From 4d5c1ac56bfde0532f7500a6d4a2a245fefa2286 Mon Sep 17 00:00:00 2001 From: Ryan Hurey Date: Wed, 16 Oct 2024 10:53:29 -0700 Subject: [PATCH] Merge samples for 1.41.1 updates (#2623) * Samples updates for 1.41.1 * Update SDK version to 1.41.1 * Update main.json hashes * Add logging for failure case * Update file paths * Revert infra files * JS is .0 not .1 --------- Co-authored-by: Yulin Li --- .github/workflows/ingestion_client.yaml | 9 ++++++++- .../cpp/linux/from-microphone/README.md | 7 +------ .../cpp/linux/from-microphone/helloworld.cpp | 2 +- quickstart/cpp/linux/text-to-speech/README.md | 7 +------ .../from-file/helloworld/helloworld.cpp | 2 +- .../from-file/helloworld/helloworld.vcxproj | 4 ++-- .../from-file/helloworld/packages.config | 2 +- .../from-microphone/helloworld/helloworld.cpp | 2 +- .../helloworld/helloworld.vcxproj | 4 ++-- .../helloworld/packages.config | 2 +- .../helloworld/helloworld.cpp | 2 +- .../helloworld/helloworld.vcxproj | 4 ++-- .../helloworld/packages.config | 2 +- .../helloworld/helloworld.vcxproj | 4 ++-- .../helloworld/packages.config | 2 +- .../helloworld/helloworld.vcxproj | 4 ++-- .../helloworld/packages.config | 2 +- .../helloworld/helloworld.vcxproj | 4 ++-- .../text-to-speech/helloworld/packages.config | 2 +- .../helloworld/helloworld.cpp | 2 +- .../helloworld/helloworld.vcxproj | 4 ++-- .../helloworld/packages.config | 2 +- .../helloworld/helloworld.csproj | 2 +- .../from-file/helloworld/helloworld.csproj | 2 +- .../from-file/helloworld/packages.config | 2 +- .../from-microphone/helloworld/Program.cs | 2 +- .../helloworld/helloworld.csproj | 2 +- .../helloworld/packages.config | 2 +- .../intent-recognition/helloworld/Program.cs | 2 +- .../helloworld/helloworld.csproj | 2 +- .../helloworld/packages.config | 2 +- .../helloworld/helloworld.csproj | 2 +- .../helloworld/helloworld.csproj | 2 +- .../helloworld/packages.config | 2 +- .../helloworld/helloworld.csproj | 2 +- .../helloworld/packages.config | 2 +- .../helloworld/helloworld.csproj | 2 +- .../text-to-speech/helloworld/packages.config | 2 +- .../helloworld/helloworld.csproj | 2 +- .../helloworld/packages.config | 2 +- .../dotnetcore/from-microphone/README.md | 7 +------ .../from-microphone/helloworld/Program.cs | 2 +- .../helloworld/helloworld.csproj | 2 +- .../dotnetcore/text-to-speech/README.md | 7 +------ .../helloworld/helloworld.csproj | 2 +- .../translate-speech-to-text/README.md | 7 +------ .../helloworld/helloworld.csproj | 2 +- .../Assets/Scripts/HelloWorld.cs | 2 +- .../csharp/uwp/from-microphone/README.md | 2 +- .../helloworld/MainPage.xaml.cs | 2 +- .../helloworld/helloworld.csproj | 2 +- .../helloworld/helloworld.csproj | 2 +- .../helloworld/helloworld.csproj | 2 +- .../uwp/translate-speech-to-text/README.md | 2 +- .../helloworld/helloworld.csproj | 2 +- .../uwp/virtual-assistant/helloworld.csproj | 2 +- .../android/from-microphone/app/build.gradle | 2 +- .../intent-recognition/app/build.gradle | 2 +- .../app/build.gradle | 2 +- .../keyword-recognizer/app/build.gradle | 2 +- .../android/text-to-speech/app/build.gradle | 2 +- .../jre/conversation-transcription/README.md | 7 +------ .../jre/conversation-transcription/pom.xml | 2 +- quickstart/java/jre/from-microphone/README.md | 7 +------ quickstart/java/jre/from-microphone/pom.xml | 2 +- .../java/jre/intent-recognition/README.md | 7 +------ .../java/jre/intent-recognition/pom.xml | 2 +- .../java/jre/meeting-transcription/README.md | 7 +------ .../java/jre/meeting-transcription/pom.xml | 2 +- .../java/jre/speaker-recognition/README.md | 7 +------ .../java/jre/speaker-recognition/pom.xml | 2 +- quickstart/java/jre/text-to-speech/README.md | 7 +------ quickstart/java/jre/text-to-speech/pom.xml | 2 +- .../jre/translate-speech-to-text/README.md | 7 +------ .../java/jre/translate-speech-to-text/pom.xml | 2 +- .../java/jre/virtual-assistant/README.md | 7 +------ quickstart/java/jre/virtual-assistant/pom.xml | 2 +- .../conversation-transcription/package.json | 2 +- .../javascript/node/from-file/package.json | 2 +- .../node/meeting-transcription/package.json | 2 +- .../identification/package.json | 2 +- .../verification/package.json | 2 +- .../node/text-to-speech/package.json | 2 +- .../macos/from-microphone/helloworld/Podfile | 2 +- .../helloworld/helloworld/AppDelegate.m | 2 +- .../macos/text-to-speech/helloworld/Podfile | 2 +- quickstart/python/from-microphone/README.md | 7 +------ .../python/from-microphone/quickstart.ipynb | 2 +- .../python/from-microphone/quickstart.py | 2 +- .../python/intent-recognition/README.md | 7 +------ .../intent-recognition/quickstart.ipynb | 2 +- .../python/intent-recognition/quickstart.py | 2 +- quickstart/python/text-to-speech/README.md | 7 +------ .../embedded-speech/samples/packages.config | 10 +++++----- .../embedded-speech/samples/samples.vcxproj | 20 +++++++++---------- .../linux/compressed-audio-input/README.md | 11 ++++------ .../compressed-audio-input.cpp | 2 +- .../samples/intent_recognition_samples.cpp | 6 +++--- .../windows/console/samples/packages.config | 4 ++-- .../windows/console/samples/samples.vcxproj | 8 ++++---- .../samples/speech_recognition_samples.cpp | 14 ++++++------- .../standalone_language_detection_samples.cpp | 4 ++-- .../console/samples/translation_samples.cpp | 4 ++-- .../console/samples/packages.config | 4 ++-- .../console/samples/samples.csproj | 6 +++--- .../speechtotext-naudio/packages.config | 2 +- .../speechtotext-naudio.csproj | 8 ++++---- samples/csharp/dotnetcore/console/README.md | 7 +------ .../dotnetcore/console/samples/samples.csproj | 6 +++--- .../embedded-speech/samples/samples.csproj | 10 +++++----- .../embedded-speech/embedded-speech.csproj | 10 +++++----- .../speech-to-text/MainPage.xaml.cs | 2 +- .../speech-to-text/speech-to-text.csproj | 2 +- .../console/intent_recognition_samples.cs | 6 +++--- .../console/speech_recognition_samples.cs | 10 +++++----- ...ch_recognition_with_language_id_samples.cs | 2 +- .../console/TtsTextStreamSample.csproj | 2 +- .../speechtotext-uwp/MainPage.xaml.cs | 2 +- .../speechtotext-uwp/speechtotext-uwp.csproj | 2 +- .../texttospeech-uwp/texttospeech-uwp.csproj | 2 +- .../VirtualAssistantPreview.csproj | 2 +- samples/csharp/web/avatar/Avatar.csproj | 2 +- .../AppInsightsServiceCollectionExtensions.cs | 2 +- .../android/SpeechSynthesis/app/build.gradle | 2 +- .../samples/speechsynthesis/MainActivity.java | 4 ++-- samples/java/android/avatar/app/build.gradle | 2 +- .../android/compressed-input/app/build.gradle | 2 +- .../java/android/embedded-speech/README.md | 2 +- .../android/embedded-speech/app/build.gradle | 2 +- samples/java/android/sdkdemo/app/build.gradle | 2 +- samples/java/jre/console/README.md | 7 +------ samples/java/jre/console/pom.xml | 2 +- .../console/IntentRecognitionSamples.java | 2 +- samples/java/jre/embedded-speech/pom.xml | 2 +- samples/js/browser/package.json | 2 +- samples/js/node/package.json | 2 +- .../android/continuous-reco/app/build.gradle | 2 +- .../tts-pause-example/app/build.gradle | 2 +- .../speech-samples.xcodeproj/project.pbxproj | 2 +- .../helloworld/Podfile | 2 +- samples/python/console/.flake8 | 2 +- samples/python/console/README.md | 7 +------ samples/python/console/chatting/README.md | 2 +- .../console/chatting/chatting_sample.py | 10 +++++----- samples/python/console/intent_sample.py | 6 +++--- .../speech_language_detection_sample.py | 4 ++-- samples/python/console/speech_sample.py | 12 +++++------ samples/python/console/translation_sample.py | 4 ++-- .../helloworld/Podfile | 2 +- .../captioning/captioning/captioning.vcxproj | 4 ++-- .../captioning/captioning/packages.config | 2 +- .../captioning/captioning/captioning.csproj | 2 +- scenarios/java/jre/console/captioning/pom.xml | 2 +- 153 files changed, 234 insertions(+), 325 deletions(-) diff --git a/.github/workflows/ingestion_client.yaml b/.github/workflows/ingestion_client.yaml index f7ad8c3c5..dc7160ecd 100644 --- a/.github/workflows/ingestion_client.yaml +++ b/.github/workflows/ingestion_client.yaml @@ -35,8 +35,15 @@ jobs: - name: Validate ARM Template run: | - if ! cmp -s ./samples/ingestion/ingestion-client/infra/main.json ./samples/ingestion/ingestion-client/infra/generated_main.json; then + if ! cmp ./samples/ingestion/ingestion-client/infra/main.json ./samples/ingestion/ingestion-client/infra/generated_main.json; then echo "Generated ARM template does not match the existing main.json. Please update main.json accordingly." >&2 + echo "====================main.json"====================" + cat ./samples/ingestion/ingestion-client/infra/main.json + echo "==================================================" + echo + echo "===============generated_main.json"===============" + cat ./samples/ingestion/ingestion-client/infra/generated_main.json + echo "==================================================" exit 1 fi diff --git a/quickstart/cpp/linux/from-microphone/README.md b/quickstart/cpp/linux/from-microphone/README.md index fcb44b479..0839d184f 100644 --- a/quickstart/cpp/linux/from-microphone/README.md +++ b/quickstart/cpp/linux/from-microphone/README.md @@ -10,12 +10,7 @@ See the [accompanying article](https://docs.microsoft.com/azure/cognitive-servic * A subscription key for the Speech service. See [Try the speech service for free](https://docs.microsoft.com/azure/cognitive-services/speech-service/get-started). * A Linux PC with a working microphone. -* On Ubuntu or Debian, install these packages to build and run this sample: - - ```sh - sudo apt-get update - sudo apt-get install build-essential libssl-dev libasound2 wget - ``` +* See the [Linux platform requirements](https://learn.microsoft.com/azure/ai-services/speech-service/quickstarts/setup-platform?tabs=linux&pivots=programming-language-cpp#platform-requirements) for installing the required dependencies. ## Build the sample diff --git a/quickstart/cpp/linux/from-microphone/helloworld.cpp b/quickstart/cpp/linux/from-microphone/helloworld.cpp index cd4956f58..fdd7cc4b6 100644 --- a/quickstart/cpp/linux/from-microphone/helloworld.cpp +++ b/quickstart/cpp/linux/from-microphone/helloworld.cpp @@ -20,7 +20,7 @@ void recognizeSpeech() { cout << "Say something...\n"; // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. diff --git a/quickstart/cpp/linux/text-to-speech/README.md b/quickstart/cpp/linux/text-to-speech/README.md index 62cd4f1ac..206459cd2 100644 --- a/quickstart/cpp/linux/text-to-speech/README.md +++ b/quickstart/cpp/linux/text-to-speech/README.md @@ -10,12 +10,7 @@ See the [accompanying article](https://docs.microsoft.com/azure/cognitive-servic * A subscription key for the Speech service. See [Try the speech service for free](https://docs.microsoft.com/azure/cognitive-services/speech-service/get-started). * A Linux PC with a working speaker or headset. -* On Ubuntu or Debian, install these packages to build and run this sample: - - ```sh - sudo apt-get update - sudo apt-get install build-essential libssl-dev libasound2 wget - ``` +* See the [Linux platform requirements](https://learn.microsoft.com/azure/ai-services/speech-service/quickstarts/setup-platform?tabs=linux&pivots=programming-language-cpp#platform-requirements) for installing the required dependencies. ## Build the sample diff --git a/quickstart/cpp/windows/from-file/helloworld/helloworld.cpp b/quickstart/cpp/windows/from-file/helloworld/helloworld.cpp index 0735406df..c58bbb56e 100644 --- a/quickstart/cpp/windows/from-file/helloworld/helloworld.cpp +++ b/quickstart/cpp/windows/from-file/helloworld/helloworld.cpp @@ -24,7 +24,7 @@ void recognizeSpeechFromWavFile() auto recognizer = SpeechRecognizer::FromConfig(config, audioInput); // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. diff --git a/quickstart/cpp/windows/from-file/helloworld/helloworld.vcxproj b/quickstart/cpp/windows/from-file/helloworld/helloworld.vcxproj index 7574b1107..ded6ab68c 100644 --- a/quickstart/cpp/windows/from-file/helloworld/helloworld.vcxproj +++ b/quickstart/cpp/windows/from-file/helloworld/helloworld.vcxproj @@ -170,12 +170,12 @@ - + This project references NuGet package(s) that are missing on this computer. Use NuGet Package Restore to download them. For more information, see http://go.microsoft.com/fwlink/?LinkID=322105. The missing file is {0}. - + \ No newline at end of file diff --git a/quickstart/cpp/windows/from-file/helloworld/packages.config b/quickstart/cpp/windows/from-file/helloworld/packages.config index b2fd9e72f..e51eea91b 100644 --- a/quickstart/cpp/windows/from-file/helloworld/packages.config +++ b/quickstart/cpp/windows/from-file/helloworld/packages.config @@ -1,4 +1,4 @@ - + \ No newline at end of file diff --git a/quickstart/cpp/windows/from-microphone/helloworld/helloworld.cpp b/quickstart/cpp/windows/from-microphone/helloworld/helloworld.cpp index f9ebad2fb..60328376c 100644 --- a/quickstart/cpp/windows/from-microphone/helloworld/helloworld.cpp +++ b/quickstart/cpp/windows/from-microphone/helloworld/helloworld.cpp @@ -22,7 +22,7 @@ void recognizeSpeech() cout << "Say something...\n"; // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. diff --git a/quickstart/cpp/windows/from-microphone/helloworld/helloworld.vcxproj b/quickstart/cpp/windows/from-microphone/helloworld/helloworld.vcxproj index 3d0e8a9aa..12627cda7 100644 --- a/quickstart/cpp/windows/from-microphone/helloworld/helloworld.vcxproj +++ b/quickstart/cpp/windows/from-microphone/helloworld/helloworld.vcxproj @@ -166,12 +166,12 @@ - + This project references NuGet package(s) that are missing on this computer. Use NuGet Package Restore to download them. For more information, see http://go.microsoft.com/fwlink/?LinkID=322105. The missing file is {0}. - + \ No newline at end of file diff --git a/quickstart/cpp/windows/from-microphone/helloworld/packages.config b/quickstart/cpp/windows/from-microphone/helloworld/packages.config index b2fd9e72f..e51eea91b 100644 --- a/quickstart/cpp/windows/from-microphone/helloworld/packages.config +++ b/quickstart/cpp/windows/from-microphone/helloworld/packages.config @@ -1,4 +1,4 @@ - + \ No newline at end of file diff --git a/quickstart/cpp/windows/intent-recognition/helloworld/helloworld.cpp b/quickstart/cpp/windows/intent-recognition/helloworld/helloworld.cpp index cf698c207..f2bf178be 100644 --- a/quickstart/cpp/windows/intent-recognition/helloworld/helloworld.cpp +++ b/quickstart/cpp/windows/intent-recognition/helloworld/helloworld.cpp @@ -49,7 +49,7 @@ void recognizeIntent() cout << "Say something...