Speech-to-Text 客户端库

使用集合让一切井井有条 根据您的偏好保存内容并对其进行分类。
}

本页面介绍如何开始使用 Speech-to-Text API 的 Cloud 客户端库。如需详细了解 Cloud API 的客户端库(包括旧版 Google API 客户端库),请参阅客户端库说明

安装客户端库

C#

如需了解详情,请参阅设置 C# 开发环境

如果您使用的是 Visual Studio 2017 或更高版本,请打开 nuget 软件包管理器窗口并输入以下内容:

Install-Package Google.Apis

如果您使用 .NET Core 命令行界面工具来安装依赖项,请运行以下命令:

dotnet add package Google.Apis

Go

如需了解详情,请参阅设置 Go 开发环境

go get cloud.google.com/go/speech/apiv1

Java

如需了解详情,请参阅设置 Java 开发环境

如果您使用的是 Maven,请将以下代码添加到您的 pom.xml 文件中。如需详细了解 BOM,请参阅 Google Cloud Platform 库 BOM

<dependencyManagement>
  <dependencies>
    <dependency>
      <groupId>com.google.cloud</groupId>
      <artifactId>libraries-bom</artifactId>
      <version>26.1.3</version>
      <type>pom</type>
      <scope>import</scope>
    </dependency>
  </dependencies>
</dependencyManagement>

<dependencies>
  <dependency>
      <groupId>org.json</groupId>
      <artifactId>json</artifactId>
      <version>20220924</version>
  </dependency>
  <dependency>
    <groupId>com.google.cloud</groupId>
    <artifactId>google-cloud-speech</artifactId>
  </dependency>
</dependencies>

如果您使用的是 Gradle,请将以下代码添加到您的依赖项中:

implementation platform('com.google.cloud:libraries-bom:26.1.3')

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

如果您使用的是 sbt,请将以下代码添加到您的依赖项中:

libraryDependencies += "com.google.cloud" % "google-cloud-speech" % "2.6.1"

如果您使用的是 Visual Studio Code、IntelliJ 或 Eclipse,可以通过以下 IDE 插件将客户端库添加到您的项目中:

上述插件还提供其他功能,例如服务帐号密钥管理。如需了解详情,请参阅各个插件相应的文档。

Node.js

如需了解详情,请参阅设置 Node.js 开发环境

npm install --save @google-cloud/speech

PHP

如需了解详情,请参阅在 Google Cloud 上使用 PHP

composer require google/apiclient

Python

如需了解详情,请参阅设置 Python 开发环境

pip install --upgrade google-cloud-speech

Ruby

如需了解详情,请参阅设置 Ruby 开发环境

gem install google-api-client

设置身份验证

使用客户端库时,您可以使用应用默认凭据 (ADC) 进行身份验证。如需了解如何设置 ADC,请参阅为应用默认凭据提供凭据。如需了解如何将 ADC 与客户端库搭配使用,请参阅使用客户端库进行身份验证

使用客户端库

以下示例展示了如何使用客户端库。

Go


// Sample speech-quickstart uses the Google Cloud Speech API to transcribe
// audio.
package main

import (
	"context"
	"fmt"
	"log"

	speech "cloud.google.com/go/speech/apiv1"
	"cloud.google.com/go/speech/apiv1/speechpb"
)

func main() {
	ctx := context.Background()

	// Creates a client.
	client, err := speech.NewClient(ctx)
	if err != nil {
		log.Fatalf("Failed to create client: %v", err)
	}
	defer client.Close()

	// The path to the remote audio file to transcribe.
	fileURI := "gs://cloud-samples-data/speech/brooklyn_bridge.raw"

	// Detects speech in the audio file.
	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: fileURI},
		},
	})
	if err != nil {
		log.Fatalf("failed to recognize: %v", err)
	}

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

Java

// Imports the Google Cloud client library
import com.google.cloud.speech.v1.RecognitionAudio;
import com.google.cloud.speech.v1.RecognitionConfig;
import com.google.cloud.speech.v1.RecognitionConfig.AudioEncoding;
import com.google.cloud.speech.v1.RecognizeResponse;
import com.google.cloud.speech.v1.SpeechClient;
import com.google.cloud.speech.v1.SpeechRecognitionAlternative;
import com.google.cloud.speech.v1.SpeechRecognitionResult;
import java.util.List;

public class QuickstartSample {

  /** Demonstrates using the Speech API to transcribe an audio file. */
  public static void main(String... args) throws Exception {
    // Instantiates a client
    try (SpeechClient speechClient = SpeechClient.create()) {

      // The path to the audio file to transcribe
      String gcsUri = "gs://cloud-samples-data/speech/brooklyn_bridge.raw";

      // Builds the sync recognize request
      RecognitionConfig config =
          RecognitionConfig.newBuilder()
              .setEncoding(AudioEncoding.LINEAR16)
              .setSampleRateHertz(16000)
              .setLanguageCode("en-US")
              .build();
      RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(gcsUri).build();

      // Performs speech recognition on the audio file
      RecognizeResponse response = speechClient.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());
      }
    }
  }
}

Node.js

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

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

async function quickstart() {
  // The path to the remote LINEAR16 file
  const gcsUri = 'gs://cloud-samples-data/speech/brooklyn_bridge.raw';

  // The audio file's encoding, sample rate in hertz, and BCP-47 language code
  const audio = {
    uri: gcsUri,
  };
  const config = {
    encoding: 'LINEAR16',
    sampleRateHertz: 16000,
    languageCode: 'en-US',
  };
  const request = {
    audio: audio,
    config: config,
  };

  // 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}`);
}
quickstart();

Python


# Imports the Google Cloud client library
from google.cloud import speech

# Instantiates a client
client = speech.SpeechClient()

# The name of the audio file to transcribe
gcs_uri = "gs://cloud-samples-data/speech/brooklyn_bridge.raw"

audio = speech.RecognitionAudio(uri=gcs_uri)

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

# Detects speech in the audio file
response = client.recognize(config=config, audio=audio)

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

其他资源