// [END speech_transcribe_async]
// [START speech_transcribe_async_gcs]
static object AsyncRecognizeGcs(string storageUri)
{
var speech = SpeechClient.Create();
var longOperation = speech.LongRunningRecognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 16000,
LanguageCode = "en",
}, RecognitionAudio.FromStorageUri(storageUri));
longOperation = longOperation.PollUntilCompleted();
var response = longOperation.Result;
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
Console.WriteLine($"Transcript: { alternative.Transcript}");
}
}
return(0);
}
public async Task <string> LongRecognize(string googleLink, string language, int rate, Action <int> onProgress = null)
{
var speech = SpeechClient.Create();
var request = await speech.LongRunningRecognizeAsync(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = rate,
LanguageCode = language,
}, RecognitionAudio.FromStorageUri(googleLink));
do
{
await Task.Delay(TimeSpan.FromSeconds(5));
request = await request.PollOnceAsync();
onProgress?.Invoke(request.Metadata.ProgressPercent);
} while (!request.IsCompleted);
return(request.Result.Results.SelectMany(R => R.Alternatives)
.Select(A => A.Transcript)
.ConcatStrings(" "));
}
// [END speech_sync_recognize_gcs]
// [START speech_async_recognize]
static object LongRunningRecognize(string filePath)
{
var speech = SpeechClient.Create();
var longOperation = speech.LongRunningRecognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Flac,
SampleRateHertz = 16000,
LanguageCode = "en",
}, RecognitionAudio.FromFile(filePath));
longOperation = longOperation.PollUntilCompleted();
var response = longOperation.Result;
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
Console.WriteLine(alternative.Transcript);
}
}
return(0);
}
// [END speech_transcribe_auto_punctuation]
// [START speech_transcribe_model_selection]
static object SyncRecognizeModelSelection(string filePath, string model)
{
var speech = SpeechClient.Create();
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 16000,
LanguageCode = "en",
// The `model` value must be one of the following:
// "video", "phone_call", "command_and_search", "default"
Model = model
}, RecognitionAudio.FromFile(filePath));
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
Console.WriteLine(alternative.Transcript);
}
}
return(0);
}
public async Task StartRecording()
{
_speechClient = SpeechClient.Create();
_streamingRecognizeStream = _speechClient.StreamingRecognize();
// Write the initial request with the config.
await _streamingRecognizeStream.WriteAsync(
new StreamingRecognizeRequest()
{
StreamingConfig = new StreamingRecognitionConfig()
{
Config = new RecognitionConfig()
{
Encoding =
RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 16000,
LanguageCode = "ro"
},
InterimResults = false,
SingleUtterance = false
}
});
_sendResponses = Task.Run(async() =>
{
var responseStream = _streamingRecognizeStream.GetResponseStream();
while (await responseStream.MoveNextAsync())
{
StreamingRecognizeResponse response = responseStream.Current;
foreach (StreamingRecognitionResult result in response.Results)
{
foreach (SpeechRecognitionAlternative alternative in result.Alternatives)
{
await Clients.All.SendAsync("ReceiveMessage", alternative.Transcript);
}
}
}
});
}
/// <summary>
/// Sends a speech recognition request to the speech service
/// </summary>
/// <param name="audioFile">The audio file.</param>
/// <param name="locale">The locale.</param>
/// <param name="serviceUrl">The service URL.</param>
/// <param name="subscriptionKey">The subscription key.</param>
/// <returns>
/// A task
/// </returns>
public async Task Run(string audioFile, string locale, Uri serviceUrl, string subscriptionKey)
{
// create the preferences object
var preferences = new Preferences(locale, serviceUrl, new CognitiveServicesAuthorizationProvider(subscriptionKey));
// Create a a speech client
using (var speechClient = new SpeechClient(preferences))
{
speechClient.SubscribeToPartialResult(this.OnPartialResult);
speechClient.SubscribeToRecognitionResult(this.OnRecognitionResult);
// create an audio content and pass it a stream.
