谷歌语音到 C# 中的文本 API

我在我的代码中使用操作名称做了同样的事情，这里是代码供参考public async TaskTranscribeLongMediaFile(字符串操作名称){string bearerToken = GetOAuthToken();var baseUrl = new Uri(googleSpeechBaseUrl + operationName);字符串 resultContent = string.Empty;使用 (var client = new HttpClient()){client.DefaultRequestHeaders.Add(HttpRequestHeader.Authorization.ToString(), "Bearer " + bearerToken);client.DefaultRequestHeaders.Add(HttpRequestHeader.ContentType.ToString(), "application/json; charset=utf-8");client.Timeout = TimeSpan.FromMilliseconds(Timeout.Infinite);int currentPercentage = 0;bool responseStatus = false;而(！响应状态){响应状态 = 假；//发送请求使用 (var 结果 = await client.GetAsync(baseUrl)){resultContent = 等待 result.Content.ReadAsStringAsync();ResponseObject responseObject = JsonConvert.DeserializeObject(resultContent);currentPercentage = responseObject.metadata.progressPercent;responseStatus = (responseObject.done && currentPercentage == 100);//根据百分比值延迟请求重复发出 GET 请求，直到响应的 done 属性为真.等待 Task.Delay(CalculateDealy(currentPercentage));}}};返回结果内容；}为了延迟get请求:///////将请求延迟到毫秒数///</总结>///<param name="currentPercentage"></param>///<returns></returns>私人 int CalculateDealy(int currentPercentage){int x = currentPercentage/10;返回 (10 - x) * 1500；}获取身份验证令牌:///////获取 OAuth 令牌///</总结>///<returns></returns>公共字符串 GetOAuthToken(){返回 googleCredential.UnderlyingCredential.GetAccessTokenForRequestAsync("https://accounts.google.com/o/oauth2/v2/auth", CancellationToken.None).Result;}最后你会得到这样的结果: {"name": "此处的操作名称",元数据":{"@type": "type.googleapis.com/google.cloud.speech.v1.LongRunningRecognizeMetadata",进度百分比":100，"startTime": "2018-12-18T10:56:09.425584Z","lastUpdateTime": "2018-12-18T11:10:27.147310Z"},完成":真的，回复": {"@type": "type.googleapis.com/google.cloud.speech.v1.LongRunningRecognizeResponse",结果": [{备择方案": [{"transcript": "好的，让我们开始吧",信心":0.97442055}]}， 等等 .....需要的东西:api-key.json 文件安装包 Google.Apis.Auth.OAuth2 以授权HTTP 网络请求谢谢My program get a correct respon from google when the flac file recorded manual by using windows's sound recorder and convert it using a software converter.But when I use the file that recorded by my program, I got "{"result":[]}" from google. What should I do?here is my code :the sender : private static void CopyStream(FileStream fileStream, Stream requestStream) { var buffer = new byte[32768]; int read; while ((read = fileStream.Read(buffer, 0, buffer.Length)) > 0) { requestStream.Write(buffer, 0, read); } } private static void ConfigureRequest(HttpWebRequest request) { request.KeepAlive = true; request.SendChunked = true; request.ContentType = "audio/x-flac; rate=44100"; request.UserAgent = "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.121 Safari/535.2"; request.Headers.Set(HttpRequestHeader.AcceptEncoding, "gzip,deflate,sdch"); request.Headers.Set(HttpRequestHeader.AcceptLanguage, "en-GB,en-US;q=0.8,en;q=0.6"); request.Headers.Set(HttpRequestHeader.AcceptCharset, "ISO-8859-1,utf-8;q=0.7,*;q=0.3"); request.Method = "POST"; } using (var fileStream = new FileStream(@"C:UsersAhmad MustofaDocumentsVisual Studio 2010ProjectsFPFPinDebugvoice.flac", FileMode.Open)) { const string requestUrl = "https://www.google.com/speech-api/v2/recognize?output=json&lang=ar-sa&key=AIzaSyBJ6VJ326Rpb23msih2wGhXENEwU1TF1PA&client=chromium&maxresults=1&pfilter=2"; var request = (HttpWebRequest)WebRequest.Create(requestUrl); ConfigureRequest(request); var requestStream = request.GetRequestStream(); CopyStream(fileStream, requestStream); using (var response = request.GetResponse()) { using (var responseStream = response.GetResponseStream()) { using (var zippedStream = new GZipStream(responseStream, CompressionMode.Decompress)) { using (var sr = new StreamReader(zippedStream)) { var res = sr.ReadToEnd(); state.Text = res; } } } } }the wav recorder: private void sourceStream_DataAvailable(object sender, NAudio.Wave.WaveInEventArgs e) { if (waveWriter == null) return; waveWriter.WriteData(e.Buffer, 0, e.BytesRecorded); waveWriter.Flush(); } fileName = "C:\Users\Ahmad Mustofa\Documents\Visual Studio 2010\Projects\FP\FP\bin\debug\voice.wav"; int deviceNumber = hardware.SelectedItems[0].Index; try { sourceStream = new NAudio.Wave.WaveIn(); sourceStream.DeviceNumber = deviceNumber; sourceStream.WaveFormat = new NAudio.Wave.WaveFormat(44100, NAudio.Wave.WaveIn.GetCapabilities(deviceNumber).Channels); sourceStream.DataAvailable += new EventHandler<NAudio.Wave.WaveInEventArgs>(sourceStream_DataAvailable); waveWriter = new NAudio.Wave.WaveFileWriter(fileName, sourceStream.WaveFormat); sourceStream.StartRecording(); } catch (Exception ex) { state.Text = "disini" + ex.Message; }flac converter: string inputFile = Path.Combine("wav ", input); string outputFile = Path.Combine("flac", Path.ChangeExtension(input, ".flac")); if (!File.Exists(inputFile)) throw new ApplicationException("Input file " + inputFile + " cannot be found!"); WavReader wav = new WavReader(inputFile); using (var flacStream = File.Create(outputFile)) { FlacWriter flac = new FlacWriter(flacStream, wav.BitDepth, wav.Channels, wav.SampleRate); // Buffer for 1 second's worth of audio data byte[] buffer = new byte[wav.Bitrate / 8]; int bytesRead; do { bytesRead = wav.InputStream.Read(buffer, 0, buffer.Length); flac.Convert(buffer, 0, bytesRead); } while (bytesRead > 0); flac.Dispose(); flac = null; } 解决方案 It's clearly mentioned in the Google cloud api url i.ehttps://cloud.google.com/speech-to-text/docs/async-recognize#speech-async-recognize-gcs-protocolIf the operation has not completed, you can poll the endpoint by repeatedly making the GET request until the done property of the response is true. { "name": "operationname here", "metadata": { "@type": "type.googleapis.com/google.cloud.speech.v1.LongRunningRecognizeMetadata", "progressPercent": 0, "startTime": "2018-12-18T10:56:09.425584Z", "lastUpdateTime": "2018-12-18T11:10:27.147310Z" }, "done": true, }poll the endpoint by repeatedly making the GET request until the done property of the response is true or you can check for the "progressPercent": 0 until it's value become 100. Once its 100 percent then done property becomes true.I did the same in my code using operation name, for reference here is the codepublic async Task<string> TranscribeLongMediaFile(string operationName) { string bearerToken = GetOAuthToken(); var baseUrl = new Uri(googleSpeechBaseUrl + operationName); string resultContent = string.Empty; using (var client = new HttpClient()) { client.DefaultRequestHeaders.Add(HttpRequestHeader.Authorization.ToString(), "Bearer " + bearerToken); client.DefaultRequestHeaders.Add(HttpRequestHeader.ContentType.ToString(), "application/json; charset=utf-8"); client.Timeout = TimeSpan.FromMilliseconds(Timeout.Infinite); int currentPercentage = 0; bool responseStatus = false; while (!responseStatus) { responseStatus = false; // Send request using (var result = await client.GetAsync(baseUrl)) { resultContent = await result.Content.ReadAsStringAsync(); ResponseObject responseObject = JsonConvert.DeserializeObject<ResponseObject>(resultContent); currentPercentage = responseObject.metadata.progressPercent; responseStatus = (responseObject.done && currentPercentage == 100); // Delay the request based on percentage value to repeatedly making the GET request until the done property of the response is true. await Task.Delay(CalculateDealy(currentPercentage)); } } }; return resultContent; }In order to delay the get request:/// <summary> /// Delay the request to number of milliseconds /// </summary> /// <param name="currentPercentage"></param> /// <returns></returns> private int CalculateDealy(int currentPercentage) { int x = currentPercentage / 10; return (10 - x) * 1500; }Get auth token:/// <summary> /// Get OAuth token /// </summary> /// <returns></returns> public string GetOAuthToken() { return googleCredential.UnderlyingCredential.GetAccessTokenForRequestAsync("https://accounts.google.com/o/oauth2/v2/auth", CancellationToken.None).Result; }At last, you will get the result like: { "name": "operationname here", "metadata": { "@type": "type.googleapis.com/google.cloud.speech.v1.LongRunningRecognizeMetadata", "progressPercent": 100, "startTime": "2018-12-18T10:56:09.425584Z", "lastUpdateTime": "2018-12-18T11:10:27.147310Z" }, "done": true, "response": { "@type": "type.googleapis.com/google.cloud.speech.v1.LongRunningRecognizeResponse", "results": [ { "alternatives": [ { "transcript": "okay let's get started", "confidence": 0.97442055 } ] }, and so on .....Things required:api-key.json fileInstall package Google.Apis.Auth.OAuth2 in order to authorize theHTTP web requestThanks 这篇关于谷歌语音到 C# 中的文本 API的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！ 上岸，阿里云！