Audio File Transcription for Transcribe API Aws == Tekraze.com

audio-transcriptions-aws.java

/********** Step 1 **********************
*********** File Imports ***************/
import com.amazonaws.services.transcribe.AmazonTranscribe;
import com.amazonaws.services.transcribe.AmazonTranscribeClientBuilder;
import com.amazonaws.services.transcribe.model.DeleteTranscriptionJobRequest;
import com.amazonaws.services.transcribe.model.GetTranscriptionJobRequest;
import com.amazonaws.services.transcribe.model.GetTranscriptionJobResult;
import com.amazonaws.services.transcribe.model.LanguageCode;
import com.amazonaws.services.transcribe.model.Media;
import com.amazonaws.services.transcribe.model.StartTranscriptionJobRequest;
import com.amazonaws.services.transcribe.model.StartTranscriptionJobResult;
import com.amazonaws.services.transcribe.model.TranscriptionJob;
import com.amazonaws.services.transcribe.model.TranscriptionJobStatus;
import com.fasterxml.jackson.databind.ObjectMapper;

import okhttp3.OkHttpClient;
import okhttp3.Request;
import okhttp3.Response;

// Check at Another Gist >> https://gist.github.com/balvinder294/fd16a7bd8cf5d9a889161d370cf8ee3f
import dehaze.mvp.service.dto.awstranscribe.TranscriptionResponseDTO;


/*********************************** Step 2***********************************
 ****************  Initialize Trascribe Client *******************************/
     AmazonTranscribe transcribeClient() {
        log.debug("Intialize Transcribe Client");
        BasicAWSCredentials awsCreds = new BasicAWSCredentials(awsAccessKey, awsSecretKey);
        AWSStaticCredentialsProvider awsStaticCredentialsProvider = new AWSStaticCredentialsProvider(awsCreds);
        return AmazonTranscribeClientBuilder.standard().withCredentials(awsStaticCredentialsProvider)
                .withRegion(awsRegion).build();
    }


/***** Step 3*********************************************************************
 * ***************Upload/Delte File to Aws method ***************************************
 ******* You can skip if you already have file in the aws bucket*******/     
    
    AmazonS3 s3Client() {
        log.debug("Intialize AWS S3 Client");
        BasicAWSCredentials awsCreds = new BasicAWSCredentials(awsAccessKey, awsSecretKey);
        AWSStaticCredentialsProvider awsStaticCredentialsProvider = new AWSStaticCredentialsProvider(awsCreds);
        return AmazonS3ClientBuilder.standard().withCredentials(awsStaticCredentialsProvider).withRegion(awsRegion)
                .build();
    }
     
     public void uploadFileToAwsBucket(MultipartFile file) {
        log.debug("Upload file to AWS Bucket {}", file);
        String key = file.getOriginalFilename().replaceAll(" ", "_").toLowerCase();
        try {
            s3Client().putObject(bucketName, key, file.getInputStream(), null);
        } catch (SdkClientException | IOException e) {
            e.printStackTrace();
        }
    }
    
    
        public void deleteFileFromAwsBucket(String fileName) {
        log.debug("Delete File from AWS Bucket {}", fileName);
        String key = fileName.replaceAll(" ", "_").toLowerCase();
        s3Client().deleteObject(bucketName, key);
    }


/*************** Step 4 ******************
 * **** Start Transcription Job Method******/

    StartTranscriptionJobResult startTranscriptionJob(String key) {
        log.debug("Start Transcription Job By Key {}",key);
        Media media = new Media().withMediaFileUri(s3Client().getUrl(bucketName, key).toExternalForm());
        String jobName = key.concat(RandomString.make());
        StartTranscriptionJobRequest startTranscriptionJobRequest = new StartTranscriptionJobRequest()
                .withLanguageCode(LanguageCode.EnUS).withTranscriptionJobName(jobName).withMedia(media);
        StartTranscriptionJobResult startTranscriptionJobResult = transcribeClient()
                .startTranscriptionJob(startTranscriptionJobRequest);
        return startTranscriptionJobResult;
    } 
    
    
    
/**************************Step 5*****************
 * *** Get Transcription Job Result method *********/
 
