仅“连续 LID”需要 SpeechServiceConnection_LanguageIdMode 属性。 如果不进行设置,语音服务默认为“启动时 LID”。 支持的值为启动时 LID AtStart 或连续 LID Continuous。
// Recognize once with At-start LID. Continuous LID isn't supported for recognize once.
var result = await recognizer.RecognizeOnceAsync();
// Start and stop continuous recognition with At-start LID
await recognizer.StartContinuousRecognitionAsync();
await recognizer.StopContinuousRecognitionAsync();
// Start and stop continuous recognition with Continuous LID
speechConfig.SetProperty(PropertyId.SpeechServiceConnection_LanguageIdMode, "Continuous");
await recognizer.StartContinuousRecognitionAsync();
await recognizer.StopContinuousRecognitionAsync();
// Recognize once with At-start LID. Continuous LID isn't supported for recognize once.
auto result = recognizer->RecognizeOnceAsync().get();
// Start and stop continuous recognition with At-start LID
recognizer->StartContinuousRecognitionAsync().get();
recognizer->StopContinuousRecognitionAsync().get();
// Start and stop continuous recognition with Continuous LID
speechConfig->SetProperty(PropertyId::SpeechServiceConnection_LanguageIdMode, "Continuous");
recognizer->StartContinuousRecognitionAsync().get();
recognizer->StopContinuousRecognitionAsync().get();
// Recognize once with At-start LID. Continuous LID isn't supported for recognize once.
SpeechRecognitionResult result = recognizer->RecognizeOnceAsync().get();
// Start and stop continuous recognition with At-start LID
recognizer.startContinuousRecognitionAsync().get();
recognizer.stopContinuousRecognitionAsync().get();
// Start and stop continuous recognition with Continuous LID
speechConfig.setProperty(PropertyId.SpeechServiceConnection_LanguageIdMode, "Continuous");
recognizer.startContinuousRecognitionAsync().get();
recognizer.stopContinuousRecognitionAsync().get();
# Recognize once with At-start LID. Continuous LID isn't supported for recognize once.
result = recognizer.recognize_once()
# Start and stop continuous recognition with At-start LID
recognizer.start_continuous_recognition()
recognizer.stop_continuous_recognition()
# Start and stop continuous recognition with Continuous LID
speech_config.set_property(property_id=speechsdk.PropertyId.SpeechServiceConnection_LanguageIdMode, value='Continuous')
recognizer.start_continuous_recognition()
recognizer.stop_continuous_recognition()
using Microsoft.CognitiveServices.Speech;
using Microsoft.CognitiveServices.Speech.Audio;
var speechConfig = SpeechConfig.FromSubscription("YourSubscriptionKey","YourServiceRegion");
var autoDetectSourceLanguageConfig =
AutoDetectSourceLanguageConfig.FromLanguages(
new string[] { "en-US", "de-DE", "zh-cn" });
using var audioConfig = AudioConfig.FromDefaultMicrophoneInput();
using (var recognizer = new SpeechRecognizer(
speechConfig,
autoDetectSourceLanguageConfig,
audioConfig))
{
var speechRecognitionResult = await recognizer.RecognizeOnceAsync();
var autoDetectSourceLanguageResult =
AutoDetectSourceLanguageResult.FromResult(speechRecognitionResult);
var detectedLanguage = autoDetectSourceLanguageResult.Language;
}
using Microsoft.CognitiveServices.Speech;
using Microsoft.CognitiveServices.Speech.Audio;
var region = "YourServiceRegion";
// Currently the v2 endpoint is required. In a future SDK release you won't need to set it.
var endpointString = $"wss://{region}.stt.speech.azure.cn/speech/universal/v2";
var endpointUrl = new Uri(endpointString);
var config = SpeechConfig.FromEndpoint(endpointUrl, "YourSubscriptionKey");
// Set the LanguageIdMode (Optional; Either Continuous or AtStart are accepted; Default AtStart)
config.SetProperty(PropertyId.SpeechServiceConnection_LanguageIdMode, "Continuous");
var autoDetectSourceLanguageConfig = AutoDetectSourceLanguageConfig.FromLanguages(new string[] { "en-US", "de-DE", "zh-cn" });
var stopRecognition = new TaskCompletionSource<int>();
using (var audioInput = AudioConfig.FromWavFileInput(@"en-us_zh-cn.wav"))
{
using (var recognizer = new SpeechRecognizer(config, autoDetectSourceLanguageConfig, audioInput))
{
// Subscribes to events.
