use of com.google.cloud.videointelligence.v1p1beta1.SpeechRecognitionAlternative in project Saiy-PS by brandall76.
the class RecognitionGoogleCloud method onNext.
/**
* Receives a value from the stream.
* <p>
* <p>Can be called many times but is never called after {@link #onError(Throwable)} or {@link
* #onCompleted()} are called.
* <p>
* <p>Unary calls must invoke onNext at most once. Clients may invoke onNext at most once for
* server streaming calls, but may receive many onNext callbacks. Servers may invoke onNext at
* most once for client streaming calls, but may receive many onNext callbacks.
* <p>
* <p>If an exception is thrown by an implementation the caller is expected to terminate the
* stream by calling {@link #onError(Throwable)} with the caught exception prior to
* propagating it.
*
* @param value the value passed to the stream
*/
@Override
public void onNext(final StreamingRecognizeResponse value) {
if (DEBUG) {
MyLog.i(CLS_NAME, "onNext: " + TextFormat.printToString(value));
}
final StreamingRecognizeResponse.EndpointerType endpointerType = value.getEndpointerType();
switch(endpointerType) {
case START_OF_SPEECH:
if (DEBUG) {
MyLog.i(CLS_NAME, "onNext: START_OF_SPEECH");
}
if (doBeginning.get()) {
doBeginning.set(false);
listener.onBeginningOfSpeech();
}
break;
case END_OF_SPEECH:
if (DEBUG) {
MyLog.i(CLS_NAME, "onNext: END_OF_SPEECH");
}
if (doEnd.get()) {
doEnd.set(false);
stopListening();
}
break;
case END_OF_AUDIO:
if (DEBUG) {
MyLog.i(CLS_NAME, "onNext: END_OF_AUDIO");
}
if (doEnd.get()) {
doEnd.set(false);
stopListening();
}
break;
case END_OF_UTTERANCE:
if (DEBUG) {
MyLog.i(CLS_NAME, "onNext: END_OF_UTTERANCE");
}
if (doEnd.get()) {
doEnd.set(false);
stopListening();
}
break;
case UNRECOGNIZED:
if (DEBUG) {
MyLog.i(CLS_NAME, "onNext: UNRECOGNIZED");
}
break;
case ENDPOINTER_EVENT_UNSPECIFIED:
default:
if (DEBUG) {
MyLog.i(CLS_NAME, "onNext: ENDPOINTER_EVENT_UNSPECIFIED");
}
break;
}
if (doResults.get()) {
if (UtilsList.notNaked(value.getResultsList())) {
partialArray.clear();
resultsArray.clear();
confidenceArray.clear();
bundle.clear();
boolean isFinal = false;
for (final StreamingRecognitionResult recognitionResult : value.getResultsList()) {
if (DEBUG) {
MyLog.i(CLS_NAME, "recognitionResult stability: " + recognitionResult.getStability());
}
isFinal = recognitionResult.getIsFinal();
if (DEBUG) {
MyLog.i(CLS_NAME, "isFinal: " + isFinal);
}
for (final SpeechRecognitionAlternative alternative : recognitionResult.getAlternativesList()) {
if (DEBUG) {
MyLog.i(CLS_NAME, "alternative: " + alternative.getTranscript());
}
if (isFinal) {
resultsArray.add(alternative.getTranscript());
confidenceArray.add(alternative.getConfidence());
} else {
if (partialArray.isEmpty()) {
partialArray.add(alternative.getTranscript());
} else {
partialArray.add(partialArray.get(0) + " " + alternative.getTranscript());
}
}
}
}
doResults.set(!isFinal);
if (isFinal) {
bundle.putStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION, resultsArray);
bundle.putFloatArray(SpeechRecognizer.CONFIDENCE_SCORES, ArrayUtils.toPrimitive(confidenceArray.toArray(new Float[0]), 0.0F));
listener.onResults(bundle);
stopListening();
} else {
bundle.putStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION, partialArray);
listener.onPartialResults(bundle);
}
} else {
if (DEBUG) {
MyLog.i(CLS_NAME, "onNext: results list naked");
}
}
} else {
if (DEBUG) {
MyLog.i(CLS_NAME, "onNext: doResults false");
}
}
}
use of com.google.cloud.videointelligence.v1p1beta1.SpeechRecognitionAlternative in project java-docs-samples by GoogleCloudPlatform.
the class QuickstartSample method main.
/**
* Demonstrates using the Speech API to transcribe an audio file.
