use of com.ibm.watson.speech_to_text.v1.model.GetCorpusOptions in project java-sdk by watson-developer-cloud.
the class SpeechToTextIT method testCreateLanguageModel.
/**
* Test create language model.
*
* @throws InterruptedException the interrupted exception
*/
@Test
public void testCreateLanguageModel() throws InterruptedException, FileNotFoundException {
CreateLanguageModelOptions createOptions = new CreateLanguageModelOptions.Builder().name("java-sdk-temporary").baseModelName(EN_BROADBAND16K).description("Temporary custom model for testing the Java SDK").build();
LanguageModel myModel = service.createLanguageModel(createOptions).execute();
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(String.format(SPEECH_RESOURCE, "corpus1.txt"))).corpusFileContentType(HttpMediaType.TEXT_PLAIN).allowOverwrite(false).build();
service.addCorpus(addOptions).execute();
// Get corpus status
GetCorpusOptions getOptions = new GetCorpusOptions.Builder().customizationId(id).corpusName("corpus-1").build();
for (int x = 0; x < 30 && !service.getCorpus(getOptions).execute().getStatus().equals(Status.ANALYZED); x++) {
Thread.sleep(5000);
}
assertTrue(service.getCorpus(getOptions).execute().getStatus().equals(Status.ANALYZED));
// Add the corpus file to the model again and allow overwrite
AddCorpusOptions addOptionsWithOverwrite = new AddCorpusOptions.Builder().customizationId(id).corpusName("corpus-1").corpusFile(new File(String.format(SPEECH_RESOURCE, "corpus1.txt"))).corpusFileContentType(HttpMediaType.TEXT_PLAIN).allowOverwrite(true).build();
service.addCorpus(addOptionsWithOverwrite).execute();
// Get corpus status
for (int x = 0; x < 30 && !service.getCorpus(getOptions).execute().getStatus().equals(Status.ANALYZED); x++) {
Thread.sleep(5000);
}
assertTrue(service.getCorpus(getOptions).execute().getStatus().equals(Status.ANALYZED));
// Get corpora
ListCorporaOptions listCorporaOptions = new ListCorporaOptions.Builder().customizationId(id).build();
Corpora corpora = service.listCorpora(listCorporaOptions).execute();
assertNotNull(corpora);
assertTrue(corpora.getCorpora().size() == 1);
// 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();
service.addWord(new AddWordOptions.Builder().customizationId(id).wordName("aaa").word("aaa").displayAs("aaa").addSoundsLike("aaa").addSoundsLike("bbb").build()).execute();
service.addWord(new AddWordOptions.Builder().customizationId(id).wordName("bbb").word("bbb").addSoundsLike("aaa").addSoundsLike("bbb").build()).execute();
service.addWord(new AddWordOptions.Builder().customizationId(id).wordName("ccc").word("ccc").displayAs("ccc").build()).execute();
service.addWord(new AddWordOptions.Builder().customizationId(id).wordName("ddd").word("ddd").build()).execute();
service.addWord(new AddWordOptions.Builder().customizationId(id).wordName("eee").word("eee").build()).execute();
// Display all words in the words resource (coming from OOVs from the corpus add and the new words just added)
ListWordsOptions listWordsOptions = new ListWordsOptions.Builder().customizationId(id).wordType(ListWordsOptions.WordType.ALL).build();
Words words = service.listWords(listWordsOptions).execute();
assertNotNull(words);
} finally {
DeleteLanguageModelOptions deleteOptions = new DeleteLanguageModelOptions.Builder().customizationId(id).build();
service.deleteLanguageModel(deleteOptions).execute();
}
}
use of com.ibm.watson.speech_to_text.v1.model.GetCorpusOptions 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 {
SpeechToText service = new SpeechToText();
service.setUsernameAndPassword("<username>", "<password>");
// 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();
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)).corpusFileContentType(HttpMediaType.TEXT_PLAIN).allowOverwrite(false).build();
service.addCorpus(addOptions).execute();
// Get corpus status
GetCorpusOptions getOptions = new GetCorpusOptions.Builder().customizationId(id).corpusName("corpus-1").build();
for (int x = 0; x < 30 && (service.getCorpus(getOptions).execute()).getStatus() != Status.ANALYZED; x++) {
Thread.sleep(5000);
}
// Get all corpora
ListCorporaOptions listCorporaOptions = new ListCorporaOptions.Builder().customizationId(id).build();
Corpora corpora = service.listCorpora(listCorporaOptions).execute();
System.out.println(corpora);
// Get specific corpus
Corpus corpus = service.getCorpus(getOptions).execute();
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();
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();
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() != LanguageModel.Status.AVAILABLE; x++) {
GetLanguageModelOptions getOptions = new GetLanguageModelOptions.Builder().customizationId(id).build();
myModel = service.getLanguageModel(getOptions).execute();
Thread.sleep(10000);
}
File audio = new File(AUDIO_FILE);
RecognizeOptions recognizeOptionsWithModel = new RecognizeOptions.Builder().model(RecognizeOptions.EN_US_BROADBANDMODEL).customizationId(id).audio(audio).contentType(HttpMediaType.AUDIO_WAV).build();
RecognizeOptions recognizeOptionsWithoutModel = new RecognizeOptions.Builder().model(RecognizeOptions.EN_US_BROADBANDMODEL).audio(audio).contentType(HttpMediaType.AUDIO_WAV).build();
// First decode WITHOUT the custom model
SpeechRecognitionResults transcript = service.recognize(recognizeOptionsWithoutModel).execute();
System.out.println(transcript);
// Now decode with the custom model
transcript = service.recognize(recognizeOptionsWithModel).execute();
System.out.println(transcript);
} finally {
DeleteLanguageModelOptions deleteOptions = new DeleteLanguageModelOptions.Builder().customizationId(id).build();
service.deleteLanguageModel(deleteOptions).execute();
}
}
use of com.ibm.watson.speech_to_text.v1.model.GetCorpusOptions 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();
}
}
use of com.ibm.watson.speech_to_text.v1.model.GetCorpusOptions in project java-sdk by watson-developer-cloud.