recognizer.Recognizing += (s, e) =>
{
if (e.Result.Reason == ResultReason.RecognizingSpeech)
{
Console.WriteLine($"RECOGNIZING: Text={e.Result.Text}");
var autoDetectSourceLanguageResult = AutoDetectSourceLanguageResult.FromResult(e.Result);
Console.WriteLine($"DETECTED: Language={autoDetectSourceLanguageResult.Language}");
}
};
recognizer.Recognized += (s, e) =>
{
if (e.Result.Reason == ResultReason.RecognizedSpeech)
{
Console.WriteLine($"RECOGNIZED: Text={e.Result.Text}");
var autoDetectSourceLanguageResult = AutoDetectSourceLanguageResult.FromResult(e.Result);
Console.WriteLine($"DETECTED: Language={autoDetectSourceLanguageResult.Language}");
}
else if (e.Result.Reason == ResultReason.NoMatch)
{
Console.WriteLine($"NOMATCH: Speech could not be recognized.");
}
};
recognizer.Canceled += (s, e) =>
{
Console.WriteLine($"CANCELED: Reason={e.Reason}");
if (e.Reason == CancellationReason.Error)
{
Console.WriteLine($"CANCELED: ErrorCode={e.ErrorCode}");
Console.WriteLine($"CANCELED: ErrorDetails={e.ErrorDetails}");
Console.WriteLine($"CANCELED: Did you set the speech resource key and region values?");
}
stopRecognition.TrySetResult(0);
};
recognizer.SessionStarted += (s, e) =>
{
Console.WriteLine("\n Session started event.");
};
recognizer.SessionStopped += (s, e) =>
{
Console.WriteLine("\n Session stopped event.");
Console.WriteLine("\nStop recognition.");
stopRecognition.TrySetResult(0);
};
// Starts continuous recognition. Uses StopContinuousRecognitionAsync() to stop recognition.
await recognizer.StartContinuousRecognitionAsync().ConfigureAwait(false);
// Waits for completion.
// Use Task.WaitAny to keep the task rooted.
Task.WaitAny(new[] { stopRecognition.Task });
// Stops recognition.
await recognizer.StopContinuousRecognitionAsync().ConfigureAwait(false);
}
}
using namespace std;
using namespace Microsoft::CognitiveServices::Speech;
using namespace Microsoft::CognitiveServices::Speech::Audio;
auto speechConfig = SpeechConfig::FromSubscription("YourSubscriptionKey","YourServiceRegion");
auto autoDetectSourceLanguageConfig =
AutoDetectSourceLanguageConfig::FromLanguages({ "en-US", "de-DE", "zh-cn" });
auto recognizer = SpeechRecognizer::FromConfig(
speechConfig,
autoDetectSourceLanguageConfig
);
speechRecognitionResult = recognizer->RecognizeOnceAsync().get();
auto autoDetectSourceLanguageResult =
AutoDetectSourceLanguageResult::FromResult(speechRecognitionResult);
auto detectedLanguage = autoDetectSourceLanguageResult->Language;
// Creates an instance of a speech config with specified subscription key and service region.
// Note: For multi-lingual speech recognition with language id, it only works with speech v2 endpoint,
// you must use FromEndpoint api in order to use the speech v2 endpoint.
// Replace YourServiceRegion with your region, for example "chinanorth2", and
// replace YourSubscriptionKey with your own speech key.
string speechv2Endpoint = "wss://YourServiceRegion.stt.speech.azure.cn/speech/universal/v2";
auto speechConfig = SpeechConfig::FromEndpoint(speechv2Endpoint, "YourSubscriptionKey");
// Set the mode of input language detection to either "AtStart" (the default) or "Continuous".
// Please refer to the documentation of Language ID for more information.
// https://docs.azure.cn/en-us/cognitive-services/speech-service/language-identification?pivots=programming-language-cpp&tabs=once
speechConfig->SetProperty(PropertyId::SpeechServiceConnection_LanguageIdMode, "Continuous");
// Define the set of languages to detect
auto autoDetectSourceLanguageConfig = AutoDetectSourceLanguageConfig::FromLanguages({ "en-US", "zh-cn" });
// Creates a speech recognizer using file as audio input.
// Replace with your own audio file name.
auto audioInput = AudioConfig::FromWavFileInput("en-us_zh-cn.wav");
auto recognizer = SpeechRecognizer::FromConfig(speechConfig, autoDetectSourceLanguageConfig, audioInput);
// promise for synchronization of recognition end.
promise<void> recognitionEnd;
// Subscribes to events.
recognizer->Recognizing.Connect([](const SpeechRecognitionEventArgs& e)
{
auto lidResult = AutoDetectSourceLanguageResult::FromResult(e.Result);
cout << "Recognizing in " << lidResult->Language << ": Text =" << e.Result->Text << std::endl;
});
recognizer->Recognized.Connect([](const SpeechRecognitionEventArgs& e)
{
if (e.Result->Reason == ResultReason::RecognizedSpeech)
{
auto lidResult = AutoDetectSourceLanguageResult::FromResult(e.Result);
cout << "RECOGNIZED in " << lidResult->Language << ": Text=" << e.Result->Text << "\n"
<< " Offset=" << e.Result->Offset() << "\n"
<< " Duration=" << e.Result->Duration() << std::endl;
}
else if (e.Result->Reason == ResultReason::NoMatch)
{
cout << "NOMATCH: Speech could not be recognized." << std::endl;
}
});
recognizer->Canceled.Connect([&recognitionEnd](const SpeechRecognitionCanceledEventArgs& e)
{
cout << "CANCELED: Reason=" << (int)e.Reason << std::endl;
if (e.Reason == CancellationReason::Error)
{
cout << "CANCELED: ErrorCode=" << (int)e.ErrorCode << "\n"
<< "CANCELED: ErrorDetails=" << e.ErrorDetails << "\n"
<< "CANCELED: Did you update the subscription info?" << std::endl;
recognitionEnd.set_value(); // Notify to stop recognition.