\n"; // Starts intent recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. diff --git a/quickstart/cpp/windows/intent-recognition/helloworld/helloworld.vcxproj b/quickstart/cpp/windows/intent-recognition/helloworld/helloworld.vcxproj index 3d0e8a9aa..12627cda7 100644 --- a/quickstart/cpp/windows/intent-recognition/helloworld/helloworld.vcxproj +++ b/quickstart/cpp/windows/intent-recognition/helloworld/helloworld.vcxproj @@ -166,12 +166,12 @@ - + This project references NuGet package(s) that are missing on this computer. Use NuGet Package Restore to download them. For more information, see http://go.microsoft.com/fwlink/?LinkID=322105. The missing file is {0}. - + \ No newline at end of file diff --git a/quickstart/cpp/windows/intent-recognition/helloworld/packages.config b/quickstart/cpp/windows/intent-recognition/helloworld/packages.config index b2fd9e72f..e51eea91b 100644 --- a/quickstart/cpp/windows/intent-recognition/helloworld/packages.config +++ b/quickstart/cpp/windows/intent-recognition/helloworld/packages.config @@ -1,4 +1,4 @@ - + \ No newline at end of file diff --git a/quickstart/cpp/windows/multi-device-conversation/helloworld/helloworld.vcxproj b/quickstart/cpp/windows/multi-device-conversation/helloworld/helloworld.vcxproj index b6320d8df..f300d154d 100644 --- a/quickstart/cpp/windows/multi-device-conversation/helloworld/helloworld.vcxproj +++ b/quickstart/cpp/windows/multi-device-conversation/helloworld/helloworld.vcxproj @@ -158,12 +158,12 @@ - + This project references NuGet package(s) that are missing on this computer. Use NuGet Package Restore to download them. For more information, see http://go.microsoft.com/fwlink/?LinkID=322105. The missing file is {0}. - + \ No newline at end of file diff --git a/quickstart/cpp/windows/multi-device-conversation/helloworld/packages.config b/quickstart/cpp/windows/multi-device-conversation/helloworld/packages.config index b2fd9e72f..e51eea91b 100644 --- a/quickstart/cpp/windows/multi-device-conversation/helloworld/packages.config +++ b/quickstart/cpp/windows/multi-device-conversation/helloworld/packages.config @@ -1,4 +1,4 @@ - + \ No newline at end of file diff --git a/quickstart/cpp/windows/speaker-recognition/helloworld/helloworld.vcxproj b/quickstart/cpp/windows/speaker-recognition/helloworld/helloworld.vcxproj index c3921b397..6abd5d485 100644 --- a/quickstart/cpp/windows/speaker-recognition/helloworld/helloworld.vcxproj +++ b/quickstart/cpp/windows/speaker-recognition/helloworld/helloworld.vcxproj @@ -175,12 +175,12 @@ - + This project references NuGet package(s) that are missing on this computer. Use NuGet Package Restore to download them. For more information, see http://go.microsoft.com/fwlink/?LinkID=322105. The missing file is {0}. - + \ No newline at end of file diff --git a/quickstart/cpp/windows/speaker-recognition/helloworld/packages.config b/quickstart/cpp/windows/speaker-recognition/helloworld/packages.config index b2fd9e72f..e51eea91b 100644 --- a/quickstart/cpp/windows/speaker-recognition/helloworld/packages.config +++ b/quickstart/cpp/windows/speaker-recognition/helloworld/packages.config @@ -1,4 +1,4 @@ - + \ No newline at end of file diff --git a/quickstart/cpp/windows/text-to-speech/helloworld/helloworld.vcxproj b/quickstart/cpp/windows/text-to-speech/helloworld/helloworld.vcxproj index 3d0e8a9aa..12627cda7 100644 --- a/quickstart/cpp/windows/text-to-speech/helloworld/helloworld.vcxproj +++ b/quickstart/cpp/windows/text-to-speech/helloworld/helloworld.vcxproj @@ -166,12 +166,12 @@ - + This project references NuGet package(s) that are missing on this computer. Use NuGet Package Restore to download them. For more information, see http://go.microsoft.com/fwlink/?LinkID=322105. The missing file is {0}. - + \ No newline at end of file diff --git a/quickstart/cpp/windows/text-to-speech/helloworld/packages.config b/quickstart/cpp/windows/text-to-speech/helloworld/packages.config index b2fd9e72f..e51eea91b 100644 --- a/quickstart/cpp/windows/text-to-speech/helloworld/packages.config +++ b/quickstart/cpp/windows/text-to-speech/helloworld/packages.config @@ -1,4 +1,4 @@ - + \ No newline at end of file diff --git a/quickstart/cpp/windows/translate-speech-to-text/helloworld/helloworld.cpp b/quickstart/cpp/windows/translate-speech-to-text/helloworld/helloworld.cpp index 913f1619a..819614a06 100644 --- a/quickstart/cpp/windows/translate-speech-to-text/helloworld/helloworld.cpp +++ b/quickstart/cpp/windows/translate-speech-to-text/helloworld/helloworld.cpp @@ -32,7 +32,7 @@ void TranslationWithMicrophone() 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // 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. diff --git a/quickstart/cpp/windows/translate-speech-to-text/helloworld/helloworld.vcxproj b/quickstart/cpp/windows/translate-speech-to-text/helloworld/helloworld.vcxproj index 49b6502e4..4fab00933 100644 --- a/quickstart/cpp/windows/translate-speech-to-text/helloworld/helloworld.vcxproj +++ b/quickstart/cpp/windows/translate-speech-to-text/helloworld/helloworld.vcxproj @@ -167,12 +167,12 @@ - + This project references NuGet package(s) that are missing on this computer. Use NuGet Package Restore to download them. For more information, see http://go.microsoft.com/fwlink/?LinkID=322105. The missing file is {0}. - + \ No newline at end of file diff --git a/quickstart/cpp/windows/translate-speech-to-text/helloworld/packages.config b/quickstart/cpp/windows/translate-speech-to-text/helloworld/packages.config index 3edf4f372..3a0bf1d48 100644 --- a/quickstart/cpp/windows/translate-speech-to-text/helloworld/packages.config +++ b/quickstart/cpp/windows/translate-speech-to-text/helloworld/packages.config @@ -1,4 +1,4 @@ - + diff --git a/quickstart/csharp/dotnet/conversation-transcription/helloworld/helloworld.csproj b/quickstart/csharp/dotnet/conversation-transcription/helloworld/helloworld.csproj index aff3194c9..1585cee85 100644 --- a/quickstart/csharp/dotnet/conversation-transcription/helloworld/helloworld.csproj +++ b/quickstart/csharp/dotnet/conversation-transcription/helloworld/helloworld.csproj @@ -102,7 +102,7 @@ - 1.40.0 + 1.41.1 13.0.1 diff --git a/quickstart/csharp/dotnet/from-file/helloworld/helloworld.csproj b/quickstart/csharp/dotnet/from-file/helloworld/helloworld.csproj index 97954495d..5c729463e 100644 --- a/quickstart/csharp/dotnet/from-file/helloworld/helloworld.csproj +++ b/quickstart/csharp/dotnet/from-file/helloworld/helloworld.csproj @@ -95,7 +95,7 @@ - 1.40.0 + 1.41.1 diff --git a/quickstart/csharp/dotnet/from-file/helloworld/packages.config b/quickstart/csharp/dotnet/from-file/helloworld/packages.config index 9c68fa2c0..484b29cc7 100644 --- a/quickstart/csharp/dotnet/from-file/helloworld/packages.config +++ b/quickstart/csharp/dotnet/from-file/helloworld/packages.config @@ -1,4 +1,4 @@ - + \ No newline at end of file diff --git a/quickstart/csharp/dotnet/from-microphone/helloworld/Program.cs b/quickstart/csharp/dotnet/from-microphone/helloworld/Program.cs index 3ed32a266..833c89dfd 100644 --- a/quickstart/csharp/dotnet/from-microphone/helloworld/Program.cs +++ b/quickstart/csharp/dotnet/from-microphone/helloworld/Program.cs @@ -22,7 +22,7 @@ public static async Task RecognizeSpeechAsync() Console.WriteLine("Say something..."); // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. diff --git a/quickstart/csharp/dotnet/from-microphone/helloworld/helloworld.csproj b/quickstart/csharp/dotnet/from-microphone/helloworld/helloworld.csproj index 97954495d..5c729463e 100644 --- a/quickstart/csharp/dotnet/from-microphone/helloworld/helloworld.csproj +++ b/quickstart/csharp/dotnet/from-microphone/helloworld/helloworld.csproj @@ -95,7 +95,7 @@ - 1.40.0 + 1.41.1 diff --git a/quickstart/csharp/dotnet/from-microphone/helloworld/packages.config b/quickstart/csharp/dotnet/from-microphone/helloworld/packages.config index 9c68fa2c0..484b29cc7 100644 --- a/quickstart/csharp/dotnet/from-microphone/helloworld/packages.config +++ b/quickstart/csharp/dotnet/from-microphone/helloworld/packages.config @@ -1,4 +1,4 @@ - + \ No newline at end of file diff --git a/quickstart/csharp/dotnet/intent-recognition/helloworld/Program.cs b/quickstart/csharp/dotnet/intent-recognition/helloworld/Program.cs index 4ed4a0de8..040300919 100644 --- a/quickstart/csharp/dotnet/intent-recognition/helloworld/Program.cs +++ b/quickstart/csharp/dotnet/intent-recognition/helloworld/Program.cs @@ -52,7 +52,7 @@ public static