gcp_stt.go

// Refer https://github.com/kkdai/linebot-video-gcp for more detail.

// Must use "apiv1p1beta1" version to enable support on Chinese and MP3
speech "cloud.google.com/go/speech/apiv1p1beta1" //v1p1beta1
speechpb "google.golang.org/genproto/googleapis/cloud/speech/v1p1beta1" //v1p1beta1


func (c *ClientUploader) SpeachToText() (error, string) {
	ctx := context.Background()

	ctx, cancel := context.WithTimeout(ctx, time.Second*50)
	defer cancel()
	// Creates a client.
	client, err := speech.NewClient(ctx)
	if err != nil {
		log.Fatalf("Failed to create client: %v", err)
		return err, fmt.Sprintf("Failed to create client: %v", err)
	}
	// The path to the remote audio file to transcribe.
	fileURI := fmt.Sprintf("gs://%s/%s", c.bucketName, c.uploadPath+c.objectName)

	// Detects speech in the audio file.
	resp, err := client.Recognize(ctx, &speechpb.RecognizeRequest{
		Config: &speechpb.RecognitionConfig{
			Encoding:        speechpb.RecognitionConfig_MP3,
			SampleRateHertz: 48000,
			LanguageCode:    "zh-TW",
		},
		Audio: &speechpb.RecognitionAudio{
			AudioSource: &speechpb.RecognitionAudio_Uri{Uri: fileURI},
		},
	})
	if err != nil {
		log.Fatalf("failed to recognize: %v", err)
		return err, fmt.Sprintf("failed to recognize: %v", err)
	}

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

	return nil, resultStr
}