}
});
recognizer->SessionStopped.Connect([&recognitionEnd](const SessionEventArgs& e)
{
cout << "Session stopped.";
recognitionEnd.set_value(); // Notify to stop recognition.
});
// Starts continuous recognition. Uses StopContinuousRecognitionAsync() to stop recognition.
recognizer->StartContinuousRecognitionAsync().get();
// Waits for recognition end.
recognitionEnd.get_future().get();
// Stops recognition.
recognizer->StopContinuousRecognitionAsync().get();
public static void continuousRecognitionFromFileWithAtStartLanguageDetection() throws InterruptedException, ExecutionException, IOException
{
// Creates an instance of a speech config with specified subscription key and service region. Replace with your own subscription key
// and service region (e.g., "chinaeast2").
SpeechConfig speechConfig = SpeechConfig.fromSubscription("YourSubscriptionKey", "YourServiceRegion");
// Define a set of expected spoken languages in the audio. Update the below with your own languages.
// Please see /cognitive-services/speech-service/language-support for all supported languages.
AutoDetectSourceLanguageConfig autoDetectSourceLanguageConfig = AutoDetectSourceLanguageConfig.fromLanguages(Arrays.asList("en-US", "es-MX", "de-DE"));
// We provide a WAV file with Spanish speech as an example. Replace it with your own.
AudioConfig audioConfig = AudioConfig.fromWavFileInput("es-mx.wav");
// Creates a speech recognizer using file as audio input and the AutoDetectSourceLanguageConfig
SpeechRecognizer speechRecognizer = new SpeechRecognizer(speechConfig, autoDetectSourceLanguageConfig, audioConfig);
// Semaphore used to signal the call to stop continuous recognition (following either a session ended or a cancelled event)
final Semaphore doneSemaphone = new Semaphore(0);
// Subscribes to events.
speechRecognizer.recognizing.addEventListener((s, e) -> {
AutoDetectSourceLanguageResult autoDetectSourceLanguageResult = AutoDetectSourceLanguageResult.fromResult(e.getResult());
String language = autoDetectSourceLanguageResult.getLanguage();
System.out.println(" RECOGNIZING: Text = " + e.getResult().getText());
System.out.println(" RECOGNIZING: Language = " + language);
});
speechRecognizer.recognized.addEventListener((s, e) -> {
AutoDetectSourceLanguageResult autoDetectSourceLanguageResult = AutoDetectSourceLanguageResult.fromResult(e.getResult());
String language = autoDetectSourceLanguageResult.getLanguage();
if (e.getResult().getReason() == ResultReason.RecognizedSpeech) {
System.out.println(" RECOGNIZED: Text = " + e.getResult().getText());
System.out.println(" RECOGNIZED: Language = " + language);
}
else if (e.getResult().getReason() == ResultReason.NoMatch) {
if (language == null || language.isEmpty() || language.toLowerCase().equals("unknown")) {
System.out.println(" NOMATCH: Speech Language could not be detected.");
}
else {
System.out.println(" NOMATCH: Speech could not be recognized.");
}
}
});
speechRecognizer.canceled.addEventListener((s, e) -> {
System.out.println(" CANCELED: Reason = " + e.getReason());
if (e.getReason() == CancellationReason.Error) {
System.out.println(" CANCELED: ErrorCode = " + e.getErrorCode());
System.out.println(" CANCELED: ErrorDetails = " + e.getErrorDetails());
System.out.println(" CANCELED: Did you update the subscription info?");
}
doneSemaphone.release();
});
speechRecognizer.sessionStarted.addEventListener((s, e) -> {
System.out.println("\n Session started event.");
});
speechRecognizer.sessionStopped.addEventListener((s, e) -> {
System.out.println("\n Session stopped event.");
doneSemaphone.release();
});
// Starts continuous recognition and wait for processing to end
System.out.println(" Recognizing from WAV file... please wait");
speechRecognizer.startContinuousRecognitionAsync().get();
doneSemaphone.tryAcquire(30, TimeUnit.SECONDS);
// Stop continuous recognition
speechRecognizer.stopContinuousRecognitionAsync().get();
// These objects must be closed in order to dispose underlying native resources
speechRecognizer.close();
speechConfig.close();
audioConfig.close();
autoDetectSourceLanguageConfig.close();
}
import azure.cognitiveservices.speech as speechsdk
import time
import json
speech_key, service_region = "YourSubscriptionKey","YourServiceRegion"
weatherfilename="en-us_zh-cn.wav"