async Task RecognizeIntentAsync() Console.WriteLine("Say something..."); // Starts intent recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. diff --git a/quickstart/csharp/dotnet/intent-recognition/helloworld/helloworld.csproj b/quickstart/csharp/dotnet/intent-recognition/helloworld/helloworld.csproj index dab185482..74f48ca8f 100644 --- a/quickstart/csharp/dotnet/intent-recognition/helloworld/helloworld.csproj +++ b/quickstart/csharp/dotnet/intent-recognition/helloworld/helloworld.csproj @@ -97,7 +97,7 @@ - 1.40.0 + 1.41.1 diff --git a/quickstart/csharp/dotnet/intent-recognition/helloworld/packages.config b/quickstart/csharp/dotnet/intent-recognition/helloworld/packages.config index 9c68fa2c0..484b29cc7 100644 --- a/quickstart/csharp/dotnet/intent-recognition/helloworld/packages.config +++ b/quickstart/csharp/dotnet/intent-recognition/helloworld/packages.config @@ -1,4 +1,4 @@ - + \ No newline at end of file diff --git a/quickstart/csharp/dotnet/meeting-transcription/helloworld/helloworld.csproj b/quickstart/csharp/dotnet/meeting-transcription/helloworld/helloworld.csproj index 48d09c732..8318c3c12 100644 --- a/quickstart/csharp/dotnet/meeting-transcription/helloworld/helloworld.csproj +++ b/quickstart/csharp/dotnet/meeting-transcription/helloworld/helloworld.csproj @@ -110,7 +110,7 @@ - 1.40.0 + 1.41.1 13.0.1 diff --git a/quickstart/csharp/dotnet/multi-device-conversation/helloworld/helloworld.csproj b/quickstart/csharp/dotnet/multi-device-conversation/helloworld/helloworld.csproj index 3797d319a..8452918b2 100644 --- a/quickstart/csharp/dotnet/multi-device-conversation/helloworld/helloworld.csproj +++ b/quickstart/csharp/dotnet/multi-device-conversation/helloworld/helloworld.csproj @@ -74,7 +74,7 @@ - 1.40.0 + 1.41.1 diff --git a/quickstart/csharp/dotnet/multi-device-conversation/helloworld/packages.config b/quickstart/csharp/dotnet/multi-device-conversation/helloworld/packages.config index f6b884fdc..ad3a8933b 100644 --- a/quickstart/csharp/dotnet/multi-device-conversation/helloworld/packages.config +++ b/quickstart/csharp/dotnet/multi-device-conversation/helloworld/packages.config @@ -1,4 +1,4 @@ - + \ No newline at end of file diff --git a/quickstart/csharp/dotnet/speaker-recognition/helloworld/helloworld.csproj b/quickstart/csharp/dotnet/speaker-recognition/helloworld/helloworld.csproj index 87aeac31b..f6d133716 100644 --- a/quickstart/csharp/dotnet/speaker-recognition/helloworld/helloworld.csproj +++ b/quickstart/csharp/dotnet/speaker-recognition/helloworld/helloworld.csproj @@ -105,7 +105,7 @@ - 1.40.0 + 1.41.1 diff --git a/quickstart/csharp/dotnet/speaker-recognition/helloworld/packages.config b/quickstart/csharp/dotnet/speaker-recognition/helloworld/packages.config index 9c68fa2c0..484b29cc7 100644 --- a/quickstart/csharp/dotnet/speaker-recognition/helloworld/packages.config +++ b/quickstart/csharp/dotnet/speaker-recognition/helloworld/packages.config @@ -1,4 +1,4 @@ - + \ No newline at end of file diff --git a/quickstart/csharp/dotnet/text-to-speech/helloworld/helloworld.csproj b/quickstart/csharp/dotnet/text-to-speech/helloworld/helloworld.csproj index 8bae726ed..36b9df1d8 100644 --- a/quickstart/csharp/dotnet/text-to-speech/helloworld/helloworld.csproj +++ b/quickstart/csharp/dotnet/text-to-speech/helloworld/helloworld.csproj @@ -94,7 +94,7 @@ - 1.40.0 + 1.41.1 diff --git a/quickstart/csharp/dotnet/text-to-speech/helloworld/packages.config b/quickstart/csharp/dotnet/text-to-speech/helloworld/packages.config index 9c68fa2c0..484b29cc7 100644 --- a/quickstart/csharp/dotnet/text-to-speech/helloworld/packages.config +++ b/quickstart/csharp/dotnet/text-to-speech/helloworld/packages.config @@ -1,4 +1,4 @@ - + \ No newline at end of file diff --git a/quickstart/csharp/dotnet/translate-speech-to-text/helloworld/helloworld.csproj b/quickstart/csharp/dotnet/translate-speech-to-text/helloworld/helloworld.csproj index 8761ceb1a..b46077c53 100644 --- a/quickstart/csharp/dotnet/translate-speech-to-text/helloworld/helloworld.csproj +++ b/quickstart/csharp/dotnet/translate-speech-to-text/helloworld/helloworld.csproj @@ -76,7 +76,7 @@ - 1.40.0 + 1.41.1 diff --git a/quickstart/csharp/dotnet/translate-speech-to-text/helloworld/packages.config b/quickstart/csharp/dotnet/translate-speech-to-text/helloworld/packages.config index d6b210000..52a742c5c 100644 --- a/quickstart/csharp/dotnet/translate-speech-to-text/helloworld/packages.config +++ b/quickstart/csharp/dotnet/translate-speech-to-text/helloworld/packages.config @@ -1,4 +1,4 @@ - + diff --git a/quickstart/csharp/dotnetcore/from-microphone/README.md b/quickstart/csharp/dotnetcore/from-microphone/README.md index 5f05d22e0..9395af5b4 100644 --- a/quickstart/csharp/dotnetcore/from-microphone/README.md +++ b/quickstart/csharp/dotnetcore/from-microphone/README.md @@ -17,12 +17,7 @@ This sample demonstrates how to recognize speech with C# under .NET 6.0 (Windows * On Windows, macOS, or Linux: * [.NET 6.0](https://dotnet.microsoft.com/download/dotnet/6.0) * On Windows you also need the [Microsoft Visual C++ Redistributable for Visual Studio 2015, 2017 and 2019](https://support.microsoft.com/help/2977003/the-latest-supported-visual-c-downloads) for your platform. -* On Ubuntu or Debian, run the following commands for the installation of required packages: - - ```sh - sudo apt-get update - sudo apt-get install libssl-dev libasound2 - ``` +* On Linux, see the [Linux platform requirements](https://learn.microsoft.com/azure/ai-services/speech-service/quickstarts/setup-platform?tabs=linux&pivots=programming-language-csharp#platform-requirements) for installing the required dependencies. ## Build the sample diff --git a/quickstart/csharp/dotnetcore/from-microphone/helloworld/Program.cs b/quickstart/csharp/dotnetcore/from-microphone/helloworld/Program.cs index d7e9824e2..403f201a4 100644 --- a/quickstart/csharp/dotnetcore/from-microphone/helloworld/Program.cs +++ b/quickstart/csharp/dotnetcore/from-microphone/helloworld/Program.cs @@ -24,7 +24,7 @@ public static async Task RecognizeSpeechAsync() Console.WriteLine("Say something..."); // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. diff --git a/quickstart/csharp/dotnetcore/from-microphone/helloworld/helloworld.csproj b/quickstart/csharp/dotnetcore/from-microphone/helloworld/helloworld.csproj index 058e48805..b5bef2de2 100644 --- a/quickstart/csharp/dotnetcore/from-microphone/helloworld/helloworld.csproj +++ b/quickstart/csharp/dotnetcore/from-microphone/helloworld/helloworld.csproj @@ -7,7 +7,7 @@ - + diff --git a/quickstart/csharp/dotnetcore/text-to-speech/README.md b/quickstart/csharp/dotnetcore/text-to-speech/README.md index 929ec7b89..41eb5dd9a 100644 --- a/quickstart/csharp/dotnetcore/text-to-speech/README.md +++ b/quickstart/csharp/dotnetcore/text-to-speech/README.md @@ -18,12 +18,7 @@ See the [accompanying article](https://docs.microsoft.com/azure/cognitive-servic * On Windows or Linux: * [.NET 6.0](https://dotnet.microsoft.com/download/dotnet/6.0) * On Windows you also need the [Microsoft Visual C++ Redistributable for Visual Studio 2015, 2017 and 2019](https://support.microsoft.com/help/2977003/the-latest-supported-visual-c-downloads) for your platform. -* On Ubuntu or Debian, run the following commands for the installation of required packages: - - ```sh - sudo apt-get update - sudo apt-get install libssl-dev libasound2 - ``` +* On Linux, see the [Linux platform requirements](https://learn.microsoft.com/azure/ai-services/speech-service/quickstarts/setup-platform?tabs=linux&pivots=programming-language-csharp#platform-requirements) for installing the required dependencies. ## Build