using (var audio = new FileStream(audioFile, FileMode.Open, FileAccess.Read))
{
var deviceMetadata = new DeviceMetadata(DeviceType.Near, DeviceFamily.Desktop, NetworkType.Ethernet, OsName.Windows, "1607", "Dell", "T3600");
var applicationMetadata = new ApplicationMetadata("SampleApp", "1.0.0");
var requestMetadata = new RequestMetadata(Guid.NewGuid(), deviceMetadata, applicationMetadata, "SampleAppService");
await speechClient.RecognizeAsync(new SpeechInput(audio, requestMetadata), this.cts.Token).ConfigureAwait(false);
}
}
}
public ActionResult <IEnumerable <string> > Post(IFormFile content)
{
List <string> returnResult = new List <string>();
if (content == null)
{
throw new Exception("Dosya Bulunamadı!");
}
try
{
Environment.SetEnvironmentVariable("GOOGLE_APPLICATION_CREDENTIALS", credential_path);
var speech = SpeechClient.Create();
if (content.Length > 0)
{
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 8000,
LanguageCode = "tr-TR",
}, RecognitionAudio.FromStream(content.OpenReadStream()));
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
returnResult.Add(alternative.Transcript);
}
}
}
return(returnResult);
}
catch (Exception e)
{
throw;
}
}
public async Task <LongRunningRecognizeResponse> Recognize(string storageUri, RecognizeConfiguration configuration = null)
{
configuration ??= new RecognizeConfiguration();
var speech = SpeechClient.Create();
var audio = RecognitionAudio.FromStorageUri(storageUri);
var longOperation = await speech.LongRunningRecognizeAsync(new RecognitionConfig()
{
Encoding = configuration.AudioEncoding,
SampleRateHertz = configuration.SampleRateHertz,
LanguageCode = configuration.LanguageCode,
DiarizationConfig = new SpeakerDiarizationConfig()
{
EnableSpeakerDiarization = true,
MinSpeakerCount = configuration.MinSpeakerCount,
MaxSpeakerCount = configuration.MaxSpeakerCount
},
Metadata = new RecognitionMetadata()
{
OriginalMediaType = RecognitionMetadata.Types.OriginalMediaType.Video
}
//}, RecognitionAudio.FromStorageUri(storageUri));
}, audio);
//}, RecognitionAudio.FetchFromUri("https://www.youtube.com/watch?v=5Btbdt7ksko&fbclid=IwAR2FQ5KlTzxHH7UdYDTx4Vcnk6TfFfFtWpMJw-jH1UOMAbodsnY8mS1bNlI"));
longOperation = await longOperation.PollUntilCompletedAsync();
LongRunningRecognizeResponse response = longOperation.Result;
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
Console.WriteLine($"Transcript: { alternative.Transcript}");
}
}
return(response);
}
public async Task <IActionResult> InsertAudio(int caminhaoId, IFormFile file)
{
try
{
MemoryStream msAudio = new MemoryStream();
file.CopyTo(msAudio);
/* Grava no S3*/
var link = await _serv.SalvaAudioNoS3(msAudio);
/* Transcreve audio */
string AudioTranscrito = String.Empty;
var speech = SpeechClient.Create();
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.EncodingUnspecified,
LanguageCode = "pt-br",
},
await RecognitionAudio.FromStreamAsync(file.OpenReadStream()));
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
AudioTranscrito = alternative.Transcript;
}
}
await _serv.SalvaMensagemBanco(link, AudioTranscrito, 1, caminhaoId, "you");
return(Ok(file));
}
catch (Exception ex)
{
return(StatusCode(500, ex.Message));
}
}
public void CreateClients()
{
try
{
if (settingsService.settings.googleSettings.ServiceAccountKey != "")
{
//Environment.SetEnvironmentVariable("GOOGLE_APPLICATION_CREDENTIALS", settings.googleSettings.ServiceAccountKey);
var credential = GoogleCredential.FromFile(settingsService.settings.googleSettings.ServiceAccountKey)
.CreateScoped(TextToSpeechClient.DefaultScopes);
var channel = new Channel(TextToSpeechClient.DefaultEndpoint.ToString(), credential.ToChannelCredentials());
toSpeechClient = TextToSpeechClient.Create(channel);
credential = GoogleCredential.FromFile(settingsService.settings.googleSettings.ServiceAccountKey)
.CreateScoped(SpeechClient.DefaultScopes);
channel = new Channel(SpeechClient.DefaultEndpoint.ToString(), credential.ToChannelCredentials());
toTextClient = SpeechClient.Create(channel);
}
}
catch (Exception e)
{
Console.WriteLine($"Google credentials not set. Error: {e}");
