Speech-to-Text 客户端库

<dependencyManagement>
  <dependencies>
    <dependency>
      <groupId>com.google.cloud</groupId>
      <artifactId>libraries-bom</artifactId>
      <version>26.50.0</version>
      <type>pom</type>
      <scope>import</scope>
    </dependency>
  </dependencies>
</dependencyManagement>

<dependencies>
  <dependency>
    <groupId>com.google.cloud</groupId>
    <artifactId>google-cloud-speech</artifactId>
  </dependency>
</dependencies>

implementation 'com.google.cloud:google-cloud-speech:4.48.0'

libraryDependencies += "com.google.cloud" % "google-cloud-speech" % "4.48.0"

// Imports the Google Cloud client library
import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.speech.v2.AutoDetectDecodingConfig;
import com.google.cloud.speech.v2.CreateRecognizerRequest;
import com.google.cloud.speech.v2.OperationMetadata;
import com.google.cloud.speech.v2.RecognitionConfig;
import com.google.cloud.speech.v2.RecognizeRequest;
import com.google.cloud.speech.v2.RecognizeResponse;
import com.google.cloud.speech.v2.Recognizer;
import com.google.cloud.speech.v2.SpeechClient;
import com.google.cloud.speech.v2.SpeechRecognitionAlternative;
import com.google.cloud.speech.v2.SpeechRecognitionResult;
import com.google.protobuf.ByteString;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.util.List;
import java.util.concurrent.ExecutionException;

public class QuickstartSampleV2 {

  public static void main(String[] args) throws IOException, ExecutionException,
      InterruptedException {
    String projectId = "my-project-id";
    String filePath = "path/to/audioFile.raw";
    String recognizerId = "my-recognizer-id";
    quickstartSampleV2(projectId, filePath, recognizerId);
  }

  public static void quickstartSampleV2(String projectId, String filePath, String recognizerId)
      throws IOException, ExecutionException, InterruptedException {

    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (SpeechClient speechClient = SpeechClient.create()) {
      Path path = Paths.get(filePath);
      byte[] data = Files.readAllBytes(path);
      ByteString audioBytes = ByteString.copyFrom(data);

      String parent = String.format("projects/%s/locations/global", projectId);

      // First, create a recognizer
      Recognizer recognizer = Recognizer.newBuilder()
          .setModel("latest_long")
          .addLanguageCodes("en-US")
          .build();

      CreateRecognizerRequest createRecognizerRequest = CreateRecognizerRequest.newBuilder()
          .setParent(parent)
          .setRecognizerId(recognizerId)
          .setRecognizer(recognizer)
          .build();

      OperationFuture<Recognizer, OperationMetadata> operationFuture =
          speechClient.createRecognizerAsync(createRecognizerRequest);
      recognizer = operationFuture.get();

      // Next, create the transcription request
      RecognitionConfig recognitionConfig = RecognitionConfig.newBuilder()
          .setAutoDecodingConfig(AutoDetectDecodingConfig.newBuilder().build())
          .build();

      RecognizeRequest request = RecognizeRequest.newBuilder()
          .setConfig(recognitionConfig)
          .setRecognizer(recognizer.getName())
          .setContent(audioBytes)
          .build();

      RecognizeResponse response = speechClient.recognize(request);
      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.
        if (result.getAlternativesCount() > 0) {
          SpeechRecognitionAlternative alternative = result.getAlternativesList().get(0);
          System.out.printf("Transcription: %s%n", alternative.getTranscript());
        }
      }
    }
  }
}

import os

from google.cloud.speech_v2 import SpeechClient
from google.cloud.speech_v2.types import cloud_speech

PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")


def quickstart_v2(audio_file: str) -> cloud_speech.RecognizeResponse:
    """Transcribe an audio file.
    Args:
        audio_file (str): Path to the local audio file to be transcribed.
    Returns:
        cloud_speech.RecognizeResponse: The response from the recognize request, containing
        the transcription results
    """
    # Reads a file as bytes
    with open(audio_file, "rb") as f:
        audio_content = f.read()

    # Instantiates a client
    client = SpeechClient()

    config = cloud_speech.RecognitionConfig(
        auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
        language_codes=["en-US"],
        model="long",
    )

    request = cloud_speech.RecognizeRequest(
        recognizer=f"projects/{PROJECT_ID}/locations/global/recognizers/_",
        config=config,
        content=audio_content,
    )

    # Transcribes the audio into text
    response = client.recognize(request=request)

    for result in response.results:
        print(f"Transcript: {result.alternatives[0].transcript}")

    return response