// [END speech_transcribe_diarization]
//[START speech_transcribe_recognition_metadata]
static object SyncRecognizeRecognitionMetadata(string filePath)
{
var speech = SpeechClient.Create();
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Flac,
LanguageCode = "en",
Metadata = new RecognitionMetadata()
{
OriginalMediaType = RecognitionMetadata.Types.OriginalMediaType.Audio,
OriginalMimeType = "audio/mp3",
// The kind of device used to capture the audio
RecordingDeviceType = RecognitionMetadata.Types.RecordingDeviceType.OtherIndoorDevice,
// Use case of the audio, e.g. PHONE_CALL, DISCUSSION, etc
InteractionType = RecognitionMetadata.Types.InteractionType.VoiceSearch,
// The name of the defice used to make the recording.
// Arbitrary string, e.g. 'Pixel XL', 'VoIP', or other value
RecordingDeviceName = "Pixel XL"
}
}, RecognitionAudio.FromFile(filePath));
foreach (var result in response.Results)
{
Console.WriteLine($"Transcript: { result.Alternatives[0].Transcript}");
}
return(0);
}
// [END speech_transcribe_multichannel]
// [START speech_transcribe_diarization]
static object SyncRecognizeMultipleSpeakers(string filePath, int numberOfSpeakers)
{
var speech = SpeechClient.Create();
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
LanguageCode = "en",
DiarizationConfig = new SpeakerDiarizationConfig()
{
EnableSpeakerDiarization = true,
MinSpeakerCount = 2
}
}, RecognitionAudio.FromFile(filePath));
// Print out the results.
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
Console.WriteLine($"Transcript: { alternative.Transcript}");
Console.WriteLine("Word details:");
Console.WriteLine($" Word count:{alternative.Words.Count}");
foreach (var item in alternative.Words)
{
Console.WriteLine($" {item.Word}");
Console.WriteLine($" Speaker: {item.SpeakerTag}");
}
}
}
return(0);
}
public string ConvertAudioToText(string path)
{
var speech = SpeechClient.Create();
var config = new RecognitionConfig
{
Encoding = RecognitionConfig.Types.AudioEncoding.Flac,
SampleRateHertz = 16000,
LanguageCode = LanguageCodes.English.UnitedStates
};
var audio = RecognitionAudio.FromFile(path);
var response = speech.Recognize(config, audio);
var sd = "";
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
sd += alternative.Transcript;
//Console.WriteLine(alternative.Transcript);
}
}
return(sd);
}
public async void GetTranscript(string uri, Action <string> callback)
{
if (client == null)
{
return;
}
var context = new SpeechContext()
{
Phrases = { File.ReadLines(CloudUtility.SwearList) }
};
var speechOperation = await client.LongRunningRecognizeAsync(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Flac,
LanguageCode = "en-US",
EnableWordTimeOffsets = true,
SpeechContexts = { context }
}, RecognitionAudio.FromFile(uri));
speechOperation = await speechOperation.PollUntilCompletedAsync();
var response = speechOperation.Result;
string builder = "";
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
builder += alternative.Transcript;
}
builder += Environment.NewLine;
}
callback(builder);
}
// [END speech_transcribe_enhanced_model]
// [START speech_transcribe_multichannel]
static object SyncRecognizeMultipleChannels(string filePath, int channelCount)
{
var speech = SpeechClient.Create();
// Create transcription request
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
LanguageCode = "en",
// Configure request to enable multiple channels
EnableSeparateRecognitionPerChannel = true,
AudioChannelCount = channelCount
// Note: Sample uses local file.
}, RecognitionAudio.FromFile(filePath));
// Print out the results.
foreach (var result in response.Results)
{
// There can be several transcripts for a chunk of audio.
// Print out the first (most likely) one here.