the class SpeechToTextIT method testGetCorpus.
/**
* Test get corpus.
*/
@Test
@Ignore
public void testGetCorpus() {
GetCorpusOptions getOptions = new GetCorpusOptions.Builder().corpusName("foo3").customizationId(customizationId).build();
Corpus result = service.getCorpus(getOptions).execute().getResult();
assertNotNull(result);
}
use of com.ibm.watson.speech_to_text.v1.model.GetCorpusOptions in project java-sdk by watson-developer-cloud.
the class SpeechToTextIT method testCreateLanguageModel.
/**
* Test create language model.
*
* <p>Takes a long time to the point of timing out on Travis sometimes, so we'll just run locally.
*
* @throws InterruptedException the interrupted exception
* @throws FileNotFoundException the file not found exception
*/
@Test
@Ignore
public void testCreateLanguageModel() throws InterruptedException, FileNotFoundException {
CreateLanguageModelOptions createOptions = new CreateLanguageModelOptions.Builder().name("java-sdk-temporary").baseModelName(EN_BROADBAND16K).description("Temporary custom model for testing the Java SDK").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(String.format(SPEECH_RESOURCE, "corpus1.txt"))).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);
}
assertTrue(service.getCorpus(getOptions).execute().getResult().getStatus().equals(Corpus.Status.ANALYZED));
// Add the corpus file to the model again and allow overwrite
AddCorpusOptions addOptionsWithOverwrite = new AddCorpusOptions.Builder().customizationId(id).corpusName("corpus-1").corpusFile(new File(String.format(SPEECH_RESOURCE, "corpus1.txt"))).allowOverwrite(true).build();
service.addCorpus(addOptionsWithOverwrite).execute().getResult();
// Get corpus status
for (int x = 0; x < 30 && !service.getCorpus(getOptions).execute().getResult().getStatus().equals(Corpus.Status.ANALYZED); x++) {
Thread.sleep(5000);
}
assertTrue(service.getCorpus(getOptions).execute().getResult().getStatus().equals(Corpus.Status.ANALYZED));
// Get corpora
ListCorporaOptions listCorporaOptions = new ListCorporaOptions.Builder().customizationId(id).build();
Corpora corpora = service.listCorpora(listCorporaOptions).execute().getResult();
assertNotNull(corpora);
assertTrue(corpora.getCorpora().size() == 1);
// 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().getResult();
service.addWord(new AddWordOptions.Builder().customizationId(id).wordName("hhonors").word("hhonors").displayAs("IEEE").addSoundsLike("H. honors").addSoundsLike("Hilton honors").build()).execute().getResult();
service.addWord(new AddWordOptions.Builder().customizationId(id).wordName("aaa").word("aaa").displayAs("aaa").addSoundsLike("aaa").addSoundsLike("bbb").build()).execute().getResult();
service.addWord(new AddWordOptions.Builder().customizationId(id).wordName("bbb").word("bbb").addSoundsLike("aaa").addSoundsLike("bbb").build()).execute().getResult();
service.addWord(new AddWordOptions.Builder().customizationId(id).wordName("ccc").word("ccc").displayAs("ccc").build()).execute().getResult();
service.addWord(new AddWordOptions.Builder().customizationId(id).wordName("ddd").word("ddd").build()).execute().getResult();
service.addWord(new AddWordOptions.Builder().customizationId(id).wordName("eee").word("eee").build()).execute().getResult();
// Display all words in the words resource (coming from OOVs from the corpus add
// and the new
// words just added)
ListWordsOptions listWordsOptions = new ListWordsOptions.Builder().customizationId(id).wordType(ListWordsOptions.WordType.ALL).build();
Words words = service.listWords(listWordsOptions).execute().getResult();
assertNotNull(words);
} finally {
DeleteLanguageModelOptions deleteOptions = new DeleteLanguageModelOptions.Builder().customizationId(id).build();
service.deleteLanguageModel(deleteOptions).execute();
}
}
Aggregations