use of com.google.cloud.videointelligence.v1.WordInfo 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);
}
}
}
}
use of com.google.cloud.videointelligence.v1.WordInfo in project java-docs-samples by GoogleCloudPlatform.
the class Recognize method syncRecognizeWords.
/**
* Performs sync recognize and prints word time offsets.
*
* @param fileName the path to a PCM audio file to transcribe get offsets on.
*/
public static void syncRecognizeWords(String fileName) throws Exception {
try (SpeechClient speech = SpeechClient.create()) {
Path path = Paths.get(fileName);
byte[] data = Files.readAllBytes(path);
ByteString audioBytes = ByteString.copyFrom(data);
// Configure request with local raw PCM audio
RecognitionConfig config = RecognitionConfig.newBuilder().setEncoding(AudioEncoding.LINEAR16).setLanguageCode("en-US").setSampleRateHertz(16000).setEnableWordTimeOffsets(true).build();
RecognitionAudio audio = RecognitionAudio.newBuilder().setContent(audioBytes).build();
// Use blocking call to get audio transcript
RecognizeResponse response = speech.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());
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);
}
}
}
}
use of com.google.cloud.videointelligence.v1.WordInfo in project java-docs-samples by GoogleCloudPlatform.
the class Detect method speechTranscription.
// [END video_face_emotions]
// [START video_speech_transcription]
/**
* Transcribe speech from a video stored on GCS.
*
* @param gcsUri the path to the video file to analyze.
*/
public static void speechTranscription(String gcsUri) throws Exception {
// Instantiate a com.google.cloud.videointelligence.v1p1beta1.VideoIntelligenceServiceClient
try (VideoIntelligenceServiceClient client = VideoIntelligenceServiceClient.create()) {
// Set the language code
SpeechTranscriptionConfig config = SpeechTranscriptionConfig.newBuilder().setLanguageCode("en-US").build();
// Set the video context with the above configuration
VideoContext context = VideoContext.newBuilder().setSpeechTranscriptionConfig(config).build();
// Create the request
AnnotateVideoRequest request = AnnotateVideoRequest.newBuilder().setInputUri(gcsUri).addFeatures(Feature.SPEECH_TRANSCRIPTION).setVideoContext(context).build();
// asynchronously perform facial analysis on videos
OperationFuture<AnnotateVideoResponse, AnnotateVideoProgress> response = client.annotateVideoAsync(request);
System.out.println("Waiting for operation to complete...");
// Display the results
for (VideoAnnotationResults results : response.get(180, TimeUnit.SECONDS).getAnnotationResultsList()) {
for (SpeechTranscription speechTranscription : results.getSpeechTranscriptionsList()) {
try {
// Print the transcription
if (speechTranscription.getAlternativesCount() > 0) {
SpeechRecognitionAlternative alternative = speechTranscription.getAlternatives(0);
System.out.printf("Transcript: %s\n", alternative.getTranscript());
System.out.printf("Confidence: %.2f\n", alternative.getConfidence());
System.out.println("Word level information:");
for (WordInfo wordInfo : alternative.getWordsList()) {
double startTime = wordInfo.getStartTime().getSeconds() + wordInfo.getStartTime().getNanos() / 1e9;
double endTime = wordInfo.getEndTime().getSeconds() + wordInfo.getEndTime().getNanos() / 1e9;
System.out.printf("\t%4.2fs - %4.2fs: %s\n", startTime, endTime, wordInfo.getWord());
}
} else {
System.out.println("No transcription found");
}
} catch (IndexOutOfBoundsException ioe) {
System.out.println("Could not retrieve frame: " + ioe.getMessage());
}
}
}
}
}
use of com.google.cloud.videointelligence.v1.WordInfo in project java-speech by googleapis.
the class Recognize method asyncRecognizeWords.
// [END speech_transcribe_async]
// [START speech_transcribe_async_word_time_offsets_gcs]
/**
* 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 FLAC
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);
}
}
}
}
use of com.google.cloud.videointelligence.v1.WordInfo in project java-speech by googleapis.
the class RecognizeBeta method transcribeDiarization.
// [END speech_transcribe_recognition_metadata_beta]
// [START speech_transcribe_diarization_beta]
/**
* Transcribe the given audio file using speaker diarization.
*
* @param fileName the path to an audio file.
*/
public static void transcribeDiarization(String fileName) throws Exception {
Path path = Paths.get(fileName);
byte[] content = Files.readAllBytes(path);
try (SpeechClient speechClient = SpeechClient.create()) {
// Get the contents of the local audio file
RecognitionAudio recognitionAudio = RecognitionAudio.newBuilder().setContent(ByteString.copyFrom(content)).build();
SpeakerDiarizationConfig speakerDiarizationConfig = SpeakerDiarizationConfig.newBuilder().setEnableSpeakerDiarization(true).setMinSpeakerCount(2).setMaxSpeakerCount(2).build();
// Configure request to enable Speaker diarization
RecognitionConfig config = RecognitionConfig.newBuilder().setEncoding(AudioEncoding.LINEAR16).setLanguageCode("en-US").setSampleRateHertz(8000).setDiarizationConfig(speakerDiarizationConfig).build();
// Perform the transcription request
RecognizeResponse recognizeResponse = speechClient.recognize(config, recognitionAudio);
// Speaker Tags are only included in the last result object, which has only one alternative.
SpeechRecognitionAlternative alternative = recognizeResponse.getResults(recognizeResponse.getResultsCount() - 1).getAlternatives(0);
// The alternative is made up of WordInfo objects that contain the speaker_tag.
WordInfo wordInfo = alternative.getWords(0);
int currentSpeakerTag = wordInfo.getSpeakerTag();
// For each word, get all the words associated with one speaker, once the speaker changes,
// add a new line with the new speaker and their spoken words.
StringBuilder speakerWords = new StringBuilder(String.format("Speaker %d: %s", wordInfo.getSpeakerTag(), wordInfo.getWord()));
for (int i = 1; i < alternative.getWordsCount(); i++) {
wordInfo = alternative.getWords(i);
if (currentSpeakerTag == wordInfo.getSpeakerTag()) {
speakerWords.append(" ");
speakerWords.append(wordInfo.getWord());
} else {
speakerWords.append(String.format("\nSpeaker %d: %s", wordInfo.getSpeakerTag(), wordInfo.getWord()));
currentSpeakerTag = wordInfo.getSpeakerTag();
}
}
System.out.println(speakerWords.toString());
}
}
Aggregations