var alternative = result.Alternatives[0];
Console.WriteLine($"Transcript: {alternative.Transcript}");
Console.WriteLine($"Channel Tag: {result.ChannelTag}");
}
return(0);
}
// [END speech_sync_recognize]
// [START speech_sync_recognize_words]
static object SyncRecognizeWords(string filePath)
{
var speech = SpeechClient.Create();
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 16000,
LanguageCode = "en",
EnableWordTimeOffsets = true,
}, RecognitionAudio.FromFile(filePath));
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
Console.WriteLine($"Transcript: { alternative.Transcript}");
Console.WriteLine("Word details:");
Console.WriteLine($" Word count:{alternative.Words.Count}");
foreach (var item in alternative.Words)
{
Console.WriteLine($" {item.Word}");
Console.WriteLine($" WordStartTime: {item.StartTime}");
Console.WriteLine($" WordEndTime: {item.EndTime}");
}
}
}
return(0);
}
static object SyncRecognizeWithCredentials(string filePath, string credentialsFilePath)
{
GoogleCredential googleCredential;
using (Stream m = new FileStream(credentialsFilePath, FileMode.Open))
googleCredential = GoogleCredential.FromStream(m);
var channel = new Grpc.Core.Channel(SpeechClient.DefaultEndpoint.Host,
googleCredential.ToChannelCredentials());
var speech = SpeechClient.Create(channel);
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);
}
public static string StartTranslate(string path, string lang)
{
var builder = new SpeechClientBuilder();
builder.CredentialsPath = "key.json";
var speech = builder.Build();
var config = new RecognitionConfig
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
LanguageCode = lang,
AudioChannelCount = 1
};
var audio = RecognitionAudio.FromFile(path);
var response = speech.Recognize(config, audio);
string fullText = "";
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
fullText += alternative.Transcript;
}
}
return(fullText);
}
static object RecognizeWithContext(string filePath, IEnumerable <string> phrases)
{
var speech = SpeechClient.Create();
var config = new RecognitionConfig()
{
SpeechContexts = { new SpeechContext()
{
Phrases ={ phrases }
} },
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 16000,
LanguageCode = "en",
};
var audio = IsStorageUri(filePath) ?
RecognitionAudio.FromStorageUri(filePath) :
RecognitionAudio.FromFile(filePath);
var response = speech.Recognize(config, audio);
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
Console.WriteLine(alternative.Transcript);
}
}
return(0);
}
public void FromFile()
{
using (var tempFile = TempFile.Generate(500))
{
var audio = RecognitionAudio.FromFile(tempFile.Name);
Assert.Equal(tempFile.Bytes, audio.Content.ToByteArray());
}
}
static void Main(string[] args)
{
var client = SpeechClient.Create();
var results = client.Recognize(new RecognitionConfig()
{
Encoding = AudioEncoding.Flac,
LanguageCode = "en",
}, RecognitionAudio.FromFile(@"c:\users\rennie\Music\audio.flac"));
JsonDumper.Dump(results);
}
private void SearchButton_Click(object sender, EventArgs e)
{
string wolframKey = "Wolframkeywhichicantuploadongithub";
string credential_path = @"I:/IgenVoiceRecognition-file.json";
System.Environment.SetEnvironmentVariable("GOOGLE_APPLICATION_CREDENTIALS", credential_path);
var speech = SpeechClient.Create();
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 16000,
LanguageCode = "en",
}, RecognitionAudio.FromFile("C:/Users/PrAnk/Desktop/test.flac"));
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
string str = alternative.Transcript;
if (str.StartsWith("answer"))
{
string wolframUrl = "http://api.wolframalpha.com/v2/query?input=" + str + "&appid=" + wolframKey;
/*
* WolframAlpha wolfram = new WolframAlpha(wolframKey);
*
* //Then you simply query Wolfram|Alpha like this
* //Note that the spelling error will be correct by Wolfram|Alpha
* QueryResult results = wolfram.Query("Who is Danald Duck?");
*
* //The QueryResult object contains the parsed XML from Wolfram|Alpha. Lets look at it.
* //The results from wolfram is split into "pods". We just print them.
