使用增强型模型识别语音

本页面介绍了当您向 Speech-to-Text 发送转录请求时,如何请求增强型语音识别模型。

目前有两种增强型模型:电话视频。这些模型经过优化,可以更准确地转录来自这些特定来源的音频数据。如需了解增强型模型是否支持您的语言,请参阅受支持的语言页面

Google 会根据通过数据日志记录计划收集的数据创建并改进增强型模型。虽然使用增强型模型不要求选择加入数据日志记录计划,但是如果您选择加入,则可以帮助 Google 改进这些模型,并享受使用费折扣。

如需使用增强型识别模型,请在 RecognitionConfig 中设置以下字段:

  1. useEnhanced 设置为 true
  2. model 字段中传递 phone_callvideo 字符串。

Speech-to-Text 的增强型模型支持以下所有语音识别方法:speech:recognizespeech:longrunningrecognize流式

以下代码示例演示如何要求使用增强型模型进行转录。

协议

如需了解完整的详细信息,请参阅 speech:recognize API 端点。

如需执行同步语音识别,请发出 POST 请求并提供相应的请求正文。以下示例展示了一个使用 curl 发出的 POST 请求。该示例使用通过 Google Cloud Cloud SDK 为项目设置的服务帐号的访问令牌。如需了解有关安装 Cloud SDK、建立项目和服务帐号以及获取访问令牌的说明,请参阅快速入门

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",
        "languageCode": "en-US",
        "enableWordTimeOffsets": false,
        "enableAutomaticPunctuation": true,
        "model": "phone_call",
        "useEnhanced": true
    },
    "audio": {
        "uri": "gs://cloud-samples-tests/speech/commercial_mono.wav"
    }
}'

如需详细了解如何配置请求正文,请参阅 RecognitionConfig 参考文档。

如果请求成功,服务器将返回一个 200 OK HTTP 状态代码以及 JSON 格式的响应。

{
  "results": [
    {
      "alternatives": [
        {
          "transcript": "Hi, I'd like to buy a Chromecast. I was wondering whether you could help me with that.",
          "confidence": 0.8930228
        }
      ],
      "resultEndTime": "5.640s"
    },
    {
      "alternatives": [
        {
          "transcript": " Certainly, which color would you like? We are blue black and red.",
          "confidence": 0.9101991
        }
      ],
      "resultEndTime": "10.220s"
    },
    {
      "alternatives": [
        {
          "transcript": " Let's go with the black one.",
          "confidence": 0.8818244
        }
      ],
      "resultEndTime": "13.870s"
    },
    {
      "alternatives": [
        {
          "transcript": " Would you like the new Chromecast Ultra model or the regular Chromecast?",
          "confidence": 0.94733626
        }
      ],
      "resultEndTime": "18.460s"
    },
    {
      "alternatives": [
        {
          "transcript": " Regular Chromecast is fine. Thank you. Okay. Sure. Would you like to ship it regular or Express?",
          "confidence": 0.9519095
        }
      ],
      "resultEndTime": "25.930s"
    },
    {
      "alternatives": [
        {
          "transcript": " Express, please.",
          "confidence": 0.9101229
        }
      ],
      "resultEndTime": "28.260s"
    },
    {
      "alternatives": [
        {
          "transcript": " Terrific. It's on the way. Thank you. Thank you very much. Bye.",
          "confidence": 0.9321616
        }
      ],
      "resultEndTime": "34.150s"
    }
 ]
}

Go


func enhancedModel(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",
			UseEnhanced:     true,
			// A model must be specified to use enhanced model.
			Model: "phone_call",
		},
		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
}

Python

import io

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",
    use_enhanced=True,
    # A model must be specified to use enhanced model.
    model="phone_call",
)

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))

Java

/**
 * Transcribe the given audio file using an enhanced model.
 *
 * @param fileName the path to an audio file.
 */
public static void transcribeFileWithEnhancedModel(String fileName) throws Exception {
  Path path = Paths.get(fileName);
  byte[] content = Files.readAllBytes(path);

  try (SpeechClient speechClient = SpeechClient.create()) {
    // Get the contents of the local audio file
    RecognitionAudio recognitionAudio =
        RecognitionAudio.newBuilder().setContent(ByteString.copyFrom(content)).build();

    // Configure request to enable enhanced models
    RecognitionConfig config =
        RecognitionConfig.newBuilder()
            .setEncoding(AudioEncoding.LINEAR16)
            .setLanguageCode("en-US")
            .setSampleRateHertz(8000)
            .setUseEnhanced(true)
            // A model must be specified to use enhanced model.
            .setModel("phone_call")
            .build();

    // Perform the transcription request
    RecognizeResponse recognizeResponse = speechClient.recognize(config, recognitionAudio);

    // Print out the results
    for (SpeechRecognitionResult result : recognizeResponse.getResultsList()) {
      // There can be several alternative transcripts for a given chunk of speech. Just use the
      // first (most likely) one here.
      SpeechRecognitionAlternative alternative = result.getAlternatives(0);
      System.out.format("Transcript: %s\n\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 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,
  useEnhanced: true,
  model: 'phone_call',
};
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);
response.results.forEach(result => {
  const alternative = result.alternatives[0];
  console.log(alternative.transcript);
});

其他语言

C#:请按照客户端库页面上的 C# 设置说明操作,然后访问 .NET 的 Speech-to-Text 参考文档

PHP:请按照客户端库页面上的 PHP 设置说明 操作,然后访问 PHP 的 Speech-to-Text 参考文档

Ruby:请按照客户端库页面上的 Ruby 设置说明操作,然后访问 Ruby 的 Speech-to-Text 参考文档

后续步骤

查看如何发出同步转录请求