use of com.google.cloud.speech.v1p1beta1.SpeechAdaptation in project java-speech by googleapis.
the class SpeechAdaptation method speechAdaptation.
public static void speechAdaptation(String uriPath) throws IOException {
// the "close" method on the client to safely clean up any remaining background resources.
try (SpeechClient speechClient = SpeechClient.create()) {
// Provides "hints" to the speech recognizer to favor specific words and phrases in the
// results.
// https://cloud.google.com/speech-to-text/docs/reference/rpc/google.cloud.speech.v1p1beta1#google.cloud.speech.v1p1beta1.SpeechContext
SpeechContext speechContext = SpeechContext.newBuilder().addPhrases("Brooklyn Bridge").setBoost(20.0F).build();
// Configure recognition config to match your audio file.
RecognitionConfig config = RecognitionConfig.newBuilder().setEncoding(RecognitionConfig.AudioEncoding.MP3).setSampleRateHertz(44100).setLanguageCode("en-US").addSpeechContexts(speechContext).build();
// Set the path to your audio file
RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(uriPath).build();
// Make the request
RecognizeRequest request = RecognizeRequest.newBuilder().setConfig(config).setAudio(audio).build();
// Display the results
RecognizeResponse response = speechClient.recognize(request);
for (SpeechRecognitionResult result : response.getResultsList()) {
// First alternative is the most probable result
SpeechRecognitionAlternative alternative = result.getAlternativesList().get(0);
System.out.printf("Transcript: %s\n", alternative.getTranscript());
}
}
}
use of com.google.cloud.speech.v1p1beta1.SpeechAdaptation in project java-speech by googleapis.
the class SpeechModelAdaptationBeta method transcribeWithModelAdaptation.
/**
* Transcribe with model adaptation
*
* @param projectId your project id
* @param location the region
* @param gcsUri the path to the audio file
*/
public static void transcribeWithModelAdaptation(String projectId, String location, String gcsUri, String customClassId, String phraseSetId) throws Exception {
// the "close" method on the client to safely clean up any remaining background resources.
try (AdaptationClient adaptationClient = AdaptationClient.create()) {
// Create `PhraseSet` and `CustomClasses` to create custom lists of similar
// items that are likely to occur in your input data.
// The parent resource where the custom class and phrase set will be created.
LocationName parent = LocationName.of(projectId, location);
// Create the custom class
CreateCustomClassRequest classRequest = CreateCustomClassRequest.newBuilder().setParent(parent.toString()).setCustomClassId(customClassId).setCustomClass(CustomClass.newBuilder().addItems(ClassItem.newBuilder().setValue("sushido")).addItems(ClassItem.newBuilder().setValue("altura")).addItems(ClassItem.newBuilder().setValue("taneda")).build()).build();
CustomClass classResponse = adaptationClient.createCustomClass(classRequest);
// Create the phrase set
CreatePhraseSetRequest phraseRequest = CreatePhraseSetRequest.newBuilder().setParent(parent.toString()).setPhraseSetId(phraseSetId).setPhraseSet(PhraseSet.newBuilder().setBoost(10).addPhrases(Phrase.newBuilder().setValue(String.format("Visit restaurants like %s%n", customClassId))).build()).build();
PhraseSet phraseResponse = adaptationClient.createPhraseSet(phraseRequest);
// Next section shows how to use the newly created custom class and phrase set
// to send a transcription request with speech adaptation
// Speech adaptation configuration
SpeechAdaptation speechAdaptation = SpeechAdaptation.newBuilder().addCustomClasses(classResponse).addPhraseSets(phraseResponse).build();
// the "close" method on the client to safely clean up any remaining background resources.
try (SpeechClient speechClient = SpeechClient.create()) {
// The path to the audio file to transcribe
// gcsUri URI for audio file in Cloud Storage, e.g. gs://[BUCKET]/[FILE]
// Builds the sync recognize request
RecognitionConfig config = RecognitionConfig.newBuilder().setEncoding(AudioEncoding.FLAC).setSampleRateHertz(16000).setLanguageCode("en-US").setAdaptation(// Set the adaptation object
speechAdaptation).build();
RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(gcsUri).build();
// Performs speech recognition on the audio file.
RecognizeResponse response = speechClient.recognize(config, audio);
List<SpeechRecognitionResult> results = response.getResultsList();
for (SpeechRecognitionResult result : results) {
// There can be several alternative transcripts for a given chunk of speech. Just use the
// first (most likely) one here.
SpeechRecognitionAlternative alternative = result.getAlternativesList().get(0);
System.out.printf("Adapted Transcription: %s%n", alternative.getTranscript());
}
}
} catch (ApiException e) {
System.out.println("Client Interaction Error: \n" + e.toString());
}
}
Aggregations