# Currently the v2 endpoint is required. In a future SDK release you won't need to set it.
endpoint_string = "wss://{}.stt.speech.azure.cn/speech/universal/v2".format(service_region)
speech_config = speechsdk.SpeechConfig(subscription=speech_key, endpoint=endpoint_string)
audio_config = speechsdk.audio.AudioConfig(filename=weatherfilename)
# Set the LanguageIdMode (Optional; Either Continuous or AtStart are accepted; Default AtStart)
speech_config.set_property(property_id=speechsdk.PropertyId.SpeechServiceConnection_LanguageIdMode, value='Continuous')
auto_detect_source_language_config = speechsdk.languageconfig.AutoDetectSourceLanguageConfig(
languages=["en-US", "de-DE", "zh-cn"])
speech_recognizer = speechsdk.SpeechRecognizer(
speech_config=speech_config,
auto_detect_source_language_config=auto_detect_source_language_config,
audio_config=audio_config)
done = False
def stop_cb(evt):
"""callback that signals to stop continuous recognition upon receiving an event `evt`"""
print('CLOSING on {}'.format(evt))
nonlocal done
done = True
# Connect callbacks to the events fired by the speech recognizer
speech_recognizer.recognizing.connect(lambda evt: print('RECOGNIZING: {}'.format(evt)))
speech_recognizer.recognized.connect(lambda evt: print('RECOGNIZED: {}'.format(evt)))
speech_recognizer.session_started.connect(lambda evt: print('SESSION STARTED: {}'.format(evt)))
speech_recognizer.session_stopped.connect(lambda evt: print('SESSION STOPPED {}'.format(evt)))
speech_recognizer.canceled.connect(lambda evt: print('CANCELED {}'.format(evt)))
# stop continuous recognition on either session stopped or canceled events
speech_recognizer.session_stopped.connect(stop_cb)
speech_recognizer.canceled.connect(stop_cb)
# Start continuous speech recognition
speech_recognizer.start_continuous_recognition()
while not done:
time.sleep(.5)
speech_recognizer.stop_continuous_recognition()
var sourceLanguageConfigs = new SourceLanguageConfig[]
{
SourceLanguageConfig.FromLanguage("en-US"),
SourceLanguageConfig.FromLanguage("fr-FR", "The Endpoint Id for custom model of fr-FR")
};
var autoDetectSourceLanguageConfig =
AutoDetectSourceLanguageConfig.FromSourceLanguageConfigs(
sourceLanguageConfigs);
std::vector<std::shared_ptr<SourceLanguageConfig>> sourceLanguageConfigs;
sourceLanguageConfigs.push_back(
SourceLanguageConfig::FromLanguage("en-US"));
sourceLanguageConfigs.push_back(
SourceLanguageConfig::FromLanguage("fr-FR", "The Endpoint Id for custom model of fr-FR"));
auto autoDetectSourceLanguageConfig =
AutoDetectSourceLanguageConfig::FromSourceLanguageConfigs(
sourceLanguageConfigs);
List sourceLanguageConfigs = new ArrayList<SourceLanguageConfig>();
sourceLanguageConfigs.add(
SourceLanguageConfig.fromLanguage("en-US"));
sourceLanguageConfigs.add(
SourceLanguageConfig.fromLanguage("fr-FR", "The Endpoint Id for custom model of fr-FR"));
AutoDetectSourceLanguageConfig autoDetectSourceLanguageConfig =
AutoDetectSourceLanguageConfig.fromSourceLanguageConfigs(
sourceLanguageConfigs);
en_language_config = speechsdk.languageconfig.SourceLanguageConfig("en-US")
fr_language_config = speechsdk.languageconfig.SourceLanguageConfig("fr-FR", "The Endpoint Id for custom model of fr-FR")
auto_detect_source_language_config = speechsdk.languageconfig.AutoDetectSourceLanguageConfig(
sourceLanguageConfigs=[en_language_config, fr_language_config])
SPXSourceLanguageConfiguration* enLanguageConfig = [[SPXSourceLanguageConfiguration alloc]init:@"en-US"];
SPXSourceLanguageConfiguration* frLanguageConfig = \
[[SPXSourceLanguageConfiguration alloc]initWithLanguage:@"fr-FR"
endpointId:@"The Endpoint Id for custom model of fr-FR"];
NSArray *languageConfigs = @[enLanguageConfig, frLanguageConfig];
SPXAutoDetectSourceLanguageConfiguration* autoDetectSourceLanguageConfig = \
[[SPXAutoDetectSourceLanguageConfiguration alloc]initWithSourceLanguageConfigurations:languageConfigs];
var enLanguageConfig = SpeechSDK.SourceLanguageConfig.fromLanguage("en-US");
var frLanguageConfig = SpeechSDK.SourceLanguageConfig.fromLanguage("fr-FR", "The Endpoint Id for custom model of fr-FR");
var autoDetectSourceLanguageConfig = SpeechSDK.AutoDetectSourceLanguageConfig.fromSourceLanguageConfigs([enLanguageConfig, frLanguageConfig]);
using Microsoft.CognitiveServices.Speech;
using Microsoft.CognitiveServices.Speech.Audio;
using Microsoft.CognitiveServices.Speech.Translation;
public static async Task RecognizeOnceSpeechTranslationAsync()
{
var region = "YourServiceRegion";
// Currently the v2 endpoint is required. In a future SDK release you won't need to set it.