MessageBox.Show($"Google credentials not set. Error: {e}");
}
}
public async Task <RecognitionResponseModel> Recognize(byte[] file, string languageCode, CancellationToken cancellationToken = default)
{
var speech = SpeechClient.Create();
var response = await speech.RecognizeAsync(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.OggOpus,
LanguageCode = "uz-UZ",
SampleRateHertz = 48000
},
RecognitionAudio.FromBytes(file),
cancellationToken);
var alternative = response?.Results?.FirstOrDefault()?.Alternatives?.FirstOrDefault();
return(new RecognitionResponseModel()
{
Transcript = alternative?.Transcript,
Confidence = alternative?.Confidence ?? 0,
Words = alternative?.Words.Select(p => new Models.WordInfo {
Confidence = p.Confidence, EndTime = p.EndTime.ToTimeSpan().ToString(), SpeakerTag = p.SpeakerTag, StartTime = p.StartTime.ToTimeSpan().ToString(), Word = p.Word
}).ToArray()
});
}
private void Recognize()
{
SpeechClientBuilder builder = new SpeechClientBuilder();
builder.CredentialsPath = GOOGLE_API_CREDS_PATH;
SpeechClient client = builder.Build();
RecognizeRequest request = new RecognizeRequest()
{
Audio = RecognitionAudio.FromFile(TEMP_AUDIO_PATH),
Config = new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.EncodingUnspecified,
LanguageCode = "ru-RU",
EnableWordTimeOffsets = false
}
};
RecognizeResponse response = client.Recognize(request);
Result.Text = string.Join("\n", response.Results.Select(
result => result.Alternatives[0].Transcript
));
}
public static string SpeechToText(string file)
{
string fileContent = "";
var speech = SpeechClient.Create();
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 44100,
LanguageCode = "pl-PL"
}, RecognitionAudio.FromFile(file));
Console.WriteLine("Transcript of " + file + " ready.");
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
//Console.WriteLine(alternative.Transcript);
fileContent += alternative.Transcript;
}
}
return(fileContent);
}
void GRecognition()
{
System.Environment.SetEnvironmentVariable("GOOGLE_APPLICATION_CREDENTIALS", "GOOGLECREDENTIALS.json");
var speech = SpeechClient.Create();
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 16000,
LanguageCode = "en",
}, RecognitionAudio.FromFile("resampled.wav"));
string Text = "";
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
Text = Text + " " + alternative.Transcript;
}
}
Console.WriteLine(Text);
}
private static void RecognizeFromAudioFile(string fileName)
{
var speech = SpeechClient.Create();
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 16000,
LanguageCode = "en",
}, RecognitionAudio.FromFile(fileName));
Console.WriteLine("Recognized text:");
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
Console.WriteLine(alternative.Transcript);
Console.WriteLine($"Confidence: {alternative.Confidence * 100}%");
Console.WriteLine("****");
}
Console.ReadLine();
}
}
public string AudioFileToText(string fileName)
{
string gcsUri = $"gs://catta-telegram-bot-voice-messages/{fileName}";
var speech = SpeechClient.Create();
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 48000,
LanguageCode = "it-IT",
}, RecognitionAudio.FromStorageUri(gcsUri));
string text = "";
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
text += alternative.Transcript + "\n";
}
}
return(text);
}
/// <summary>Snippet for Recognize</summary>
public void Recognize_RequestObject()
{
// Snippet: Recognize(RecognizeRequest,CallSettings)
// Create client
SpeechClient speechClient = SpeechClient.Create();
// Initialize request argument(s)
RecognizeRequest request = new RecognizeRequest
{
Config = new RecognitionConfig
{
Encoding = RecognitionConfig.Types.AudioEncoding.Flac,
SampleRateHertz = 44100,
LanguageCode = "en-US",
},
Audio = new RecognitionAudio
{
Uri = "gs://bucket_name/file_name.flac",
},
};
// Make the request
RecognizeResponse response = speechClient.Recognize(request);
// End snippet
}
static object SyncRecognizeWithCredentials(string filePath, string credentialsFilePath)
{
SpeechClientBuilder builder = new SpeechClientBuilder
{
