Selecciona un modelo de transcripción

En esta página, se describe cómo usar un modelo de aprendizaje automático específico para las solicitudes de transcripción de audio a Speech-to-Text.

Modelos de transcripción

Speech-to-Text detecta palabras en un clip de audio mediante la comparación de los datos de entrada en uno de muchos modelos de aprendizaje automático. Cada modelo se ha entrenado mediante el análisis de millones de ejemplos, en este caso, muchísimas grabaciones de audio de personas hablando.

En Speech-to-Text, hay modelos especializados entrenados con audio proveniente de fuentes específicas, como llamadas telefónicas o videos. Debido a este proceso de entrenamiento, estos modelos especializados brindan mejores resultados cuando se aplican a tipos similares de datos de audio.

Por ejemplo, en Speech-to-Text hay un modelo de transcripción entrenado para reconocer la voz capturada en un teléfono. Cuando en Speech-to-Text se usa este modelo para transcribir el audio del teléfono, los resultados son mucho mejores que los de otros modelos.

En la siguiente tabla, se muestran los modelos de transcripción disponibles para usar con Speech-to-Text.

Nombre del modelo Descripción
command_and_search La mejor opción para expresiones cortas o de una sola palabra, como comandos por voz o búsqueda por voz.
phone_call La mejor opción para audios que pertenecen a una llamada telefónica (en general, grabada con una tasa de muestreo de 8 khz).
video

La mejor opción para audios provenientes de videos o que incluyen a más de una persona hablando. Idealmente, este audio está grabado con una tasa de muestreo de 16 khz o superior.

Este es un modelo premium que cuesta más que la tarifa estándar. Consulta la página de precios para obtener más detalles.

default La mejor opción para los audios no incluidos en los demás modelos, como audios largos y dictados. Idealmente, este audio es de alta fidelidad y está grabado con una tasa de muestreo de 16 khz o superior.

Selecciona un modelo para la transcripción de audio

A fin de especificar un modelo específico para la transcripción de audio, debes configurar el campo model con uno de los valores permitidos: video, phone_call, command_and_search o default, en los parámetros RecognitionConfig de la solicitud. En Speech-to-Text, se admite la selección de modelos para todos los métodos de reconocimiento de voz: speech:recognize, speech:longrunningrecognize y transmisión.

Realiza la transcripción de un archivo de audio local

Protocolo

Consulta el extremo de la API de [speech:recognize] para obtener todos los detalles.

Para realizar un reconocimiento de voz síncrono, haz una solicitud POST y proporciona el cuerpo de la solicitud apropiado. A continuación, se muestra un ejemplo de una solicitud POST con curl. En el ejemplo, se utiliza el token de acceso correspondiente a la configuración de una cuenta de servicio para el proyecto con el SDK de Cloud de Google Cloud. Si deseas obtener instrucciones para instalar el SDK de Cloud, configurar un proyecto con una cuenta de servicio y conseguir un token de acceso, consulta la guía de inicio rápido.

curl -s -H "Content-Type: application/json" \
    -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
    https://speech.googleapis.com/v1/speech:recognize \
    --data '{
    "config": {
        "encoding": "LINEAR16",
        "sampleRateHertz": 16000,
        "languageCode": "en-US",
        "model": "video"
    },
    "audio": {
        "uri": "gs://cloud-samples-tests/speech/Google_Gnome.wav"
    }
}'

Consulta la documentación de referencia de RecognitionConfig para obtener más información sobre la configuración del cuerpo de la solicitud.

Si la solicitud se completa correctamente, el servidor muestra un código de estado HTTP 200 OK y la respuesta en formato JSON:

{
  "results": [
    {
      "alternatives": [
        {
          "transcript": "OK Google stream stranger things from
            Netflix to my TV okay stranger things from
            Netflix playing on TV from the people that brought you
            Google home comes the next evolution of the smart home
            and it's just outside your window me Google know hi
            how can I help okay no what's the weather like outside
            the weather outside is sunny and 76 degrees he's right
            okay no turn on the hose I'm holding sure okay no I'm can
            I eat this lemon tree leaf yes what about this Daisy yes
            but I wouldn't recommend it but I could eat it okay
            Nomad milk to my shopping list I'm sorry that sounds like
            an indoor request I keep doing that sorry you do keep
            doing that okay no is this compost really we're all
            compost if you think about it pretty much everything is
            made up of organic matter and will return",
          "confidence": 0.9251011
        }
      ]
    }
  ]
}

C#

static object SyncRecognizeModelSelection(string filePath, string model)
{
    var speech = SpeechClient.Create();
    var response = speech.Recognize(new RecognitionConfig()
    {
        Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
        SampleRateHertz = 16000,
        LanguageCode = "en",
        // The `model` value must be one of the following:
        // "video", "phone_call", "command_and_search", "default"
        Model = model
    }, RecognitionAudio.FromFile(filePath));
    foreach (var result in response.Results)
    {
        foreach (var alternative in result.Alternatives)
        {
            Console.WriteLine(alternative.Transcript);
        }
    }
    return 0;
}