var endpointString = $"wss://{region}.stt.speech.azure.cn/speech/universal/v2";
var endpointUrl = new Uri(endpointString);
var config = SpeechTranslationConfig.FromEndpoint(endpointUrl, "YourSubscriptionKey");
// Source language is required, but currently ignored.
string fromLanguage = "en-US";
speechTranslationConfig.SpeechRecognitionLanguage = fromLanguage;
speechTranslationConfig.AddTargetLanguage("de");
speechTranslationConfig.AddTargetLanguage("fr");
var autoDetectSourceLanguageConfig = AutoDetectSourceLanguageConfig.FromLanguages(new string[] { "en-US", "de-DE", "zh-cn" });
using var audioConfig = AudioConfig.FromDefaultMicrophoneInput();
using (var recognizer = new TranslationRecognizer(
speechTranslationConfig,
autoDetectSourceLanguageConfig,
audioConfig))
{
Console.WriteLine("Say something or read from file...");
var result = await recognizer.RecognizeOnceAsync().ConfigureAwait(false);
if (result.Reason == ResultReason.TranslatedSpeech)
{
var lidResult = result.Properties.GetProperty(PropertyId.SpeechServiceConnection_AutoDetectSourceLanguageResult);
Console.WriteLine($"RECOGNIZED in '{lidResult}': Text={result.Text}");
foreach (var element in result.Translations)
{
Console.WriteLine($" TRANSLATED into '{element.Key}': {element.Value}");
}
}
}
}
using Microsoft.CognitiveServices.Speech;
using Microsoft.CognitiveServices.Speech.Audio;
using Microsoft.CognitiveServices.Speech.Translation;
public static async Task MultiLingualTranslation()
{
var region = "YourServiceRegion";
// Currently the v2 endpoint is required. In a future SDK release you won't need to set it.
var endpointString = $"wss://{region}.stt.speech.azure.cn/speech/universal/v2";
var endpointUrl = new Uri(endpointString);
var config = SpeechTranslationConfig.FromEndpoint(endpointUrl, "YourSubscriptionKey");
// Source language is required, but currently ignored.
string fromLanguage = "en-US";
config.SpeechRecognitionLanguage = fromLanguage;
config.AddTargetLanguage("de");
config.AddTargetLanguage("fr");
// Set the LanguageIdMode (Optional; Either Continuous or AtStart are accepted; Default AtStart)
config.SetProperty(PropertyId.SpeechServiceConnection_LanguageIdMode, "Continuous");
var autoDetectSourceLanguageConfig = AutoDetectSourceLanguageConfig.FromLanguages(new string[] { "en-US", "de-DE", "zh-cn" });
var stopTranslation = new TaskCompletionSource<int>();
using (var audioInput = AudioConfig.FromWavFileInput(@"en-us_zh-cn.wav"))
{
using (var recognizer = new TranslationRecognizer(config, autoDetectSourceLanguageConfig, audioInput))
{
recognizer.Recognizing += (s, e) =>
{
var lidResult = e.Result.Properties.GetProperty(PropertyId.SpeechServiceConnection_AutoDetectSourceLanguageResult);
Console.WriteLine($"RECOGNIZING in '{lidResult}': Text={e.Result.Text}");
foreach (var element in e.Result.Translations)
{
Console.WriteLine($" TRANSLATING into '{element.Key}': {element.Value}");
}
};
recognizer.Recognized += (s, e) => {
if (e.Result.Reason == ResultReason.TranslatedSpeech)
{
var lidResult = e.Result.Properties.GetProperty(PropertyId.SpeechServiceConnection_AutoDetectSourceLanguageResult);
Console.WriteLine($"RECOGNIZED in '{lidResult}': Text={e.Result.Text}");
foreach (var element in e.Result.Translations)
{
Console.WriteLine($" TRANSLATED into '{element.Key}': {element.Value}");
}
}
else if (e.Result.Reason == ResultReason.RecognizedSpeech)
{
Console.WriteLine($"RECOGNIZED: Text={e.Result.Text}");
Console.WriteLine($" Speech not translated.");
}
else if (e.Result.Reason == ResultReason.NoMatch)
{
Console.WriteLine($"NOMATCH: Speech could not be recognized.");
}
};
recognizer.Canceled += (s, e) =>
{
Console.WriteLine($"CANCELED: Reason={e.Reason}");
if (e.Reason == CancellationReason.Error)
{
Console.WriteLine($"CANCELED: ErrorCode={e.ErrorCode}");
Console.WriteLine($"CANCELED: ErrorDetails={e.ErrorDetails}");
Console.WriteLine($"CANCELED: Did you set the speech resource key and region values?");
}
stopTranslation.TrySetResult(0);
};
recognizer.SpeechStartDetected += (s, e) => {
Console.WriteLine("\nSpeech start detected event.");
};
recognizer.SpeechEndDetected += (s, e) => {
Console.WriteLine("\nSpeech end detected event.");
};
recognizer.SessionStarted += (s, e) => {
Console.WriteLine("\nSession started event.");
};
recognizer.SessionStopped += (s, e) => {
Console.WriteLine("\nSession stopped event.");
Console.WriteLine($"\nStop translation.");
stopTranslation.TrySetResult(0);
};
// Starts continuous recognition. Uses StopContinuousRecognitionAsync() to stop recognition.