CredentialsPath = credentialsFilePath
};
SpeechClient speech = builder.Build();
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 16000,
LanguageCode = "en",
}, RecognitionAudio.FromFile(filePath));
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
Console.WriteLine(alternative.Transcript);
}
}
return(0);
}
/// <summary>Snippet for RecognizeAsync</summary>
public async Task RecognizeAsync()
{
// Snippet: RecognizeAsync(RecognitionConfig,RecognitionAudio,CallSettings)
// Additional: RecognizeAsync(RecognitionConfig,RecognitionAudio,CancellationToken)
// Create client
SpeechClient speechClient = await SpeechClient.CreateAsync();
// Initialize request argument(s)
RecognitionConfig config = new RecognitionConfig
{
Encoding = RecognitionConfig.Types.AudioEncoding.Flac,
SampleRateHertz = 44100,
LanguageCode = "en-US",
};
RecognitionAudio audio = new RecognitionAudio
{
Uri = "gs://bucket_name/file_name.flac",
};
// Make the request
RecognizeResponse response = await speechClient.RecognizeAsync(config, audio);
// End snippet
}
public SpeechToText(String storageUri)
{
sttResult = new StringBuilder();
var speech = SpeechClient.Create();
var longOperation = speech.LongRunningRecognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Flac,
//SampleRateHertz = 16000,
LanguageCode = "ko",
}, RecognitionAudio.FromStorageUri(storageUri));
longOperation = longOperation.PollUntilCompleted();
var response = longOperation.Result;
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
//Console.WriteLine($"Transcript: { alternative.Transcript}"); //콘솔확인용
sttResult.AppendLine(alternative.Transcript);
}
}
}
// [END speech_transcribe_model_selection]
// [START speech_transcribe_enhanced_model]
static object SyncRecognizeEnhancedModel(string filePath)
{
var speech = SpeechClient.Create();
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 8000,
LanguageCode = "en-US",
UseEnhanced = true,
// A model must be specified to use an enhanced model.
// Currently, only 'phone_call' is supported.
Model = "phone_call",
}, RecognitionAudio.FromFile(filePath));
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
Console.WriteLine(alternative.Transcript);
}
}
return(0);
}
public void Recognize()
{
var audio = LoadResourceAudio("speech.raw");
// Sample: Recognize
// Additional: Recognize(*,*,*)
SpeechClient client = SpeechClient.Create();
RecognitionConfig config = new RecognitionConfig
{
Encoding = AudioEncoding.Linear16,
SampleRateHertz = 16000,
LanguageCode = LanguageCodes.English.UnitedStates,
UseEnhanced = true
};
RecognizeResponse response = client.Recognize(config, audio);
Console.WriteLine(response);
// End sample
Assert.Equal(
"this is a test file for the google cloud speech api",
response.Results[0].Alternatives[0].Transcript,
true);
}
private void btnSpeechInfo_Click(object sender, EventArgs e)
{
btnRecordVoice.Enabled = true;
btnSave.Enabled = false;
btnSpeechInfo.Enabled = false;
if (File.Exists("audio.raw"))
{
var speech = SpeechClient.Create();
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 16000,
LanguageCode = "en",
}, RecognitionAudio.FromFile("audio.raw"));
textBox1.Text = "";
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
textBox1.Text = textBox1.Text + " " + alternative.Transcript;
}
}
if (textBox1.Text.Length == 0)
{
textBox1.Text = "No Data ";
}
}
else
{
textBox1.Text = "Audio File Missing ";
}
}
/// <summary>
/// Sends a speech recognition request to the speech service
/// </summary>
/// <param name="audioFile">The audio file.</param>
/// <param name="locale">The locale.</param>
/// <returns>
/// A task
/// </returns>
public async Task <string> TranslateToText(string audioFile, string locale = "en-GB")
{
var preferences = new Preferences(locale, _serviceUrl, new CognitiveServicesAuthorizationProvider(_subscriptionKey));
// Create a a speech client
using (var speechClient = new SpeechClient(preferences))
{
speechClient.SubscribeToPartialResult(this.OnPartialResult);
speechClient.SubscribeToRecognitionResult(this.OnRecognitionResult);
try
{
// create an audio content and pass it a stream.
