我无法使用Google Speech-to-Text Go SDK演示程序识别朝鲜语,但是中文还可以

时间:2019-04-18 09:45:06

标签: google-cloud-speech

我使用最佳示例的Go示例[live caption_from_file]代码来标识本地韩语语音频率。我将语言代码设置为“ ko-KR”,但在没有任何内容返回或错误提示的情况下,我无法识别stream.Recv()中返回io.EOF的代码。但是,如果我使用本地中文wav音频并将“语言代码”设置为“ cmn-Hans-CN”,则返回正确的识别文本不会有问题。有什么问题以及如何解决?

如果len(flag.Args())<1 {                 log.Fatal(“请将路径作为命令行参数传递到本地音频文件”)         }         audioFile:= flag.Arg(0)         langEn:= flag.Arg(1)

    ctx := context.Background()

    client, err := speech.NewClient(ctx)
    if err != nil {
            log.Fatal(err)
    }
    stream, err := client.StreamingRecognize(ctx)
    if err != nil {
            log.Fatal(err)
    }
    // Send the initial configuration message.
    if err := stream.Send(&speechpb.StreamingRecognizeRequest{
            StreamingRequest: &speechpb.StreamingRecognizeRequest_StreamingConfig{
                    StreamingConfig: &speechpb.StreamingRecognitionConfig{
                            Config: &speechpb.RecognitionConfig{
                                    Encoding:        speechpb.RecognitionConfig_LINEAR16,
                                    SampleRateHertz: 16000,
                                    LanguageCode:    langEn,
                            },
                    },
            },
    }); err != nil {
            log.Fatal(err)
    }

    f, err := os.Open(audioFile)
    if err != nil {
            log.Fatal(err)
    }
    defer f.Close()

    go func() {
            buf := make([]byte, 1024)
            for {
                    n, err := f.Read(buf)
                    if n > 0 {
                            if err := stream.Send(&speechpb.StreamingRecognizeRequest{
                                    StreamingRequest: &speechpb.StreamingRecognizeRequest_AudioContent{
                                            AudioContent: buf[:n],
                                    },
                            }); err != nil {
                                    log.Printf("Could not send audio: %v", err)
                            }
                    }
                    if err == io.EOF {
                            // Nothing else to pipe, close the stream.
                            if err := stream.CloseSend(); err != nil {
                                    log.Fatalf("Could not close stream: %v", err)
                            }
                            return
                    }
                    if err != nil {
                            log.Printf("Could not read from %s: %v", audioFile, err)
                            continue
                    }
            }
    }()

    for {
            resp, err := stream.Recv()
            //if err == io.EOF {
            //      break
            //}
            if err != nil {
                    log.Fatalf("Cannot stream results: %v", err)
            }
            if err := resp.Error; err != nil {
                    log.Fatalf("Could not recognize: %v", err)
            }
            for _, result := range resp.Results {
                    fmt.Printf("Result: %+v\n", result)
                    for _, alt := range result.Alternatives {
                            fmt.Printf("\"%v\" (confidence=%3f)\n",  alt.Transcript, alt.Confidence)

                  }
        }
    }

0 个答案:

没有答案