* if (results != null)
* {
* foreach (Pod pod in results.Pods)
* {
* Console.WriteLine(pod.Title);
* if (pod.SubPods != null)
* {
* foreach (SubPod subPod in pod.SubPods)
* {
* Console.WriteLine(subPod.Title);
* MessageBox.Show(subPod.Title,subPod.Plaintext);
* }
* }
* }
* }
*/
}
Process.Start("chrome", alternative.Transcript);
}
}
}
static void Main(string[] args)
{
var client = SpeechClient.Create();
var results = client.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Flac,
LanguageCode = "en",
}, RecognitionAudio.FromFile("GCP_Speech_Input_Sample.flac"));
JsonDumper.Dump(results);
}
// Data processing functions
public static Boolean getGoogleResponse(String[] args)
{
Console.WriteLine("Getting goodle data...");
lastResponse = SpeechClient.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Flac,
SampleRateHertz = 44100,
LanguageCode = "en",
EnableWordTimeOffsets = true
}, RecognitionAudio.FromFile(FilePath));
Console.WriteLine("Data retreved.");
return(true);
}
public void OnClickGCPRecognitionButton()
{
var response = client.Recognize(
new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Flac,
SampleRateHertz = 22050,
LanguageCode = LanguageCodes.Japanese.Japan,
},
RecognitionAudio.FromFile(Application.streamingAssetsPath + "/test.flac")
);
Debug.Log(response);
}
private void btnSpeechInfo_Click(object sender, EventArgs e)
{
if (File.Exists("audio.raw"))
{
var speech = SpeechClient.Create();
bool currentAutoPunctuation = currentLanguage == "en"?true:false;
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 8000,
LanguageCode = currentLanguage,
EnableAutomaticPunctuation = currentAutoPunctuation
}, RecognitionAudio.FromFile("audio.raw"));
textBox1.Text = "";
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
speechConverter.OutputData = textBox1.Text + " " + alternative.Transcript;
}
}
textBox1.Text = speechConverter.OutputData;
if (textBox1.Text.Length == 0)
{
textBox1.Text = "No data";
}
speechConverter.OutputData = textBox1.Text;
}
else
{
textBox1.Text = "Audio File Missing";
return;
}
if (textBox1.Text != "No data" && SaveFileDialog.FileName != "")
{
TextFileCreator textFileCreator = new TextFileCreator(SaveFileDialog.FileName);
textFileCreator.WriteToFile(textBox1.Text);
}
if (openFileDialog1.FileName != "")
{
TextFileCreator textFileCreator = new TextFileCreator(openFileDialog1.FileName);
textFileCreator.WriteToFile(textBox1.Text);
}
menuStrip1.Enabled = true;
btnRecordVoice.Enabled = true;
btnSave.Enabled = false;
btnSpeechInfo.Enabled = false;
btnFindRelated.Enabled = false;
}
private void SpeechToText()
{
strRecgnResult = "";
var audio = RecognitionAudio.FromFile(outputFilePath);
var response = speech.Recognize(config, audio);
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
strRecgnResult += ((alternative.Transcript) + "...");
}
}
isResultRecieved = true;
}
public string ConvertSpeechToText(string waveFilePath)
{
//var fileDetails = new FileInfo(waveFilePath);
//if (fileDetails.Length > )
var speech = SpeechClient.Create();
var response = speech.Recognize(new RecognitionConfig
{
SampleRateHertz = 44100,
LanguageCode = "en"
}, RecognitionAudio.FromFile(waveFilePath));
var speechRecognitionAlternative = response.Results.FirstOrDefault()?.Alternatives.OrderBy(x => x.Confidence).FirstOrDefault();
return(speechRecognitionAlternative != null ? speechRecognitionAlternative.Transcript : string.Empty);
}
// Not an actual test... just examples
public void FactoryMethods()
{
// Sample: FactoryMethods
RecognitionAudio audio1 = RecognitionAudio.FromFile("Sound/SpeechSample.flac");
RecognitionAudio audio2 = RecognitionAudio.FromUri("https://.../HostedSpeech.flac");
RecognitionAudio audio3 = RecognitionAudio.FromStorageUri("gs://my-bucket/my-file");
byte[] bytes = ReadAudioData(); // For example, from a database
RecognitionAudio audio4 = RecognitionAudio.FromBytes(bytes);
using (Stream stream = OpenAudioStream()) // Any regular .NET stream
{
RecognitionAudio audio5 = RecognitionAudio.FromStream(stream);
}
// End sample
}
public static void Main(string[] args)
{
var speech = SpeechClient.Create();
var response = speech.SyncRecognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRate = 16000,
}, RecognitionAudio.FromFile("audio.raw"));
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
Console.WriteLine(alternative.Transcript);
}
}
}
// Transcribe a local audio file. We can only use this with audios up to 1 minute long.
