Transcribe a file in Cloud Storage with word-level confidence (beta)

/**
 * Transcribe a remote audio file with word level confidence
 *
 * @param gcsUri path to the remote audio file
 */
public static void transcribeWordLevelConfidenceGcs(String gcsUri) throws Exception {
  try (SpeechClient speechClient = SpeechClient.create()) {

    // Configure request to enable word level confidence
    RecognitionConfig config =
        RecognitionConfig.newBuilder()
            .setEncoding(AudioEncoding.FLAC)
            .setSampleRateHertz(44100)
            .setLanguageCode("en-US")
            .setEnableWordConfidence(true)
            .build();

    // Set the remote path for the audio file
    RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(gcsUri).build();

    // Use non-blocking call for getting file transcription
    OperationFuture<LongRunningRecognizeResponse, LongRunningRecognizeMetadata> response =
        speechClient.longRunningRecognizeAsync(config, audio);

    while (!response.isDone()) {
      System.out.println("Waiting for response...");
      Thread.sleep(10000);
    }
    // Just print the first result here.
    SpeechRecognitionResult result = response.get().getResultsList().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);
    // Print out the result
    System.out.printf("Transcript : %s\n", alternative.getTranscript());
    System.out.format(
        "First Word and Confidence : %s %s \n",
        alternative.getWords(0).getWord(), alternative.getWords(0).getConfidence());
  }
}

// Imports the Google Cloud client library
const speech = require('@google-cloud/speech').v1p1beta1;

// Creates a client
const client = new speech.SpeechClient();

/**
 * TODO(developer): Uncomment the following line before running the sample.
 */
// const uri = path to GCS audio file e.g. `gs:/bucket/audio.wav`;

const config = {
  encoding: 'FLAC',
  sampleRateHertz: 16000,
  languageCode: 'en-US',
  enableWordConfidence: true,
};

const audio = {
  uri: gcsUri,
};

const request = {
  config: config,
  audio: audio,
};

const [response] = await client.recognize(request);
const transcription = response.results
  .map(result => result.alternatives[0].transcript)
  .join('\n');
const confidence = response.results
  .map(result => result.alternatives[0].confidence)
  .join('\n');
console.log(`Transcription: ${transcription} \n Confidence: ${confidence}`);

console.log('Word-Level-Confidence:');
const words = response.results.map(result => result.alternatives[0]);
words[0].words.forEach(a => {
  console.log(` word: ${a.word}, confidence: ${a.confidence}`);
});

from google.cloud import speech_v1p1beta1 as speech


def transcribe_file_with_word_level_confidence(audio_uri: str) -> str:
    """Transcribe a remote audio file with word level confidence.
    Args:
        audio_uri (str): The Cloud Storage URI of the input audio.
            E.g., gs://[BUCKET]/[FILE]
    Returns:
        The generated transcript from the audio file provided with word level confidence.
    """

    client = speech.SpeechClient()

    # Configure request to enable word level confidence
    config = speech.RecognitionConfig(
        encoding=speech.RecognitionConfig.AudioEncoding.FLAC,
        sample_rate_hertz=44100,
        language_code="en-US",
        enable_word_confidence=True,  # Enable word level confidence
    )

    # Set the remote path for the audio file
    audio = speech.RecognitionAudio(uri=audio_uri)

    # Use non-blocking call for getting file transcription
    response = client.long_running_recognize(config=config, audio=audio).result(
        timeout=300
    )

    transcript_builder = []
    for i, result in enumerate(response.results):
        alternative = result.alternatives[0]
        transcript_builder.append("-" * 20)
        transcript_builder.append(f"\nFirst alternative of result {i}")
        transcript_builder.append(f"\nTranscript: {alternative.transcript}")
        transcript_builder.append(
            "\nFirst Word and Confidence: ({}, {})".format(
                alternative.words[0].word, alternative.words[0].confidence
            )
        )

    transcript = "".join(transcript_builder)
    print(transcript)

    return transcript