Console.WriteLine("Start translation...");
await recognizer.StartContinuousRecognitionAsync().ConfigureAwait(false);
Task.WaitAny(new[] { stopTranslation.Task });
await recognizer.StopContinuousRecognitionAsync().ConfigureAwait(false);
}
}
}
auto region = "YourServiceRegion";
// Currently the v2 endpoint is required. In a future SDK release you won't need to set it.
auto endpointString = std::format("wss://{}.stt.speech.azure.cn/speech/universal/v2", region);
auto config = SpeechTranslationConfig::FromEndpoint(endpointString, "YourSubscriptionKey");
auto autoDetectSourceLanguageConfig = AutoDetectSourceLanguageConfig::FromLanguages({ "en-US", "de-DE" });
// Sets source and target languages
// The source language will be detected by the language detection feature.
// However, the SpeechRecognitionLanguage still need to set with a locale string, but it will not be used as the source language.
// This will be fixed in a future version of Speech SDK.
auto fromLanguage = "en-US";
config->SetSpeechRecognitionLanguage(fromLanguage);
config->AddTargetLanguage("de");
config->AddTargetLanguage("fr");
// Creates a translation recognizer using microphone as audio input.
auto recognizer = TranslationRecognizer::FromConfig(config, autoDetectSourceLanguageConfig);
cout << "Say something...\n";
// Starts translation, and returns after a single utterance is recognized. The end of a
// single utterance is determined by listening for silence at the end or until a maximum of 15
// seconds of audio is processed. The task returns the recognized text as well as the translation.
// Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single
// shot recognition like command or query.
// For long-running multi-utterance recognition, use StartContinuousRecognitionAsync() instead.
auto result = recognizer->RecognizeOnceAsync().get();
// Checks result.
if (result->Reason == ResultReason::TranslatedSpeech)
{
cout << "RECOGNIZED: Text=" << result->Text << std::endl;
for (const auto& it : result->Translations)
{
cout << "TRANSLATED into '" << it.first.c_str() << "': " << it.second.c_str() << std::endl;
}
}
else if (result->Reason == ResultReason::RecognizedSpeech)
{
cout << "RECOGNIZED: Text=" << result->Text << " (text could not be translated)" << std::endl;
}
else if (result->Reason == ResultReason::NoMatch)
{
cout << "NOMATCH: Speech could not be recognized." << std::endl;
}
else if (result->Reason == ResultReason::Canceled)
{
auto cancellation = CancellationDetails::FromResult(result);
cout << "CANCELED: Reason=" << (int)cancellation->Reason << std::endl;
if (cancellation->Reason == CancellationReason::Error)
{
cout << "CANCELED: ErrorCode=" << (int)cancellation->ErrorCode << std::endl;
cout << "CANCELED: ErrorDetails=" << cancellation->ErrorDetails << std::endl;
cout << "CANCELED: Did you set the speech resource key and region values?" << std::endl;
}
}
using namespace std;
using namespace Microsoft::CognitiveServices::Speech;
using namespace Microsoft::CognitiveServices::Speech::Audio;
using namespace Microsoft::CognitiveServices::Speech::Translation;
void MultiLingualTranslation()
{
auto region = "YourServiceRegion";
// Currently the v2 endpoint is required. In a future SDK release you won't need to set it.
auto endpointString = std::format("wss://{}.stt.speech.azure.cn/speech/universal/v2", region);
auto config = SpeechTranslationConfig::FromEndpoint(endpointString, "YourSubscriptionKey");
// Set the LanguageIdMode (Optional; Either Continuous or AtStart are accepted; Default AtStart)
speechConfig->SetProperty(PropertyId::SpeechServiceConnection_LanguageIdMode, "Continuous");
auto autoDetectSourceLanguageConfig = AutoDetectSourceLanguageConfig::FromLanguages({ "en-US", "de-DE", "zh-cn" });
promise<void> recognitionEnd;
// Source language is required, but currently ignored.