     GetTranscriptionJobResult getTranscriptionJobResult(String jobName) {
        log.debug("Get Transcription Job Result By Job Name : {}",jobName);
        GetTranscriptionJobRequest getTranscriptionJobRequest = new GetTranscriptionJobRequest()
                .withTranscriptionJobName(jobName);
        Boolean resultFound = false;
        TranscriptionJob transcriptionJob = new TranscriptionJob();
        GetTranscriptionJobResult getTranscriptionJobResult = new GetTranscriptionJobResult();
        while (resultFound == false) {
            getTranscriptionJobResult = transcribeClient().getTranscriptionJob(getTranscriptionJobRequest);
            transcriptionJob = getTranscriptionJobResult.getTranscriptionJob();
            if (transcriptionJob.getTranscriptionJobStatus()
                    .equalsIgnoreCase(TranscriptionJobStatus.COMPLETED.name())) {
                return getTranscriptionJobResult;
            } else if (transcriptionJob.getTranscriptionJobStatus()
                    .equalsIgnoreCase(TranscriptionJobStatus.FAILED.name())) {
                return null;
            } else if (transcriptionJob.getTranscriptionJobStatus()
                    .equalsIgnoreCase(TranscriptionJobStatus.IN_PROGRESS.name())) {
                try {
                    Thread.sleep(15000);
                } catch (InterruptedException e) {
                    log.debug("Interrupted Exception {}", e.getMessage());
                }
            }
        }
        return getTranscriptionJobResult;
    }
    
/******************Step 6 **************************
 *  Download Transcription Result from URI Method *********/
 
    TranscriptionResponseDTO downloadTranscriptionResponse(String uri){
        log.debug("Download Transcription Result from Transcribe URi {}", uri);
        OkHttpClient okHttpClient = new OkHttpClient()
            .newBuilder()
            .connectTimeout(60, TimeUnit.SECONDS)
            .writeTimeout(60, TimeUnit.SECONDS)
            .readTimeout(60, TimeUnit.SECONDS)
            .build();
        Request request = new Request.Builder().url(uri).build();
        Response response;
        try {
            response = okHttpClient.newCall(request).execute();
            String body = response.body().string();
            ObjectMapper objectMapper = new ObjectMapper();
            response.close();
            return objectMapper.readValue(body, TranscriptionResponseDTO.class);
        } catch (IOException e) {
            e.printStackTrace();
        }
        return null;
    }

/***************************** Step 7 *****************************
 * **** Delete Transcription Job Method ************
 * TO delete transcription job after getting result****/

    void deleteTranscriptionJob(String jobName) {
        log.debug("Delete Transcription Job from amazon Transcribe {}",jobName);
        DeleteTranscriptionJobRequest deleteTranscriptionJobRequest = new DeleteTranscriptionJobRequest()
            .withTranscriptionJobName(jobName);
        transcribeClient().deleteTranscriptionJob(deleteTranscriptionJobRequest);
    }



/********************************* Step 8****************************************
 *  Extract Speech Text method that combines all methods to a single method******
 
 ***** You can do skip upload delete methods if you want to just process file in AWs
 * ** by passing key for filename in bucket and create media *****/

    public TranscriptionResponseDTO extractSpeechTextFromVideo(MultipartFile file) {
        log.debug("Request to extract Speech Text from Video : {}",file);
        
        // Upload file to Aws
        uploadFileToAwsBucket(file);
        
        // Create a key that is like name for file and will be used for creating unique name based id for transcription job
        String key = file.getOriginalFilename().replaceAll(" ", "_").toLowerCase();
        
        // Start Transcription Job and get result
        StartTranscriptionJobResult startTranscriptionJobResult = startTranscriptionJob(key);
        
        
        // Get name of job started for the file
        String transcriptionJobName = startTranscriptionJobResult.getTranscriptionJob().getTranscriptionJobName();
        
        // Get result after the procesiing is complete
        GetTranscriptionJobResult getTranscriptionJobResult = getTranscriptionJobResult(transcriptionJobName);
        
        //delete file as processing is done
        deleteFileFromAwsBucket(key);
        
        // Url of result file for transcription
        String transcriptFileUriString = getTranscriptionJobResult.getTranscriptionJob().getTranscript().getTranscriptFileUri();
        
        // Get the transcription response by downloading the file
        TranscriptionResponseDTO transcriptionResponseDTO = downloadTranscriptionResponse(transcriptFileUriString);
        
        //Delete the transcription job after finishing or it will get deleted after 90 days automatically if you do not call
        deleteTranscriptionJob(transcriptionJobName);
        
        return transcriptionResponseDTO;
    }
    
    
    
    //////  For the transcription Response DTO
    //// Check this Url for Gist >> https://gist.github.com/balvinder294/fd16a7bd8cf5d9a889161d370cf8ee3f