*/
public static void main(String... args) throws Exception {
// Instantiates a client
try (SpeechClient speechClient = SpeechClient.create()) {
// The path to the audio file to transcribe
String fileName = "./resources/audio.raw";
// Reads the audio file into memory
Path path = Paths.get(fileName);
byte[] data = Files.readAllBytes(path);
ByteString audioBytes = ByteString.copyFrom(data);
// Builds the sync recognize request
RecognitionConfig config = RecognitionConfig.newBuilder().setEncoding(AudioEncoding.LINEAR16).setSampleRateHertz(16000).setLanguageCode("en-US").build();
RecognitionAudio audio = RecognitionAudio.newBuilder().setContent(audioBytes).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("Transcription: %s%n", alternative.getTranscript());
}
}
}
use of com.google.cloud.videointelligence.v1p1beta1.SpeechRecognitionAlternative in project java-docs-samples by GoogleCloudPlatform.
the class Recognize method asyncRecognizeGcs.
/**
* Performs non-blocking speech recognition on remote FLAC file and prints
* the transcription.
*
* @param gcsUri the path to the remote LINEAR16 audio file to transcribe.
*/
public static void asyncRecognizeGcs(String gcsUri) throws Exception {
// Instantiates a client with GOOGLE_APPLICATION_CREDENTIALS
try (SpeechClient speech = SpeechClient.create()) {
// Configure remote file request for Linear16
RecognitionConfig config = RecognitionConfig.newBuilder().setEncoding(AudioEncoding.FLAC).setLanguageCode("en-US").setSampleRateHertz(16000).build();
RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(gcsUri).build();
// Use non-blocking call for getting file transcription
OperationFuture<LongRunningRecognizeResponse, LongRunningRecognizeMetadata> response = speech.longRunningRecognizeAsync(config, audio);
while (!response.isDone()) {
System.out.println("Waiting for response...");
Thread.sleep(10000);
}
List<SpeechRecognitionResult> results = response.get().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("Transcription: %s\n", alternative.getTranscript());
}
}
}
use of com.google.cloud.videointelligence.v1p1beta1.SpeechRecognitionAlternative in project java-docs-samples by GoogleCloudPlatform.
the class Recognize method transcribeModelSelectionGcs.
// [START speech_transcribe_model_selection_gcs]
/**
* Performs transcription of the remote audio file asynchronously with
* the selected model.
* @param gcsUri the path to the remote audio file to transcribe.
*/
public static void transcribeModelSelectionGcs(String gcsUri) throws Exception {
try (SpeechClient speech = SpeechClient.create()) {
// Configure request with video media type
RecognitionConfig config = RecognitionConfig.newBuilder().setEncoding(AudioEncoding.LINEAR16).setLanguageCode("en-US").setSampleRateHertz(16000).setModel("video").build();
RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(gcsUri).build();
// Use non-blocking call for getting file transcription
OperationFuture<LongRunningRecognizeResponse, LongRunningRecognizeMetadata> response = speech.longRunningRecognizeAsync(config, audio);
while (!response.isDone()) {
System.out.println("Waiting for response...");
Thread.sleep(10000);
}
List<SpeechRecognitionResult> results = response.get().getResultsList();
// Just print the first result here.
SpeechRecognitionResult result = results.get(0);
// 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("Transcript : %s\n", alternative.getTranscript());
}
// [END speech_transcribe_model_selection_gcs]
}
use of com.google.cloud.videointelligence.v1p1beta1.SpeechRecognitionAlternative in project java-docs-samples by GoogleCloudPlatform.
the class Recognize method asyncRecognizeWords.
/**
* Performs non-blocking speech recognition on remote FLAC file and prints
* the transcription as well as word time offsets.
*
* @param gcsUri the path to the remote LINEAR16 audio file to transcribe.
*/
public static void asyncRecognizeWords(String gcsUri) throws Exception {
// Instantiates a client with GOOGLE_APPLICATION_CREDENTIALS
try (SpeechClient speech = SpeechClient.create()) {
// Configure remote file request for Linear16
RecognitionConfig config = RecognitionConfig.newBuilder().setEncoding(AudioEncoding.FLAC).setLanguageCode("en-US").setSampleRateHertz(16000).setEnableWordTimeOffsets(true).build();
RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(gcsUri).build();
// Use non-blocking call for getting file transcription
OperationFuture<LongRunningRecognizeResponse, LongRunningRecognizeMetadata> response = speech.longRunningRecognizeAsync(config, audio);
while (!response.isDone()) {
System.out.println("Waiting for response...");
Thread.sleep(10000);
}
List<SpeechRecognitionResult> results = response.get().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("Transcription: %s\n", alternative.getTranscript());
for (WordInfo wordInfo : alternative.getWordsList()) {
System.out.println(wordInfo.getWord());
System.out.printf("\t%s.%s sec - %s.%s sec\n", wordInfo.getStartTime().getSeconds(), wordInfo.getStartTime().getNanos() / 100000000, wordInfo.getEndTime().getSeconds(), wordInfo.getEndTime().getNanos() / 100000000);
}
}
}
}
Aggregations