Go


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

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

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

	req := &speechpb.RecognizeRequest{
		Config: &speechpb.RecognitionConfig{
			Encoding:        speechpb.RecognitionConfig_LINEAR16,
			SampleRateHertz: 16000,
			LanguageCode:    "en-US",
			Model:           "video",
		},
		Audio: &speechpb.RecognitionAudio{
			AudioSource: &speechpb.RecognitionAudio_Content{Content: data},
		},
	}

	resp, err := client.Recognize(ctx, req)
	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 of the given audio file synchronously with the selected model.
 *
 * @param fileName the path to a audio file to transcribe
 */
public static void transcribeModelSelection(String fileName) throws Exception {
  Path path = Paths.get(fileName);
  byte[] content = Files.readAllBytes(path);

  try (SpeechClient speech = SpeechClient.create()) {
    // Configure request with video media type
    RecognitionConfig recConfig =
        RecognitionConfig.newBuilder()
            // encoding may either be omitted or must match the value in the file header
            .setEncoding(AudioEncoding.LINEAR16)
            .setLanguageCode("en-US")
            // sample rate hertz may be either be omitted or must match the value in the file
            // header
            .setSampleRateHertz(16000)
            .setModel("video")
            .build();

    RecognitionAudio recognitionAudio =
        RecognitionAudio.newBuilder().setContent(ByteString.copyFrom(content)).build();

    RecognizeResponse recognizeResponse = speech.recognize(recConfig, recognitionAudio);
    // Just print the first result here.
    SpeechRecognitionResult result = recognizeResponse.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);
    System.out.printf("Transcript : %s\n", alternative.getTranscript());
  }
}

Node.js

// Imports the Google Cloud client library for Beta API
/**
 * TODO(developer): Update client library import to use new
 * version of API when desired features become available
 */
const speech = require('@google-cloud/speech').v1p1beta1;
const fs = require('fs');

// 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 model = 'Model to use, e.g. phone_call, video, default';
// 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,
  model: model,
};
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';
// $model = 'video';

// 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)
    ->setModel($model);

// 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_v1
import io

def sample_recognize(local_file_path, model):
    """
    Transcribe a short audio file using a specified transcription model

    Args:
      local_file_path Path to local audio file, e.g. /path/audio.wav
      model The transcription model to use, e.g. video, phone_call, default
      For a list of available transcription models, see:
      https://cloud.google.com/speech-to-text/docs/transcription-model#transcription_models
    """

    client = speech_v1.SpeechClient()

    # local_file_path = 'resources/hello.wav'
    # model = 'phone_call'

    # The language of the supplied audio
    language_code = "en-US"
    config = {"model": model, "language_code": language_code}
    with io.open(local_file_path, "rb") as f:
        content = f.read()
    audio = {"content": content}

    response = client.recognize(config, audio)
    for result in response.results:
        # First alternative is the most probable result
        alternative = result.alternatives[0]
        print(u"Transcript: {}".format(alternative.transcript))

Ruby

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

require "google/cloud/speech"

speech = Google::Cloud::Speech.speech

config = {
  encoding:          :LINEAR16,
  sample_rate_hertz: 16_000,
  language_code:     "en-US",
  model:             model
}

file  = File.binread file_path
audio = { content: 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

Realiza la transcripción de un archivo de audio de Google Cloud Storage

Java

/**
 * Performs transcription of the remote audio file asynchronously with the selected model.
 *
 * @param gcsUri the path to the remote audio file to transcribe.
 */
public static void transcribeModelSelectionGcs(String gcsUri) throws Exception {
  try (SpeechClient speech = SpeechClient.create()) {

    // Configure request with video media type
    RecognitionConfig config =
        RecognitionConfig.newBuilder()
            // encoding may either be omitted or must match the value in the file header
            .setEncoding(AudioEncoding.LINEAR16)
            .setLanguageCode("en-US")
            // sample rate hertz may be either be omitted or must match the value in the file
            // header
            .setSampleRateHertz(16000)
            .setModel("video")
            .build();

    RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(gcsUri).build();

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

    while (!response.isDone()) {
      System.out.println("Waiting for response...");
      Thread.sleep(10000);
    }

    List<SpeechRecognitionResult> results = response.get().getResultsList();

    // Just print the first result here.
    SpeechRecognitionResult result = results.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);
    System.out.printf("Transcript : %s\n", alternative.getTranscript());
  }
}

Node.js

// Imports the Google Cloud client library for Beta API
/**
 * TODO(developer): Update client library import to use new
 * version of API when desired features become available
 */
const speech = require('@google-cloud/speech').v1p1beta1;

// 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 model = 'Model to use, e.g. phone_call, video, default';
// 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,
  model: model,
};
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);

Python

from google.cloud import speech_v1

def sample_recognize(storage_uri, model):
    """
    Transcribe a short audio file from Cloud Storage using a specified
    transcription model

    Args:
      storage_uri URI for audio file in Cloud Storage, e.g. gs://[BUCKET]/[FILE]
      model The transcription model to use, e.g. video, phone_call, default
      For a list of available transcription models, see:
      https://cloud.google.com/speech-to-text/docs/transcription-model#transcription_models
    """

    client = speech_v1.SpeechClient()

    # storage_uri = 'gs://cloud-samples-data/speech/hello.wav'
    # model = 'phone_call'

    # The language of the supplied audio
    language_code = "en-US"
    config = {"model": model, "language_code": language_code}
    audio = {"uri": storage_uri}

    response = client.recognize(config, audio)
    for result in response.results:
        # First alternative is the most probable result
        alternative = result.alternatives[0]
        print(u"Transcript: {}".format(alternative.transcript))