转录本地视频文件中的语音

转录在本地存储的视频中的语音。

代码示例

Go

如需向 Video Intelligence 进行身份验证，请设置应用默认凭据。如需了解详情，请参阅为本地开发环境设置身份验证。

func speechTranscription(w io.Writer, file string) error {
	ctx := context.Background()
	client, err := video.NewClient(ctx)
	if err != nil {
		return err
	}
	defer client.Close()

	fileBytes, err := ioutil.ReadFile(file)
	if err != nil {
		return err
	}

	op, err := client.AnnotateVideo(ctx, &videopb.AnnotateVideoRequest{
		Features: []videopb.Feature{
			videopb.Feature_SPEECH_TRANSCRIPTION,
		},
		VideoContext: &videopb.VideoContext{
			SpeechTranscriptionConfig: &videopb.SpeechTranscriptionConfig{
				LanguageCode:               "en-US",
				EnableAutomaticPunctuation: true,
			},
		},
		InputContent: fileBytes,
	})
	if err != nil {
		return err
	}
	resp, err := op.Wait(ctx)
	if err != nil {
		return err
	}

	// A single video was processed. Get the first result.
	result := resp.AnnotationResults[0]

	for _, transcription := range result.SpeechTranscriptions {
		// The number of alternatives for each transcription is limited by
		// SpeechTranscriptionConfig.MaxAlternatives.
		// Each alternative is a different possible transcription
		// and has its own confidence score.
		for _, alternative := range transcription.GetAlternatives() {
			fmt.Fprintf(w, "Alternative level information:\n")
			fmt.Fprintf(w, "\tTranscript: %v\n", alternative.GetTranscript())
			fmt.Fprintf(w, "\tConfidence: %v\n", alternative.GetConfidence())

			fmt.Fprintf(w, "Word level information:\n")
			for _, wordInfo := range alternative.GetWords() {
				startTime := wordInfo.GetStartTime()
				endTime := wordInfo.GetEndTime()
				fmt.Fprintf(w, "\t%4.1f - %4.1f: %v (speaker %v)\n",
					float64(startTime.GetSeconds())+float64(startTime.GetNanos())*1e-9, // start as seconds
					float64(endTime.GetSeconds())+float64(endTime.GetNanos())*1e-9,     // end as seconds
					wordInfo.GetWord(),
					wordInfo.GetSpeakerTag())
			}
		}
	}

	return nil
}

后续步骤

如需搜索和过滤其他 Google Cloud 产品的代码示例，请参阅 Google Cloud 示例浏览器。