转录短音频文件

func recognize(w io.Writer, file string) error {
	ctx := context.Background()

	client, err := speech.NewClient(ctx)
	if err != nil {
		return err
	}
	defer client.Close()

	data, err := os.ReadFile(file)
	if err != nil {
		return err
	}

	// Send the contents of the audio file with the encoding and
	// and sample rate information to be transcripted.
	resp, err := client.Recognize(ctx, &speechpb.RecognizeRequest{
		Config: &speechpb.RecognitionConfig{
			Encoding:        speechpb.RecognitionConfig_LINEAR16,
			SampleRateHertz: 16000,
			LanguageCode:    "en-US",
		},
		Audio: &speechpb.RecognitionAudio{
			AudioSource: &speechpb.RecognitionAudio_Content{Content: data},
		},
	})

	// Print the results.
	for _, result := range resp.Results {
		for _, alt := range result.Alternatives {
			fmt.Fprintf(w, "\"%v\" (confidence=%3f)\n", alt.Transcript, alt.Confidence)
		}
	}
	return nil
}

/**
 * Performs speech recognition on raw PCM audio and prints the transcription.
 *
 * @param fileName the path to a PCM audio file to transcribe.
 */
public static void syncRecognizeFile(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)
            .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());
    }
  }
}

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

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

/**
 * TODO(developer): Uncomment the following lines before running the sample.
 */
// const filename = 'Local path to audio file, e.g. /path/to/audio.raw';
// const encoding = 'Encoding of the audio file, e.g. LINEAR16';
// const sampleRateHertz = 16000;
// const languageCode = 'BCP-47 language code, e.g. en-US';

const config = {
  encoding: encoding,
  sampleRateHertz: sampleRateHertz,
  languageCode: languageCode,
};
const audio = {
  content: fs.readFileSync(filename).toString('base64'),
};

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

// Detects speech in the audio file
const [response] = await client.recognize(request);
const transcription = response.results
  .map(result => result.alternatives[0].transcript)
  .join('\n');
console.log('Transcription: ', transcription);

from google.cloud import speech


def transcribe_file(audio_file: str) -> speech.RecognizeResponse:
    """Transcribe the given audio file.
    Args:
        audio_file (str): Path to the local audio file to be transcribed.
            Example: "resources/audio.wav"
    Returns:
        cloud_speech.RecognizeResponse: The response containing the transcription results
    """
    client = speech.SpeechClient()

    with open(audio_file, "rb") as f:
        audio_content = f.read()

    audio = speech.RecognitionAudio(content=audio_content)
    config = speech.RecognitionConfig(
        encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
        sample_rate_hertz=16000,
        language_code="en-US",
    )

    response = client.recognize(config=config, audio=audio)

    # Each result is for a consecutive portion of the audio. Iterate through
    # them to get the transcripts for the entire audio file.
    for result in response.results:
        # The first alternative is the most likely one for this portion.
        print(f"Transcript: {result.alternatives[0].transcript}")

    return response

func recognizeGCS(w io.Writer, gcsURI string) error {
	ctx := context.Background()

	client, err := speech.NewClient(ctx)
	if err != nil {
		return err
	}
	defer client.Close()

	// Send the request with the URI (gs://...)
	// and sample rate information to be transcripted.
	resp, err := client.Recognize(ctx, &speechpb.RecognizeRequest{
		Config: &speechpb.RecognitionConfig{
			Encoding:        speechpb.RecognitionConfig_LINEAR16,
			SampleRateHertz: 16000,
			LanguageCode:    "en-US",
		},
		Audio: &speechpb.RecognitionAudio{
			AudioSource: &speechpb.RecognitionAudio_Uri{Uri: gcsURI},
		},
	})

	// Print the results.
	for _, result := range resp.Results {
		for _, alt := range result.Alternatives {
			fmt.Fprintf(w, "\"%v\" (confidence=%3f)\n", alt.Transcript, alt.Confidence)
		}
	}
	return nil
}

/**
 * Performs speech recognition on remote FLAC file and prints the transcription.
 *
 * @param gcsUri the path to the remote FLAC audio file to transcribe.
 */
public static void syncRecognizeGcs(String gcsUri) throws Exception {
  // Instantiates a client with GOOGLE_APPLICATION_CREDENTIALS
  try (SpeechClient speech = SpeechClient.create()) {
    // Builds the request for remote FLAC file
    RecognitionConfig config =
        RecognitionConfig.newBuilder()
            .setEncoding(AudioEncoding.FLAC)
            .setLanguageCode("en-US")
            .setSampleRateHertz(16000)
            .build();
    RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(gcsUri).build();

    // Use blocking call for getting 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());
    }
  }
}

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

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

/**
 * TODO(developer): Uncomment the following lines before running the sample.
 */
// const gcsUri = 'gs://my-bucket/audio.raw';
// const encoding = 'Encoding of the audio file, e.g. LINEAR16';
// const sampleRateHertz = 16000;
// const languageCode = 'BCP-47 language code, e.g. en-US';

const config = {
  encoding: encoding,
  sampleRateHertz: sampleRateHertz,
  languageCode: languageCode,
};
const audio = {
  uri: gcsUri,
};

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

// Detects speech in the audio file
const [response] = await client.recognize(request);
const transcription = response.results
  .map(result => result.alternatives[0].transcript)
  .join('\n');
console.log('Transcription: ', transcription);

def transcribe_gcs(audio_uri: str) -> speech.RecognizeResponse:
    """Transcribes the audio file specified by the gcs_uri.
    Args:
        audio_uri (str): The Google Cloud Storage URI of the input audio file.
            E.g., gs://cloud-samples-data/speech/audio.flac
    Returns:
        cloud_speech.RecognizeResponse: The response containing the transcription results
    """
    from google.cloud import speech

    client = speech.SpeechClient()

    audio = speech.RecognitionAudio(uri=audio_uri)
    config = speech.RecognitionConfig(
        encoding=speech.RecognitionConfig.AudioEncoding.FLAC,
        sample_rate_hertz=16000,
        language_code="en-US",
    )

    response = client.recognize(config=config, audio=audio)

    # Each result is for a consecutive portion of the audio. Iterate through
    # them to get the transcripts for the entire audio file.
    for result in response.results:
        # The first alternative is the most likely one for this portion.
        print(f"Transcript: {result.alternatives[0].transcript}")

    return response