using (var downloadStream = new WebClient())
using (var audio = new MemoryStream(downloadStream.DownloadData(audioFile)))
{
var deviceMetadata = new DeviceMetadata(DeviceType.Near, DeviceFamily.Desktop,
NetworkType.Ethernet, OsName.Windows, "1607", "Dell", "T3600");
var applicationMetadata = new ApplicationMetadata("SampleApp", "1.0.0");
var requestMetadata = new RequestMetadata(Guid.NewGuid(), deviceMetadata, applicationMetadata,
"SampleAppService");
await speechClient.RecognizeAsync(new SpeechInput(audio, requestMetadata), this.cts.Token)
.ConfigureAwait(false);
}
}
catch (Exception e)
{
if (e is PlatformNotSupportedException)
{
return(await TranslateToTextFallback(audioFile).ConfigureAwait(false)); //fallback for when websockets are not supported
}
}
}
return(string.Empty);
}
public async Task AsyncRecognizeAsync_RequestObject()
{
// Snippet: AsyncRecognizeAsync(AsyncRecognizeRequest,CallSettings)
// Create client
SpeechClient speechClient = await SpeechClient.CreateAsync();
// Initialize request argument(s)
AsyncRecognizeRequest request = new AsyncRecognizeRequest
{
Config = new RecognitionConfig(),
Audio = new RecognitionAudio(),
};
// Make the request
Operation <AsyncRecognizeResponse> response =
await speechClient.AsyncRecognizeAsync(request);
// Poll until the returned long-running operation is complete
Operation <AsyncRecognizeResponse> completedResponse =
await response.PollUntilCompletedAsync();
// Retrieve the operation result
AsyncRecognizeResponse result = completedResponse.Result;
// Or get the name of the operation
string operationName = response.Name;
// This name can be stored, then the long-running operation retrieved later by name
Operation <AsyncRecognizeResponse> retrievedResponse =
await speechClient.PollOnceAsyncRecognizeAsync(operationName);
// Check if the retrieved long-running operation has completed
if (retrievedResponse.IsCompleted)
{
// If it has completed, then access the result
AsyncRecognizeResponse retrievedResult = retrievedResponse.Result;
}
// End snippet
}
/// <summary>
/// Sends a speech recognition request to the speech service
/// </summary>
/// <param name="audioFile">The audio file.</param>
/// <param name="locale">The locale.</param>
/// <param name="serviceUrl">The service URL.</param>
/// <param name="subscriptionKey">The subscription key.</param>
/// <returns>
/// A task
/// </returns>
///
public async Task Run(string audioFile, string locale, Uri serviceUrl, string subscriptionKey, string episode)
{
// create the preferences object
var preferences = new Preferences(locale, serviceUrl, new CognitiveServicesAuthorizationProvider(subscriptionKey));
string simpleFilename = Path.GetFileNameWithoutExtension(audioFile);
if (int.TryParse(episode, out int outepisode))
{
episodenumber = outepisode;
}
else
{
return;
}
htmlOutputFilePath = Path.GetDirectoryName(audioFile) + @"\" + episodenumber.ToString() + ".html";
opmlOutputFilePath = Path.GetDirectoryName(audioFile) + @"\" + episodenumber.ToString() + ".opml";
// Create a a speech client
using (var speechClient = new SpeechClient(preferences))
{
//speechClient.SubscribeToPartialResult(this.OnPartialResult);
speechClient.SubscribeToRecognitionResult(this.OnRecognitionResult);
// create an audio content and pass it a stream.
using (var audio = new FileStream(audioFile, FileMode.Open, FileAccess.Read))
{
var deviceMetadata = new DeviceMetadata(DeviceType.Near, DeviceFamily.Desktop, NetworkType.Ethernet, OsName.Windows, "1607", "Dell", "T3600");
var applicationMetadata = new ApplicationMetadata("NA Transcribe", "1.0.0");
var requestMetadata = new RequestMetadata(Guid.NewGuid(), deviceMetadata, applicationMetadata, "NATranscriptService");
await speechClient.RecognizeAsync(new SpeechInput(audio, requestMetadata), this.cts.Token).ConfigureAwait(false);
}
}
}
private void Button_WOC2_Click_1(object sender, EventArgs e)///Convert to text/////
{
recordBtn.Enabled = true;
audioSaveBtn.Enabled = false;
convertBtn.Enabled = false;
if (File.Exists("audio.raw"))
{
var speech = SpeechClient.Create();
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 16000,
LanguageCode = "en",
}, RecognitionAudio.FromFile("audio.raw"));
richTextBox1.Text = "";
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
richTextBox1.Text = richTextBox1.Text + " " + alternative.Transcript;
}
}
if (richTextBox1.Text.Length == 0)
{
richTextBox1.Text = "No Data ";
}
}
else
{
richTextBox1.Text = "Audio File Missing ";
}
}
/// <summary>
/// Print confidence level for individual words in a transcription of a short audio file
/// Separating different speakers in an audio file recording
/// </summary>
/// <param name="localFilePath">Path to local audio file, e.g. /path/audio.wav</param>
public static void SampleLongRunningRecognize(string localFilePath)
{
SpeechClient speechClient = SpeechClient.Create();
// string localFilePath = "resources/commercial_mono.wav"
LongRunningRecognizeRequest request = new LongRunningRecognizeRequest
{
Config = new RecognitionConfig
{
// If enabled, each word in the first alternative of each result will be
// tagged with a speaker tag to identify the speaker.