auto fromLanguage = "en-US";
config->SetSpeechRecognitionLanguage(fromLanguage);
config->AddTargetLanguage("de");
config->AddTargetLanguage("fr");
auto audioInput = AudioConfig::FromWavFileInput("whatstheweatherlike.wav");
auto recognizer = TranslationRecognizer::FromConfig(config, autoDetectSourceLanguageConfig, audioInput);
recognizer->Recognizing.Connect([](const TranslationRecognitionEventArgs& e)
{
std::string lidResult = e.Result->Properties.GetProperty(PropertyId::SpeechServiceConnection_AutoDetectSourceLanguageResult);
cout << "Recognizing in Language = "<< lidResult << ":" << e.Result->Text << std::endl;
for (const auto& it : e.Result->Translations)
{
cout << " Translated into '" << it.first.c_str() << "': " << it.second.c_str() << std::endl;
}
});
recognizer->Recognized.Connect([](const TranslationRecognitionEventArgs& e)
{
if (e.Result->Reason == ResultReason::TranslatedSpeech)
{
std::string lidResult = e.Result->Properties.GetProperty(PropertyId::SpeechServiceConnection_AutoDetectSourceLanguageResult);
cout << "RECOGNIZED in Language = " << lidResult << ": Text=" << e.Result->Text << std::endl;
}
else if (e.Result->Reason == ResultReason::RecognizedSpeech)
{
cout << "RECOGNIZED: Text=" << e.Result->Text << " (text could not be translated)" << std::endl;
}
else if (e.Result->Reason == ResultReason::NoMatch)
{
cout << "NOMATCH: Speech could not be recognized." << std::endl;
}
for (const auto& it : e.Result->Translations)
{
cout << " Translated into '" << it.first.c_str() << "': " << it.second.c_str() << std::endl;
}
});
recognizer->Canceled.Connect([&recognitionEnd](const TranslationRecognitionCanceledEventArgs& e)
{
cout << "CANCELED: Reason=" << (int)e.Reason << std::endl;
if (e.Reason == CancellationReason::Error)
{
cout << "CANCELED: ErrorCode=" << (int)e.ErrorCode << std::endl;
cout << "CANCELED: ErrorDetails=" << e.ErrorDetails << std::endl;
cout << "CANCELED: Did you set the speech resource key and region values?" << std::endl;
recognitionEnd.set_value();
}
});
recognizer->Synthesizing.Connect([](const TranslationSynthesisEventArgs& e)
{
auto size = e.Result->Audio.size();
cout << "Translation synthesis result: size of audio data: " << size
<< (size == 0 ? "(END)" : "");
});
recognizer->SessionStopped.Connect([&recognitionEnd](const SessionEventArgs& e)
{
cout << "Session stopped.";
recognitionEnd.set_value();
});
// Starts continuos recognition. Use StopContinuousRecognitionAsync() to stop recognition.
recognizer->StartContinuousRecognitionAsync().get();
recognitionEnd.get_future().get();
recognizer->StopContinuousRecognitionAsync().get();
}
import azure.cognitiveservices.speech as speechsdk
import time
import json
speech_key, service_region = "YourSubscriptionKey","YourServiceRegion"
weatherfilename="en-us_zh-cn.wav"
# set up translation parameters: source language and target languages
# Currently the v2 endpoint is required. In a future SDK release you won't need to set it.
endpoint_string = "wss://{}.stt.speech.azure.cn/speech/universal/v2".format(service_region)
translation_config = speechsdk.translation.SpeechTranslationConfig(
subscription=speech_key,
endpoint=endpoint_string,
speech_recognition_language='en-US',
target_languages=('de', 'fr'))
audio_config = speechsdk.audio.AudioConfig(filename=weatherfilename)
# Specify the AutoDetectSourceLanguageConfig, which defines the number of possible languages
auto_detect_source_language_config = speechsdk.languageconfig.AutoDetectSourceLanguageConfig(languages=["en-US", "de-DE", "zh-cn"])
# Creates a translation recognizer using and audio file as input.
recognizer = speechsdk.translation.TranslationRecognizer(
translation_config=translation_config,
audio_config=audio_config,
auto_detect_source_language_config=auto_detect_source_language_config)
