp3.mockwebserver.RecordedRequest) MockResponse(okhttp3.mockwebserver.MockResponse) SpeechRecognitionResults(com.ibm.watson.developer_cloud.speech_to_text.v1.model.SpeechRecognitionResults) RecognizeOptions(com.ibm.watson.developer_cloud.speech_to_text.v1.model.RecognizeOptions) WatsonServiceUnitTest(com.ibm.watson.developer_cloud.WatsonServiceUnitTest) Test(org.junit.Test)

Example 20 with RecognizeOptions

use of com.ibm.watson.speech_to_text.v1.model.RecognizeOptions in project java-sdk by watson-developer-cloud.

the class SpeechToTextTest method testRecognizeWithAcousticCustomization.

/**
 * Test recognize with acoustic customization.
 *
 * @throws FileNotFoundException the file not found exception
 * @throws InterruptedException the interrupted exception
 */
@Test
public void testRecognizeWithAcousticCustomization() throws FileNotFoundException, InterruptedException {
    String id = "foo";
    String version = "version";
    String recString = getStringFromInputStream(new FileInputStream("src/test/resources/speech_to_text/recognition.json"));
    JsonObject recognition = new JsonParser().parse(recString).getAsJsonObject();
    server.enqueue(new MockResponse().addHeader(CONTENT_TYPE, HttpMediaType.APPLICATION_JSON).setBody(recString));
    RecognizeOptions recognizeOptions = new RecognizeOptions.Builder().audio(SAMPLE_WAV).contentType(RecognizeOptions.ContentType.AUDIO_WAV).acousticCustomizationId(id).version(version).build();
    SpeechRecognitionResults result = service.recognize(recognizeOptions).execute();
    final RecordedRequest request = server.takeRequest();
    assertEquals("POST", request.getMethod());
    assertEquals(PATH_RECOGNIZE + "?acoustic_customization_id=" + id + "&version=" + version, request.getPath());
    assertEquals(recognition, GSON.toJsonTree(result));
}
Also used : RecordedRequest(okhttp3.mockwebserver.RecordedRequest) MockResponse(okhttp3.mockwebserver.MockResponse) JsonObject(com.google.gson.JsonObject) ByteString(okio.ByteString) FileInputStream(java.io.FileInputStream) SpeechRecognitionResults(com.ibm.watson.developer_cloud.speech_to_text.v1.model.SpeechRecognitionResults) JsonParser(com.google.gson.JsonParser) RecognizeOptions(com.ibm.watson.developer_cloud.speech_to_text.v1.model.RecognizeOptions) WatsonServiceUnitTest(com.ibm.watson.developer_cloud.WatsonServiceUnitTest) Test(org.junit.Test)

Aggregations

RecognizeOptions (com.ibm.watson.developer_cloud.speech_to_text.v1.model.RecognizeOptions)18 Test (org.junit.Test)18 SpeechRecognitionResults (com.ibm.watson.developer_cloud.speech_to_text.v1.model.SpeechRecognitionResults)16 File (java.io.File)13 SpeechRecognitionResults (com.ibm.watson.speech_to_text.v1.model.SpeechRecognitionResults)9 FileInputStream (java.io.FileInputStream)9 RecognizeOptions (com.ibm.watson.speech_to_text.v1.model.RecognizeOptions)8 MockResponse (okhttp3.mockwebserver.MockResponse)8 WatsonServiceUnitTest (com.ibm.watson.developer_cloud.WatsonServiceUnitTest)7 RecordedRequest (okhttp3.mockwebserver.RecordedRequest)7 WatsonServiceTest (com.ibm.watson.developer_cloud.WatsonServiceTest)6 WatsonServiceTest (com.ibm.watson.common.WatsonServiceTest)5 BaseRecognizeCallback (com.ibm.watson.developer_cloud.speech_to_text.v1.websocket.BaseRecognizeCallback)5 ByteString (okio.ByteString)5 JsonObject (com.google.gson.JsonObject)4 JsonParser (com.google.gson.JsonParser)4 Authenticator (com.ibm.cloud.sdk.core.security.Authenticator)2 IamAuthenticator (com.ibm.cloud.sdk.core.security.IamAuthenticator)2 NotFoundException (com.ibm.watson.developer_cloud.service.exception.NotFoundException)2 WordAlternativeResults (com.ibm.watson.developer_cloud.speech_to_text.v1.model.WordAlternativeResults)2