EnableSpeakerDiarization = true,
// Optional. Specifies the estimated number of speakers in the conversation.
DiarizationSpeakerCount = 2,
// The language of the supplied audio
LanguageCode = "en-US",
},
Audio = new RecognitionAudio
{
Content = ByteString.CopyFrom(File.ReadAllBytes(localFilePath)),
},
};
// Poll until the returned long-running operation is complete
LongRunningRecognizeResponse response = speechClient.LongRunningRecognize(request).PollUntilCompleted().Result;
foreach (var result in response.Results)
{
// First alternative has words tagged with speakers
SpeechRecognitionAlternative alternative = result.Alternatives[0];
Console.WriteLine($"Transcript: {alternative.Transcript}");
// Print the speakerTag of each word
foreach (var word in alternative.Words)
{
Console.WriteLine($"Word: {word.Word}");
Console.WriteLine($"Speaker tag: {word.SpeakerTag}");
}
}
}
/// <summary>Snippet for LongRunningRecognizeAsync</summary>
public async Task LongRunningRecognizeRequestObjectAsync()
{
// Snippet: LongRunningRecognizeAsync(LongRunningRecognizeRequest, CallSettings)
// Additional: LongRunningRecognizeAsync(LongRunningRecognizeRequest, CancellationToken)
// Create client
SpeechClient speechClient = await SpeechClient.CreateAsync();
// Initialize request argument(s)
LongRunningRecognizeRequest request = new LongRunningRecognizeRequest
{
Config = new RecognitionConfig(),
Audio = new RecognitionAudio(),
OutputConfig = new TranscriptOutputConfig(),
};
// Make the request
Operation <LongRunningRecognizeResponse, LongRunningRecognizeMetadata> response = await speechClient.LongRunningRecognizeAsync(request);
// Poll until the returned long-running operation is complete
Operation <LongRunningRecognizeResponse, LongRunningRecognizeMetadata> completedResponse = await response.PollUntilCompletedAsync();
// Retrieve the operation result
LongRunningRecognizeResponse result = completedResponse.Result;
// Or get the name of the operation
string operationName = response.Name;
// This name can be stored, then the long-running operation retrieved later by name
Operation <LongRunningRecognizeResponse, LongRunningRecognizeMetadata> retrievedResponse = await speechClient.PollOnceLongRunningRecognizeAsync(operationName);
// Check if the retrieved long-running operation has completed
if (retrievedResponse.IsCompleted)
{
// If it has completed, then access the result
LongRunningRecognizeResponse retrievedResult = retrievedResponse.Result;
}
// End snippet
}
static object Rec(string filePath, int bitRate,
RecognitionConfig.Types.AudioEncoding encoding)
{
var speech = SpeechClient.Create();
//var response = speech.Recognize(new RecognitionConfig()
//{
// Encoding = encoding,
// SampleRateHertz = bitRate,
// LanguageCode = "en",
//}, RecognitionAudio.FromFile(filePath));
//foreach (var result in response.Results)
//{
// foreach (var alternative in result.Alternatives)
// {
// Console.WriteLine(alternative.Transcript);
// }
//}
var longOperation = speech.LongRunningRecognize(new RecognitionConfig()
{
Encoding = encoding, //RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = bitRate,
LanguageCode = "en",
}, RecognitionAudio.FromFile(filePath));
longOperation = longOperation.PollUntilCompleted();
var response = longOperation.Result;
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
Console.WriteLine(alternative.Transcript);
}
}
return(0);
}