the sample diff --git a/quickstart/csharp/dotnetcore/text-to-speech/helloworld/helloworld.csproj b/quickstart/csharp/dotnetcore/text-to-speech/helloworld/helloworld.csproj index 058e48805..b5bef2de2 100644 --- a/quickstart/csharp/dotnetcore/text-to-speech/helloworld/helloworld.csproj +++ b/quickstart/csharp/dotnetcore/text-to-speech/helloworld/helloworld.csproj @@ -7,7 +7,7 @@ - + diff --git a/quickstart/csharp/dotnetcore/translate-speech-to-text/README.md b/quickstart/csharp/dotnetcore/translate-speech-to-text/README.md index 7860f3996..19e26984b 100644 --- a/quickstart/csharp/dotnetcore/translate-speech-to-text/README.md +++ b/quickstart/csharp/dotnetcore/translate-speech-to-text/README.md @@ -18,12 +18,7 @@ See the [accompanying article](https://docs.microsoft.com/azure/cognitive-servic * On Windows or Linux: * [.NET 6.0](https://dotnet.microsoft.com/download/dotnet/6.0) * On Windows you also need the [Microsoft Visual C++ Redistributable for Visual Studio 2015, 2017 and 2019](https://support.microsoft.com/help/2977003/the-latest-supported-visual-c-downloads) for your platform. -* On Ubuntu or Debian, run the following commands for the installation of required packages: - - ```sh - sudo apt-get update - sudo apt-get install libssl-dev libasound2 - ``` +* On Linux, see the [Linux platform requirements](https://learn.microsoft.com/azure/ai-services/speech-service/quickstarts/setup-platform?tabs=linux&pivots=programming-language-csharp#platform-requirements) for installing the required dependencies. ## Build the sample diff --git a/quickstart/csharp/dotnetcore/translate-speech-to-text/helloworld/helloworld.csproj b/quickstart/csharp/dotnetcore/translate-speech-to-text/helloworld/helloworld.csproj index 058e48805..b5bef2de2 100644 --- a/quickstart/csharp/dotnetcore/translate-speech-to-text/helloworld/helloworld.csproj +++ b/quickstart/csharp/dotnetcore/translate-speech-to-text/helloworld/helloworld.csproj @@ -7,7 +7,7 @@ - + diff --git a/quickstart/csharp/unity/from-microphone/Assets/Scripts/HelloWorld.cs b/quickstart/csharp/unity/from-microphone/Assets/Scripts/HelloWorld.cs index 188afdd18..940e0016a 100644 --- a/quickstart/csharp/unity/from-microphone/Assets/Scripts/HelloWorld.cs +++ b/quickstart/csharp/unity/from-microphone/Assets/Scripts/HelloWorld.cs @@ -47,7 +47,7 @@ public async void ButtonClick() } // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. diff --git a/quickstart/csharp/uwp/from-microphone/README.md b/quickstart/csharp/uwp/from-microphone/README.md index 816c3908b..092c5d2e9 100644 --- a/quickstart/csharp/uwp/from-microphone/README.md +++ b/quickstart/csharp/uwp/from-microphone/README.md @@ -32,7 +32,7 @@ See the [accompanying article](https://docs.microsoft.com/azure/cognitive-servic To debug the app and then run it, press F5 or use **Debug** \> **Start Debugging**. To run the app without debugging, press Ctrl+F5 or use **Debug** \> **Start Without Debugging**. -When you see the `Enable microphone` button, click it. Then select the `Speech recognition with microphone input` button and start speaking. The next (up to) 15 seconds of English speech will be sent to the Speech service and transcribed. +When you see the `Enable microphone` button, click it. Then select the `Speech recognition with microphone input` button and start speaking. The speech will be sent to the Speech service and transcribed. ## References diff --git a/quickstart/csharp/uwp/from-microphone/helloworld/MainPage.xaml.cs b/quickstart/csharp/uwp/from-microphone/helloworld/MainPage.xaml.cs index ebb565c6b..7a73f8c9c 100644 --- a/quickstart/csharp/uwp/from-microphone/helloworld/MainPage.xaml.cs +++ b/quickstart/csharp/uwp/from-microphone/helloworld/MainPage.xaml.cs @@ -65,7 +65,7 @@ private async void SpeechRecognitionFromMicrophone_ButtonClicked(object sender, { // // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. diff --git a/quickstart/csharp/uwp/from-microphone/helloworld/helloworld.csproj b/quickstart/csharp/uwp/from-microphone/helloworld/helloworld.csproj index 58e21afdd..1bddb2d6f 100644 --- a/quickstart/csharp/uwp/from-microphone/helloworld/helloworld.csproj +++ b/quickstart/csharp/uwp/from-microphone/helloworld/helloworld.csproj @@ -106,7 +106,7 @@ - 1.40.0 + 1.41.1 6.2.8 diff --git a/quickstart/csharp/uwp/keyword-recognizer/helloworld/helloworld.csproj b/quickstart/csharp/uwp/keyword-recognizer/helloworld/helloworld.csproj index b7507c297..5edefd4e9 100644 --- a/quickstart/csharp/uwp/keyword-recognizer/helloworld/helloworld.csproj +++ b/quickstart/csharp/uwp/keyword-recognizer/helloworld/helloworld.csproj @@ -154,7 +154,7 @@ - 1.40.0 + 1.41.1 6.2.9 diff --git a/quickstart/csharp/uwp/text-to-speech/helloworld/helloworld.csproj b/quickstart/csharp/uwp/text-to-speech/helloworld/helloworld.csproj index 5893e577d..752aa7978 100644 --- a/quickstart/csharp/uwp/text-to-speech/helloworld/helloworld.csproj +++ b/quickstart/csharp/uwp/text-to-speech/helloworld/helloworld.csproj @@ -106,7 +106,7 @@ - 1.40.0 + 1.41.1 6.2.8 diff --git a/quickstart/csharp/uwp/translate-speech-to-text/README.md b/quickstart/csharp/uwp/translate-speech-to-text/README.md index bcd1ea65f..771d0f1d4 100644 --- a/quickstart/csharp/uwp/translate-speech-to-text/README.md +++ b/quickstart/csharp/uwp/translate-speech-to-text/README.md @@ -31,7 +31,7 @@ See the [accompanying article](https://docs.microsoft.com/azure/cognitive-servic To debug the app and then run it, press F5 or use **Debug** \> **Start Debugging**. To run the app without debugging, press Ctrl+F5 or use **Debug** \> **Start Without Debugging**. -When you see the `Enable microphone` button, click it. Then select the `Translate speech from the microphone input` button and start speaking. The next (up to) 15 seconds of English speech will be sent to the Speech service and transcribed. +When you see the `Enable microphone` button, click it. Then select the `Translate speech from the microphone input` button and start speaking. The speech will be sent to the Speech service and transcribed. ## References diff --git a/quickstart/csharp/uwp/translate-speech-to-text/helloworld/helloworld.csproj b/quickstart/csharp/uwp/translate-speech-to-text/helloworld/helloworld.csproj index d753bffd4..e9deec321 100644 --- a/quickstart/csharp/uwp/translate-speech-to-text/helloworld/helloworld.csproj +++ b/quickstart/csharp/uwp/translate-speech-to-text/helloworld/helloworld.csproj @@ -106,7 +106,7 @@ - 1.40.0 + 1.41.1 6.2.8 diff --git a/quickstart/csharp/uwp/virtual-assistant/helloworld.csproj b/quickstart/csharp/uwp/virtual-assistant/helloworld.csproj index ebfdfa108..6765e7a2a 100644 --- a/quickstart/csharp/uwp/virtual-assistant/helloworld.csproj +++ b/quickstart/csharp/uwp/virtual-assistant/helloworld.csproj @@ -153,7 +153,7 @@ - 1.40.0 + 1.41.1 6.2.9 diff --git a/quickstart/java/android/from-microphone/app/build.gradle b/quickstart/java/android/from-microphone/app/build.gradle index 8a368cd0b..21cd202a7 100644 --- a/quickstart/java/android/from-microphone/app/build.gradle +++ b/quickstart/java/android/from-microphone/app/build.gradle @@ -25,7 +25,7 @@ dependencies { implementation fileTree(include: ['*.jar'], dir: 'libs') // Speech SDK - implementation 'com.microsoft.cognitiveservices.speech:client-sdk:1.40.0' + implementation 'com.microsoft.cognitiveservices.speech:client-sdk:1.41.1' implementation 'androidx.appcompat:appcompat:1.3.1' implementation 'androidx.constraintlayout:constraintlayout:2.1.0' diff --git a/quickstart/java/android/intent-recognition/app/build.gradle b/quickstart/java/android/intent-recognition/app/build.gradle index 8a368cd0b..21cd202a7 100644 --- a/quickstart/java/android/intent-recognition/app/build.gradle +++ b/quickstart/java/android/intent-recognition/app/build.gradle @@ -25,7 +25,7 @@ dependencies { implementation fileTree(include: ['*.jar'], dir: 'libs') // Speech SDK - implementation 'com.microsoft.cognitiveservices.speech:client-sdk:1.40.0' + implementation 'com.microsoft.cognitiveservices.speech:client-sdk:1.41.1' implementation 'androidx.appcompat:appcompat:1.3.1' implementation 'androidx.constraintlayout:constraintlayout:2.1.0' diff --git a/quickstart/java/android/keyword-recognizer-stream/app/build.gradle b/quickstart/java/android/keyword-recognizer-stream/app/build.gradle index 8a368cd0b..21cd202a7 100644 --- a/quickstart/java/android/keyword-recognizer-stream/app/build.gradle +++ b/quickstart/java/android/keyword-recognizer-stream/app/build.gradle @@ -25,7 +25,7 @@ dependencies { implementation fileTree(include: ['*.jar'], dir: 'libs') // Speech SDK - implementation 'com.microsoft.cognitiveservices.speech:client-sdk:1.40.0' + implementation 'com.microsoft.cognitiveservices.speech:client-sdk:1.41.1' implementation 'androidx.appcompat:appcompat:1.3.1' implementation 'androidx.constraintlayout:constraintlayout:2.1.0' diff --git a/quickstart/java/android/keyword-recognizer/app/build.gradle b/quickstart/java/android/keyword-recognizer/app/build.gradle index 8a368cd0b..21cd202a7 100644 --- a/quickstart/java/android/keyword-recognizer/app/build.gradle +++ b/quickstart/java/android/keyword-recognizer/app/build.gradle @@ -25,7 +25,7 @@ dependencies { implementation fileTree(include: ['*.jar'], dir: 'libs') // Speech SDK - implementation 'com.microsoft.cognitiveservices.speech:client-sdk:1.40.0' + implementation 'com.microsoft.cognitiveservices.speech:client-sdk:1.41.1' implementation 'androidx.appcompat:appcompat:1.3.1' implementation 'androidx.constraintlayout:constraintlayout:2.1.0' diff --git a/quickstart/java/android/text-to-speech/app/build.gradle b/quickstart/java/android/text-to-speech/app/build.gradle index 8a368cd0b..21cd202a7 100644 --- a/quickstart/java/android/text-to-speech/app/build.gradle +++ b/quickstart/java/android/text-to-speech/app/build.gradle @@ -25,7 +25,7 @@ dependencies { implementation fileTree(include: ['*.jar'], dir: 'libs') // Speech SDK - implementation 'com.microsoft.cognitiveservices.speech:client-sdk:1.40.0' + implementation 'com.microsoft.cognitiveservices.speech:client-sdk:1.41.1' implementation 'androidx.appcompat:appcompat:1.3.1' implementation 'androidx.constraintlayout:constraintlayout:2.1.0' diff --git a/quickstart/java/jre/conversation-transcription/README.md b/quickstart/java/jre/conversation-transcription/README.md index 5ce3f8081..1dae15b98 100644 --- a/quickstart/java/jre/conversation-transcription/README.md +++ b/quickstart/java/jre/conversation-transcription/README.md @@ -13,12 +13,7 @@ See the [accompanying article](https://docs.microsoft.com/azure/cognitive-servic * A PC (Windows x64 or a supported Linux distribution) or Mac (macOS 10.14 or later) capable to run Eclipse,[[1]](#footnote1) with a working microphone. * Java 11 JRE/JDK. * Version 4.8 of [Eclipse](https://www.eclipse.org), 64-bit.[[1]](#footnote1) -* On Ubuntu or Debian, run the following commands for the installation of required packages: - - ```sh - sudo apt-get update - sudo apt-get install libssl-dev libasound2 - ``` +* On Linux, see the [Linux platform requirements](https://learn.microsoft.com/azure/ai-services/speech-service/quickstarts/setup-platform?tabs=linux&pivots=programming-language-java#platform-requirements) for installing the required dependencies. 1. This sample has not been verified with Eclipse on ARM platforms. diff --git a/quickstart/java/jre/conversation-transcription/pom.xml b/quickstart/java/jre/conversation-transcription/pom.xml index 503771327..fbda3d0fa 100644 --- a/quickstart/java/jre/conversation-transcription/pom.xml +++ b/quickstart/java/jre/conversation-transcription/pom.xml @@ -39,7 +39,7 @@ com.microsoft.cognitiveservices.speech client-sdk - 1.40.0 + 1.41.1 com.google.code.gson diff --git a/quickstart/java/jre/from-microphone/README.md b/quickstart/java/jre/from-microphone/README.md index 8507e4128..4faffd896 100644 --- a/quickstart/java/jre/from-microphone/README.md +++ b/quickstart/java/jre/from-microphone/README.md @@ -12,12 +12,7 @@ See the [accompanying article](https://docs.microsoft.com/azure/cognitive-servic * A PC (Windows x64 or a supported Linux distribution) or Mac (macOS 10.14 or later) capable to run Eclipse,[[1]](#footnote1) with a working microphone. * Java 8 or 11 JRE/JDK. * Version 4.8 of [Eclipse](https://www.eclipse.org), 64-bit.[[1]](#footnote1) -* On Ubuntu or Debian, run the following commands for the installation of required packages: - - ```sh - sudo apt-get update - sudo apt-get install libssl-dev libasound2 - ``` +* On Linux, see the [Linux platform requirements](https://learn.microsoft.com/azure/ai-services/speech-service/quickstarts/setup-platform?tabs=linux&pivots=programming-language-java#platform-requirements) for installing the required dependencies. 1. This sample has not been verified with Eclipse on ARM platforms. diff --git a/quickstart/java/jre/from-microphone/pom.xml b/quickstart/java/jre/from-microphone/pom.xml index cf5896191..e4531d6e3 100644 --- a/quickstart/java/jre/from-microphone/pom.xml +++ b/quickstart/java/jre/from-microphone/pom.xml @@ -62,7 +62,7 @@ com.microsoft.cognitiveservices.speech client-sdk - 1.40.0 + 1.41.1 diff --git a/quickstart/java/jre/intent-recognition/README.md b/quickstart/java/jre/intent-recognition/README.md index b30900e4f..53fa487d6 100644 --- a/quickstart/java/jre/intent-recognition/README.md +++ b/quickstart/java/jre/intent-recognition/README.md @@ -12,12 +12,7 @@ See the [accompanying article](https://docs.microsoft.com/azure/cognitive-servic * A PC (Windows x64 or a supported Linux distribution) or Mac (macOS 10.14 or later) capable to run Eclipse,[[1]](#footnote1) with a working microphone. * Java 8 or 11 JRE/JDK. * Version 4.8 of [Eclipse](https://www.eclipse.org), 64-bit.[[1]](#footnote1) -* On Ubuntu or Debian, run the following commands for the installation of required packages: - - ```sh - sudo apt-get update - sudo apt-get install libssl-dev libasound2 - ``` +* On Linux, see the [Linux platform requirements](https://learn.microsoft.com/azure/ai-services/speech-service/quickstarts/setup-platform?tabs=linux&pivots=programming-language-java#platform-requirements) for installing the required dependencies. 1. This sample has not been verified with Eclipse on ARM platforms. diff --git a/quickstart/java/jre/intent-recognition/pom.xml b/quickstart/java/jre/intent-recognition/pom.xml index 47a41891b..b88c55533 100644 --- a/quickstart/java/jre/intent-recognition/pom.xml +++ b/quickstart/java/jre/intent-recognition/pom.xml @@ -39,7 +39,7 @@ com.microsoft.cognitiveservices.speech client-sdk - 1.40.0 + 1.41.1 diff --git a/quickstart/java/jre/meeting-transcription/README.md b/quickstart/java/jre/meeting-transcription/README.md index 69a88a11d..f59b655ab 100644 --- a/quickstart/java/jre/meeting-transcription/README.md +++ b/quickstart/java/jre/meeting-transcription/README.md @@ -13,12 +13,7 @@ See the [accompanying article](https://docs.microsoft.com/azure/cognitive-servic * A PC (Windows x64 or a supported Linux distribution) or Mac (macOS 10.14 or later) capable to run Eclipse,[[1]](#footnote1) with a working microphone. * Java 11 JRE/JDK. * Version 4.8 of [Eclipse](https://www.eclipse.org), 64-bit.