use of com.google.cloud.videointelligence.v1p1beta1.SpeechTranscriptionConfig 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());
}
}
}
}
}
Aggregations