c# - 使用 C# 的 Google 语音识别 REST API 的错误请求错误

Question

我想在 C# 中使用 Google 语音识别 API Rest。我想使用 API Rest 而不是客户端库的原因是因为我想使用 Unity3D，但它目前不支持客户端库。

我使用 HttpClient 进行连接，使用 Newtonsoft Json 序列化 json(我现在正在使用 Windows 窗体，当它在 Winforms 中工作时将迁移到 Unity)。

我总是从 Google 收到错误的请求响应，它没有提供更多详细信息，但我注意到，如果我将 API key 值更改为无效值，我会得到相同的结果。

这是我的代码:

类:

class Speech
{
    public RecognitionConfig config { get; set; }
    public RecognitionAudio audio { get; set; }

    public bool sendToApi(string baseUri, string url, ref string apiResponse)
    {
        try
        {
            HttpClient client = new HttpClient();

            // Update port # in the following line.
            client.BaseAddress = new Uri(baseUri);
            client.DefaultRequestHeaders.Accept.Clear();
            client.DefaultRequestHeaders.Accept.Add(new System.Net.Http.Headers.MediaTypeWithQualityHeaderValue("application/json"));

            //var speechJson = new JavaScriptSerializer().Serialize(certificado);
            string speechJson = JsonConvert.SerializeObject(this);
            var contenido = new StringContent(speechJson.ToString(), Encoding.UTF8, "application/json");
            HttpResponseMessage response = client.PostAsync(url, contenido).Result;

            if (response.IsSuccessStatusCode)
            {
                string responseJson = response.Content.ReadAsStringAsync().Result;

                apiResponse = responseJson;
            }
            else
            {
                apiResponse = "ERROR " + JsonConvert.DeserializeObject(JsonConvert.SerializeObject(response));
            }

            return true;

        }

        catch (Exception e)
        {
            apiResponse = e.Message;
            return false;
        }
    }
}

class RecognitionConfig
{
    public string encoding { get; set; }
    public int sampleRateHertz { get; set; }
    public string languageCode { get; set; }
 //   public int maxAlternatives { get; set; }
 //   public bool profanityFilter { get; set; }
 //  public List<SpeechContext> speechContexts { get; set; }
 //   public bool enableWordTimeOffsets { get; set; }

}

class SpeechContext
{
    public List<string> phrases { get; set; }

}
class RecognitionAudio
{
    public string content { get; set; }
   // public string uri { get; set; }

    public bool setContentBase64FromAudio(string path)
    {
        try
        {
            FileStream fileStream = File.OpenRead(path);

            MemoryStream memoryStream = new MemoryStream();
            memoryStream.SetLength(fileStream.Length);
            fileStream.Read(memoryStream.GetBuffer(), 0, (int)fileStream.Length);
            byte[] BA_AudioFile = memoryStream.GetBuffer();
            this.content = System.Convert.ToBase64String(BA_AudioFile);

            return true;
        }
        catch(Exception e)
        {
            return false;
        }

    }
}

电话:

   private void button1_Click(object sender, EventArgs e)
    {
        Speech speech = new Speech();

        speech.config = new RecognitionConfig();
        speech.audio = new RecognitionAudio();
        speech.config.encoding = "FLAC";
        speech.config.sampleRateHertz = 44100;
        speech.config.languageCode = "en-US";

        RecognitionAudio audio = new RecognitionAudio();
        audio.setContentBase64FromAudio("C:\\Users\\Manena\\Downloads\\good-morning-google.flac");

        speech.audio = audio;

        string response = ""; 
        speech.sendToApi("https://speech.googleapis.com/", "v1/speech:recognize?key=<mykey>", ref response);
        textBox1.Text = response;

    }
}

编辑:这是我发送的 Json:

{  
       "config":{  
          "encoding":"FLAC",
          "sampleRateHertz":44100,
          "languageCode":"en-US"
       },
       "audio":{  
          "content":"base64 audio"
       }
    }

以及我收到的:

    {
      "Version": {
        "Major": 1,
        "Minor": 1,
        "Build": -1,
        "Revision": -1,
        "MajorRevision": -1,
        "MinorRevision": -1
      },
      "Content": {
        "Headers": [
          {
            "Key": "Content-Type",
            "Value": [
              "application/json; charset=UTF-8"
            ]
          }
        ]
      },
      "StatusCode": 400,
      "ReasonPhrase": "Bad Request",
      "Headers": [
        {
          "Key": "Vary",
          "Value": [
            "X-Origin",
            "Referer",
            "Origin",
            "Accept-Encoding"
          ]
        },
        {
          "Key": "X-XSS-Protection",
          "Value": [
            "1; mode=block"
          ]
        },
        {
          "Key": "X-Frame-Options",
          "Value": [
            "SAMEORIGIN"
          ]
        },
        {
          "Key": "X-Content-Type-Options",
          "Value": [
            "nosniff"
          ]
        },
        {
          "Key": "Alt-Svc",
          "Value": [
            "hq=\":443\"; ma=2592000; quic=51303431; quic=51303339; quic=51303338; quic=51303337; quic=51303335,quic=\":443\"; ma=2592000; v=\"41,39,38,37,35\""
          ]
        },
        {
          "Key": "Transfer-Encoding",
          "Value": [
            "chunked"
          ]
        },
        {
          "Key": "Accept-Ranges",
          "Value": [
            "none"
          ]
        },
        {
          "Key": "Cache-Control",
          "Value": [
            "private"
          ]
        },
        {
          "Key": "Date",
          "Value": [
            "Sat, 30 Dec 2017 09:06:19 GMT"
          ]
        },
        {
          "Key": "Server",
          "Value": [
            "ESF"
          ]
        }
      ],
      "RequestMessage": {
        "Version": {
          "Major": 1,
          "Minor": 1,
          "Build": -1,
          "Revision": -1,
          "MajorRevision": -1,
          "MinorRevision": -1
        },
        "Content": {
          "Headers": [
            {
              "Key": "Content-Type",
              "Value": [
                "application/json; charset=utf-8"
              ]
            },
            {
              "Key": "Content-Length",
              "Value": [
                "106"
              ]
            }
          ]
        },
        "Method": {
          "Method": "POST"
        },
        "RequestUri": "https://speech.googleapis.com/v1/speech:recognize?key=mykey",
        "Headers": [
          {
            "Key": "Accept",
            "Value": [
              "application/json"
            ]
          }
        ],
        "Properties": {}
      },
      "IsSuccessStatusCode": false
    }

我知道我的代码可能不是最优雅的，但现在我只对从 Google API 获得好的响应感兴趣。有什么线索吗？

Answer 1

我已经解决了这个问题。

问题是我使用的是 2 声道音频文件，而 Google Speech API 目前只接受单声道音频。

所以问题中的代码适用于单声道音频，它可能对某些人有用

谢谢