# Starts translation, and returns after a single utterance is recognized. The end of a
# single utterance is determined by listening for silence at the end or until a maximum of 15
# seconds of audio is processed. The task returns the recognition text as result.
# Note: Since recognize_once() returns only a single utterance, it is suitable only for single
# shot recognition like command or query.
# For long-running multi-utterance recognition, use start_continuous_recognition() instead.
result = recognizer.recognize_once()
# Check the result
if result.reason == speechsdk.ResultReason.TranslatedSpeech:
print("""Recognized: {}
German translation: {}
French translation: {}""".format(
result.text, result.translations['de'], result.translations['fr']))
elif result.reason == speechsdk.ResultReason.RecognizedSpeech:
print("Recognized: {}".format(result.text))
detectedSrcLang = result.properties[speechsdk.PropertyId.SpeechServiceConnection_AutoDetectSourceLanguageResult]
print("Detected Language: {}".format(detectedSrcLang))
elif result.reason == speechsdk.ResultReason.NoMatch:
print("No speech could be recognized: {}".format(result.no_match_details))
elif result.reason == speechsdk.ResultReason.Canceled:
print("Translation canceled: {}".format(result.cancellation_details.reason))
if result.cancellation_details.reason == speechsdk.CancellationReason.Error:
print("Error details: {}".format(result.cancellation_details.error_details))
import azure.cognitiveservices.speech as speechsdk
import time
import json
speech_key, service_region = "YourSubscriptionKey","YourServiceRegion"
weatherfilename="en-us_zh-cn.wav"
# Currently the v2 endpoint is required. In a future SDK release you won't need to set it.
endpoint_string = "wss://{}.stt.speech.azure.cn/speech/universal/v2".format(service_region)
translation_config = speechsdk.translation.SpeechTranslationConfig(
subscription=speech_key,
endpoint=endpoint_string,
speech_recognition_language='en-US',
target_languages=('de', 'fr'))
audio_config = speechsdk.audio.AudioConfig(filename=weatherfilename)
# Set the LanguageIdMode (Optional; Either Continuous or AtStart are accepted; Default AtStart)
translation_config.set_property(property_id=speechsdk.PropertyId.SpeechServiceConnection_LanguageIdMode, value='Continuous')
# Specify the AutoDetectSourceLanguageConfig, which defines the number of possible languages
auto_detect_source_language_config = speechsdk.languageconfig.AutoDetectSourceLanguageConfig(languages=["en-US", "de-DE", "zh-cn"])
# Creates a translation recognizer using and audio file as input.
recognizer = speechsdk.translation.TranslationRecognizer(
translation_config=translation_config,
audio_config=audio_config,
auto_detect_source_language_config=auto_detect_source_language_config)
def result_callback(event_type, evt):
"""callback to display a translation result"""
print("{}: {}\n\tTranslations: {}\n\tResult Json: {}".format(
event_type, evt, evt.result.translations.items(), evt.result.json))
done = False
def stop_cb(evt):
"""callback that signals to stop continuous recognition upon receiving an event `evt`"""
print('CLOSING on {}'.format(evt))
nonlocal done
done = True
# connect callback functions to the events fired by the recognizer
recognizer.session_started.connect(lambda evt: print('SESSION STARTED: {}'.format(evt)))
recognizer.session_stopped.connect(lambda evt: print('SESSION STOPPED {}'.format(evt)))
# event for intermediate results
recognizer.recognizing.connect(lambda evt: result_callback('RECOGNIZING', evt))
# event for final result
recognizer.recognized.connect(lambda evt: result_callback('RECOGNIZED', evt))
# cancellation event
recognizer.canceled.connect(lambda evt: print('CANCELED: {} ({})'.format(evt, evt.reason)))
# stop continuous recognition on either session stopped or canceled events
recognizer.session_stopped.connect(stop_cb)
recognizer.canceled.connect(stop_cb)
def synthesis_callback(evt):
"""
callback for the synthesis event
"""
print('SYNTHESIZING {}\n\treceived {} bytes of audio. Reason: {}'.format(
evt, len(evt.result.audio), evt.result.reason))
if evt.result.reason == speechsdk.ResultReason.RecognizedSpeech:
print("RECOGNIZED: {}".format(evt.result.properties))
if evt.result.properties.get(speechsdk.PropertyId.SpeechServiceConnection_AutoDetectSourceLanguageResult) == None:
print("Unable to detect any language")
else:
detectedSrcLang = evt.result.properties[speechsdk.PropertyId.SpeechServiceConnection_AutoDetectSourceLanguageResult]
jsonResult = evt.result.properties[speechsdk.PropertyId.SpeechServiceResponse_JsonResult]
detailResult = json.loads(jsonResult)
startOffset = detailResult['Offset']
duration = detailResult['Duration']
if duration >= 0:
endOffset = duration + startOffset
else:
endOffset = 0
print("Detected language = " + detectedSrcLang + ", startOffset = " + str(startOffset) + " nanoseconds, endOffset = " + str(endOffset) + " nanoseconds, Duration = " + str(duration) + " nanoseconds.")
global language_detected
language_detected = True
# connect callback to the synthesis event
recognizer.synthesizing.connect(synthesis_callback)
# start translation
recognizer.start_continuous_recognition()
while not done:
time.sleep(.5)
recognizer.stop_continuous_recognition()