Transcribe a local file with auto punctuation

Transcribe a local audio file, including auto punctuation.

Explore further

For detailed documentation that includes this code sample, see the following:

Code sample

Go


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

	client, err := speech.NewClient(ctx)
	if err != nil {
		return fmt.Errorf("NewClient: %v", err)
	}
	defer client.Close()

	// path = "../testdata/commercial_mono.wav"
	data, err := ioutil.ReadFile(path)
	if err != nil {
		return fmt.Errorf("ReadFile: %v", err)
	}

	resp, err := client.Recognize(ctx, &speechpb.RecognizeRequest{
		Config: &speechpb.RecognitionConfig{
			Encoding:        speechpb.RecognitionConfig_LINEAR16,
			SampleRateHertz: 8000,
			LanguageCode:    "en-US",
			// Enable automatic punctuation.
			EnableAutomaticPunctuation: true,
		},
		Audio: &speechpb.RecognitionAudio{
			AudioSource: &speechpb.RecognitionAudio_Content{Content: data},
		},
	})
	if err != nil {
		return fmt.Errorf("Recognize: %v", err)
	}

	for i, result := range resp.Results {
		fmt.Fprintf(w, "%s\n", strings.Repeat("-", 20))
		fmt.Fprintf(w, "Result %d\n", i+1)
		for j, alternative := range result.Alternatives {
			fmt.Fprintf(w, "Alternative %d: %s\n", j+1, alternative.Transcript)
		}
	}
	return nil
}

Java

/**
 * Performs transcription on remote FLAC file and prints the transcription.
 *
 * @param gcsUri the path to the remote FLAC audio file to transcribe.
 */
public static void transcribeGcsWithAutomaticPunctuation(String gcsUri) throws Exception {
  try (SpeechClient speechClient = SpeechClient.create()) {
    // Configure request with raw PCM audio
    RecognitionConfig config =
        RecognitionConfig.newBuilder()
            .setEncoding(AudioEncoding.FLAC)
            .setLanguageCode("en-US")
            .setSampleRateHertz(16000)
            .setEnableAutomaticPunctuation(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());
  }
}

Node.js

// Imports the Google Cloud client library for API
/**
 * TODO(developer): Update client library import to use new
 * version of API when desired features become available
 */

const speech = require('@google-cloud/speech');
const fs = require('fs');

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

/**
 * TODO(developer): Uncomment the following lines before running the sample.
 * Include the sampleRateHertz field in the config object.
 */
// 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,
  languageCode: languageCode,
  enableAutomaticPunctuation: true,
};

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);

PHP

use Google\Cloud\Speech\V1\SpeechClient;
use Google\Cloud\Speech\V1\RecognitionAudio;
use Google\Cloud\Speech\V1\RecognitionConfig;
use Google\Cloud\Speech\V1\RecognitionConfig\AudioEncoding;

/** Uncomment and populate these variables in your code */
// $audioFile = 'path to an audio file';

// change these variables if necessary
$encoding = AudioEncoding::LINEAR16;
$sampleRateHertz = 32000;
$languageCode = 'en-US';

// get contents of a file into a string
$content = file_get_contents($audioFile);

// set string as audio content
$audio = (new RecognitionAudio())
    ->setContent($content);

// set config
$config = (new RecognitionConfig())
    ->setEncoding($encoding)
    ->setSampleRateHertz($sampleRateHertz)
    ->setLanguageCode($languageCode)
    ->setEnableAutomaticPunctuation(true);

// create the speech client
$client = new SpeechClient();

// make the API call
$response = $client->recognize($config, $audio);
$results = $response->getResults();

// print results
foreach ($results as $result) {
    $alternatives = $result->getAlternatives();
    $mostLikely = $alternatives[0];
    $transcript = $mostLikely->getTranscript();
    $confidence = $mostLikely->getConfidence();
    printf('Transcript: %s' . PHP_EOL, $transcript);
    printf('Confidence: %s' . PHP_EOL, $confidence);
}

$client->close();

Python

from google.cloud import speech

client = speech.SpeechClient()

# path = 'resources/commercial_mono.wav'
with io.open(path, "rb") as audio_file:
    content = audio_file.read()

audio = speech.RecognitionAudio(content=content)
config = speech.RecognitionConfig(
    encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
    sample_rate_hertz=8000,
    language_code="en-US",
    # Enable automatic punctuation
    enable_automatic_punctuation=True,
)

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

for i, result in enumerate(response.results):
    alternative = result.alternatives[0]
    print("-" * 20)
    print("First alternative of result {}".format(i))
    print("Transcript: {}".format(alternative.transcript))

Ruby

# audio_file_path = "path/to/audio.wav"

require "google/cloud/speech"

speech = Google::Cloud::Speech.speech

config = {
  encoding:                     :LINEAR16,
  sample_rate_hertz:            8000,
  language_code:                "en-US",
  enable_automatic_punctuation: true
}

audio_file = File.binread audio_file_path
audio      = { content: audio_file }

operation = speech.long_running_recognize config: config, audio: audio

puts "Operation started"

operation.wait_until_done!

raise operation.results.message if operation.error?

results = operation.response.results

results.each_with_index do |result, i|
  alternative = result.alternatives.first
  puts "-" * 20
  puts "First alternative of result #{i}"
  puts "Transcript: #{alternative.transcript}"
end

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.