public Transcribed_Dto TranscribeLocalFile(string fileName, string language)
{
// // var speechClient = SpeechClient.Create();
RecognitionAudio recogAudio = RecognitionAudio.FromFile(fileName);
var response = speechClient.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Flac,
SampleRateHertz = 48000,
EnableWordTimeOffsets = true,
LanguageCode = language,
}, recogAudio);
Transcribed_Dto resp = TransformResponse.Simpify(response.Results);
return(TransformResponse.FixSpeakerTags(resp));
}
private void TranscribeAudio(string fn)
{
uxTextbox.Text = "";
//string path = Path.Combine(Directory.GetParent(Directory.GetCurrentDirectory()).Parent.FullName, @"MyProject31047-87c642b30d06.json");
Environment.SetEnvironmentVariable("GOOGLE_APPLICATION_CREDENTIALS", "MyProject31047-87c642b30d06.json");
var speech = SpeechClient.Create();
if (hasRecorded)
{
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 16000,
LanguageCode = "en",
}, RecognitionAudio.FromFile(uxExportAudioDialog.FileName));
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
uxTextbox.Text += alternative.Transcript;
}
}
}
else if (fn != "")
{
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 16000,
LanguageCode = "en",
EnableAutomaticPunctuation = true,
}, RecognitionAudio.FromFile(fn));
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
uxTextbox.Text += alternative.Transcript;
}
}
}
else
{
MessageBox.Show("No Audio File Found");
}
}
public static void Main(string[] args)
{
Console.OutputEncoding = new System.Text.UTF8Encoding();
DotEnv.Config(true, "../../../.env");
var speech = SpeechClient.Create();
var response = speech.Recognize(
new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Flac,
SampleRateHertz = 22050,
LanguageCode = LanguageCodes.Japanese.Japan,
},
RecognitionAudio.FromFile(DEMO_FILE)
);
System.Console.WriteLine(response);
}
public static void Main(string[] args)
{
var speech = SpeechClient.Create();
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 16000,
LanguageCode = "en",
}, RecognitionAudio.FromFile(DEMO_FILE));
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
Debug.Log("Final: " + alternative.Transcript);
}
}
}
public static void Audio2Text(string filepath)
{
var speechClient = SpeechClient.Create();
var response = speechClient.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 16000,
LanguageCode = "ru"
}, RecognitionAudio.FromFile(filepath));
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
Console.WriteLine(alternative.Transcript);
}
}
}
// Transcribe a local audio file. We can only use this with audios up to 1 minute long.
public TranscribeResponse TranscribeFile(string fileName, string language)
{
var speech = SpeechClient.Create();
RecognitionAudio recogAudio = RecognitionAudio.FromFile(fileName);
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Flac,
SampleRateHertz = 48000,
EnableWordTimeOffsets = true,
LanguageCode = language,
}, recogAudio);
// Transform the Google response into a more usable object.
TranscribeResponse transcript = GetShortTranscribeResponse(response);
return(transcript);
}
// [START speech_sync_recognize]
static object SyncRecognize(string filePath)
{
var speech = SpeechClient.Create();
var response = speech.SyncRecognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRate = 16000,
}, RecognitionAudio.FromFile(filePath));
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
Console.WriteLine(alternative.Transcript);
}
}
return(0);
}
/// <summary>
/// Async recognition of file audio with credentials file(json)
/// </summary>
/// <param name="filePath"></param>
/// <param name="credentialsFilePath"></param>
/// <returns></returns>
public static object AsyncRecognizeGcsWordsWithCredentials(string filePath, string credentialsFilePath, int samplingRate)
{
//for credetial
GoogleCredential googleCredential;
using (Stream m = new FileStream(credentialsFilePath, FileMode.Open))
googleCredential = GoogleCredential.FromStream(m);
var channel = new Grpc.Core.Channel(SpeechClient.DefaultEndpoint.Host,
googleCredential.ToChannelCredentials());
var speech = SpeechClient.Create(channel);
//recognition settings
var longOperation = speech.LongRunningRecognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16, //Linear16 = wav
SampleRateHertz = samplingRate, //set the rate recorded in iPad
LanguageCode = "ja-JP", //English:en, Japanese: ja-JP
EnableWordTimeOffsets = true, //true: you can get timecodes of words
//MaxAlternatives = 3,// alternative count. this is max count. you sometimes get less number of alternatives you set. Alternatives don't have timecode
}, RecognitionAudio.FromFile(filePath));
longOperation = longOperation.PollUntilCompleted();
var response = longOperation.Result;
//recognition result
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
Console.WriteLine($"Transcript: { alternative.Transcript}");
Console.WriteLine($"Confidence: {alternative.Confidence}");
Console.WriteLine("Word details:");
Console.WriteLine($" Word count:{alternative.Words.Count}");
foreach (var item in alternative.Words)
{
Console.WriteLine($" {item.Word}");
Console.WriteLine($" WordStartTime: {item.StartTime}");
Console.WriteLine($" WordEndTime: {item.EndTime}");
}
}
}
return(0);
}
public string HttpUploadFile(string url, string file, string paramName, string contentType)
{
var speech = SpeechClient.Create();
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 48000,
LanguageCode = "en",
}, RecognitionAudio.FromFile(file));
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
return(alternative.Transcript);
}
}
return("nothing");
}
public static void Main(string[] args)
{
var speech = SpeechClient.Create();
var response = speech.Recognize(new RecognitionConfig()
{
Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
SampleRateHertz = 16000,
LanguageCode = "en",
}, RecognitionAudio.FromFile(DEMO_FILE));
foreach (var result in response.Results)
{
foreach (var alternative in result.Alternatives)
{
Console.WriteLine(alternative.Transcript);
}
}
CreateWebHostBuilder(args).Build().Run();
}