[[1]](#footnote1) -* On Ubuntu or Debian, run the following commands for the installation of required packages: - - ```sh - sudo apt-get update - sudo apt-get install libssl-dev libasound2 - ``` +* On Linux, see the [Linux platform requirements](https://learn.microsoft.com/azure/ai-services/speech-service/quickstarts/setup-platform?tabs=linux&pivots=programming-language-java#platform-requirements) for installing the required dependencies. 1. This sample has not been verified with Eclipse on ARM platforms. diff --git a/quickstart/java/jre/meeting-transcription/pom.xml b/quickstart/java/jre/meeting-transcription/pom.xml index 56c95c1df..1ac6f2d92 100644 --- a/quickstart/java/jre/meeting-transcription/pom.xml +++ b/quickstart/java/jre/meeting-transcription/pom.xml @@ -39,7 +39,7 @@ com.microsoft.cognitiveservices.speech client-sdk - 1.40.0 + 1.41.1 com.google.code.gson diff --git a/quickstart/java/jre/speaker-recognition/README.md b/quickstart/java/jre/speaker-recognition/README.md index b48e29df7..3c9ae1c65 100644 --- a/quickstart/java/jre/speaker-recognition/README.md +++ b/quickstart/java/jre/speaker-recognition/README.md @@ -14,12 +14,7 @@ See the [accompanying article](https://docs.microsoft.com/azure/cognitive-servic * A PC (Windows x64 or a supported Linux distribution) or Mac (macOS 10.14 or later) capable to run Eclipse,[[1]](#footnote1) with a working microphone. * Java 8 or 11 JRE/JDK. * Version 4.8 of [Eclipse](https://www.eclipse.org), 64-bit.[[1]](#footnote1) -* On Ubuntu or Debian, run the following commands for the installation of required packages: - - ```sh - sudo apt-get update - sudo apt-get install libssl-dev libasound2 - ``` +* On Linux, see the [Linux platform requirements](https://learn.microsoft.com/azure/ai-services/speech-service/quickstarts/setup-platform?tabs=linux&pivots=programming-language-java#platform-requirements) for installing the required dependencies. 1. This sample has not been verified with Eclipse on ARM platforms. diff --git a/quickstart/java/jre/speaker-recognition/pom.xml b/quickstart/java/jre/speaker-recognition/pom.xml index 253cdfbdc..072d736f9 100644 --- a/quickstart/java/jre/speaker-recognition/pom.xml +++ b/quickstart/java/jre/speaker-recognition/pom.xml @@ -36,7 +36,7 @@ com.microsoft.cognitiveservices.speech client-sdk - 1.40.0 + 1.41.1 diff --git a/quickstart/java/jre/text-to-speech/README.md b/quickstart/java/jre/text-to-speech/README.md index 5e77f5070..e78aeb695 100644 --- a/quickstart/java/jre/text-to-speech/README.md +++ b/quickstart/java/jre/text-to-speech/README.md @@ -12,12 +12,7 @@ See the [accompanying article](https://docs.microsoft.com/azure/cognitive-servic * A PC (Windows x64 or a supported Linux distribution) or Mac (macOS 10.14 or later) capable to run Eclipse,[[1]](#footnote1) with a working speaker. * Java 8 or 11 JRE/JDK. * Version 4.8 of [Eclipse](https://www.eclipse.org), 64-bit.[[1]](#footnote1) -* On Ubuntu or Debian, run the following commands for the installation of required packages: - - ```sh - sudo apt-get update - sudo apt-get install libssl-dev libasound2 - ``` +* On Linux, see the [Linux platform requirements](https://learn.microsoft.com/azure/ai-services/speech-service/quickstarts/setup-platform?tabs=linux&pivots=programming-language-java#platform-requirements) for installing the required dependencies. 1. This sample has not been verified with Eclipse on ARM platforms. diff --git a/quickstart/java/jre/text-to-speech/pom.xml b/quickstart/java/jre/text-to-speech/pom.xml index ff509bd64..f35f343e2 100644 --- a/quickstart/java/jre/text-to-speech/pom.xml +++ b/quickstart/java/jre/text-to-speech/pom.xml @@ -62,7 +62,7 @@ com.microsoft.cognitiveservices.speech client-sdk - 1.40.0 + 1.41.1 diff --git a/quickstart/java/jre/translate-speech-to-text/README.md b/quickstart/java/jre/translate-speech-to-text/README.md index fe9aa87f4..2ca4bd7df 100644 --- a/quickstart/java/jre/translate-speech-to-text/README.md +++ b/quickstart/java/jre/translate-speech-to-text/README.md @@ -12,12 +12,7 @@ See the [accompanying article](https://docs.microsoft.com/azure/cognitive-servic * A PC (Windows x64 or a supported Linux distribution) or Mac (macOS 10.14 or later) capable to run Eclipse,[[1]](#footnote1) with a working microphone. * Java 8 or 11 JRE/JDK. * Version 4.8 of [Eclipse](https://www.eclipse.org), 64-bit.[[1]](#footnote1) -* On Ubuntu or Debian, run the following commands for the installation of required packages: - - ```sh - sudo apt-get update - sudo apt-get install libssl-dev libasound2 - ``` +* On Linux, see the [Linux platform requirements](https://learn.microsoft.com/azure/ai-services/speech-service/quickstarts/setup-platform?tabs=linux&pivots=programming-language-java#platform-requirements) for installing the required dependencies. 1. This sample has not been verified with Eclipse on ARM platforms. diff --git a/quickstart/java/jre/translate-speech-to-text/pom.xml b/quickstart/java/jre/translate-speech-to-text/pom.xml index 6f4afacb8..d608a501f 100644 --- a/quickstart/java/jre/translate-speech-to-text/pom.xml +++ b/quickstart/java/jre/translate-speech-to-text/pom.xml @@ -20,7 +20,7 @@ com.microsoft.cognitiveservices.speech client-sdk - 1.40.0 + 1.41.1 diff --git a/quickstart/java/jre/virtual-assistant/README.md b/quickstart/java/jre/virtual-assistant/README.md index 055fa0c90..53c34fc1f 100644 --- a/quickstart/java/jre/virtual-assistant/README.md +++ b/quickstart/java/jre/virtual-assistant/README.md @@ -13,12 +13,7 @@ See the [accompanying article](https://docs.microsoft.com/azure/cognitive-servic * Java 8 or 11 JRE/JDK. * Version 4.8 of [Eclipse](https://www.eclipse.org), 64-bit.[[1]](#footnote1) * A pre-configured bot created using Bot Framework version 4.2 or above. See [here for steps on how to create a bot](https://blog.botframework.com/2018/05/07/build-a-microsoft-bot-framework-bot-with-the-bot-builder-sdk-v4/). The bot would need to subscribe to the new "Direct Line Speech" channel to receive voice inputs. -* On Ubuntu or Debian, run the following commands for the installation of required packages: - - ```sh - sudo apt-get update - sudo apt-get install libssl-dev libasound2 - ``` +* On Linux, see the [Linux platform requirements](https://learn.microsoft.com/azure/ai-services/speech-service/quickstarts/setup-platform?tabs=linux&pivots=programming-language-java#platform-requirements) for installing the required dependencies. 1. This sample has not been verified with Eclipse on ARM platforms. diff --git a/quickstart/java/jre/virtual-assistant/pom.xml b/quickstart/java/jre/virtual-assistant/pom.xml index 7e8783c34..982e3279e 100644 --- a/quickstart/java/jre/virtual-assistant/pom.xml +++ b/quickstart/java/jre/virtual-assistant/pom.xml @@ -26,7 +26,7 @@ com.microsoft.cognitiveservices.speech client-sdk - 1.40.0 + 1.41.1 org.slf4j diff --git a/quickstart/javascript/node/conversation-transcription/package.json b/quickstart/javascript/node/conversation-transcription/package.json index 40c7319d6..2bb4a57fc 100644 --- a/quickstart/javascript/node/conversation-transcription/package.json +++ b/quickstart/javascript/node/conversation-transcription/package.json @@ -12,6 +12,6 @@ "license": "MIT", "dependencies": { "https-proxy-agent": "^3.0.0", - "microsoft-cognitiveservices-speech-sdk": "^1.40.0" + "microsoft-cognitiveservices-speech-sdk": "^1.41.0" } } diff --git a/quickstart/javascript/node/from-file/package.json b/quickstart/javascript/node/from-file/package.json index 40c7319d6..2bb4a57fc 100644 --- a/quickstart/javascript/node/from-file/package.json +++ b/quickstart/javascript/node/from-file/package.json @@ -12,6 +12,6 @@ "license": "MIT", "dependencies": { "https-proxy-agent": "^3.0.0", - "microsoft-cognitiveservices-speech-sdk": "^1.40.0" + "microsoft-cognitiveservices-speech-sdk": "^1.41.0" } } diff --git a/quickstart/javascript/node/meeting-transcription/package.json b/quickstart/javascript/node/meeting-transcription/package.json index 40c7319d6..2bb4a57fc 100644 --- a/quickstart/javascript/node/meeting-transcription/package.json +++ b/quickstart/javascript/node/meeting-transcription/package.json @@ -12,6 +12,6 @@ "license": "MIT", "dependencies": { "https-proxy-agent": "^3.0.0", - "microsoft-cognitiveservices-speech-sdk": "^1.40.0" + "microsoft-cognitiveservices-speech-sdk": "^1.41.0" } } diff --git a/quickstart/javascript/node/speaker-recognition/identification/package.json b/quickstart/javascript/node/speaker-recognition/identification/package.json index 20203cb6a..3e6fc03b2 100644 --- a/quickstart/javascript/node/speaker-recognition/identification/package.json +++ b/quickstart/javascript/node/speaker-recognition/identification/package.json @@ -12,6 +12,6 @@ "license": "MIT", "dependencies": { "https-proxy-agent": "^3.0.0", - "microsoft-cognitiveservices-speech-sdk": "^1.40.0" + "microsoft-cognitiveservices-speech-sdk": "^1.41.0" } } diff --git a/quickstart/javascript/node/speaker-recognition/verification/package.json b/quickstart/javascript/node/speaker-recognition/verification/package.json index 458f5baa7..7c55381fe 100644 --- a/quickstart/javascript/node/speaker-recognition/verification/package.json +++ b/quickstart/javascript/node/speaker-recognition/verification/package.json @@ -12,6 +12,6 @@ "license": "MIT", "dependencies": { "https-proxy-agent": "^3.0.0", - "microsoft-cognitiveservices-speech-sdk": "^1.40.0" + "microsoft-cognitiveservices-speech-sdk": "^1.41.0" } } diff --git a/quickstart/javascript/node/text-to-speech/package.json b/quickstart/javascript/node/text-to-speech/package.json index b18dc9818..3754c015f 100644 --- a/quickstart/javascript/node/text-to-speech/package.json +++ b/quickstart/javascript/node/text-to-speech/package.json @@ -12,7 +12,7 @@ "license": "MIT", "dependencies": { "https-proxy-agent": "^3.0.0", - "microsoft-cognitiveservices-speech-sdk": "^1.40.0", + "microsoft-cognitiveservices-speech-sdk": "^1.41.0", "readline": "^1.3.0" } } diff --git a/quickstart/objectivec/macos/from-microphone/helloworld/Podfile b/quickstart/objectivec/macos/from-microphone/helloworld/Podfile index 6f5257e09..6a8080e85 100644 --- a/quickstart/objectivec/macos/from-microphone/helloworld/Podfile +++ b/quickstart/objectivec/macos/from-microphone/helloworld/Podfile @@ -1,4 +1,4 @@ target 'helloworld' do platform :osx, '10.13' - pod 'MicrosoftCognitiveServicesSpeech-macOS', '~> 1.40.0' + pod 'MicrosoftCognitiveServicesSpeech-macOS', '~> 1.41.1' end diff --git a/quickstart/objectivec/macos/from-microphone/helloworld/helloworld/AppDelegate.m b/quickstart/objectivec/macos/from-microphone/helloworld/helloworld/AppDelegate.m index ce080470d..e83f26455 100644 --- a/quickstart/objectivec/macos/from-microphone/helloworld/helloworld/AppDelegate.m +++ b/quickstart/objectivec/macos/from-microphone/helloworld/helloworld/AppDelegate.m @@ -56,7 +56,7 @@ - (void)buttonPressed:(NSButton *)button { NSLog(@"Say something..."); // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since recognizeOnce() returns only a single utterance, it is suitable only for single // shot recognition like command or query. diff --git a/quickstart/objectivec/macos/text-to-speech/helloworld/Podfile b/quickstart/objectivec/macos/text-to-speech/helloworld/Podfile index 6f5257e09..6a8080e85 100644 --- a/quickstart/objectivec/macos/text-to-speech/helloworld/Podfile +++ b/quickstart/objectivec/macos/text-to-speech/helloworld/Podfile @@ -1,4 +1,4 @@ target 'helloworld' do platform :osx, '10.13' - pod 'MicrosoftCognitiveServicesSpeech-macOS', '~> 1.40.0' + pod 'MicrosoftCognitiveServicesSpeech-macOS', '~> 1.41.1' end diff --git a/quickstart/python/from-microphone/README.md b/quickstart/python/from-microphone/README.md index d34ec1125..a373d18aa 100644 --- a/quickstart/python/from-microphone/README.md +++ b/quickstart/python/from-microphone/README.md @@ -11,12 +11,7 @@ Before you get started, here's a list of prerequisites: * A subscription key for the Speech service. See [Try the speech service for free](https://docs.microsoft.com/azure/cognitive-services/speech-service/get-started). * On Windows and Linux Python 3.6 or later needs to be installed. On Mac, minimum version for Python is 3.7. Downloads are available [here](https://www.python.org/downloads/). * The Python Speech SDK package is available for Windows (x64 and x86), Mac x64 (macOS X version 10.14 or later), Mac arm64 (macOS version 11.0 or later), and [specific Linux distributions and target architectures](https://docs.microsoft.com/azure/cognitive-services/speech-service/speech-sdk?tabs=linux). -* On Ubuntu or Debian, run the following commands for the installation of required packages: - ```sh - sudo apt-get update - sudo apt-get install libssl-dev libasound2 - ``` - +* On Linux, see the [Linux platform requirements](https://learn.microsoft.com/azure/ai-services/speech-service/quickstarts/setup-platform?tabs=linux&pivots=programming-language-python#platform-requirements) for installing the required dependencies. * On Windows you need the [Microsoft Visual C++ Redistributable for Visual Studio 2017](https://support.microsoft.com/help/2977003/the-latest-supported-visual-c-downloads) for your platform. ## Get the Speech SDK Python Package diff --git a/quickstart/python/from-microphone/quickstart.ipynb b/quickstart/python/from-microphone/quickstart.ipynb index bf390f10c..eaaafa282 100644 --- a/quickstart/python/from-microphone/quickstart.ipynb +++ b/quickstart/python/from-microphone/quickstart.ipynb @@ -117,7 +117,7 @@ "metadata": {}, "source": [ "Starts speech recognition, and returns after a single utterance is recognized. The end of a\n", - "single utterance is determined by listening for silence at the end or until a maximum of 15\n", + "single utterance is determined by listening for silence at the end or until a maximum of about 30\n", "seconds of audio is processed. The task returns the recognition text as result. \n", "Note: Since `recognize_once()` returns only a single utterance, it is suitable only for single\n", "shot recognition like command or query. \n", diff --git a/quickstart/python/from-microphone/quickstart.py b/quickstart/python/from-microphone/quickstart.py index b397726c3..5b2667cb3 100644 --- a/quickstart/python/from-microphone/quickstart.py +++ b/quickstart/python/from-microphone/quickstart.py @@ -16,7 +16,7 @@ # Starts speech recognition, 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 +# single utterance is determined by listening for silence at the end or until a maximum of about 30 # 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. diff --git a/quickstart/python/intent-recognition/README.md b/quickstart/python/intent-recognition/README.md index 9c95fbb8a..46886003c 100644 --- a/quickstart/python/intent-recognition/README.md +++ b/quickstart/python/intent-recognition/README.md @@ -11,12 +11,7 @@ Before you get started, here's a list of prerequisites: * A subscription key for the Speech service. See [Try the speech service for free](https://docs.microsoft.com/azure/cognitive-services/speech-service/get-started). * On Windows and Linux Python 3.6 or later needs to be installed. On Mac, minimum version for Python is 3.7. Downloads are available [here](https://www.python.org/downloads/). * The Python Speech SDK package is available for Windows (x64 and x86), Mac x64 (macOS X version 10.14 or later), Mac arm64 (macOS version 11.0 or later), and [specific Linux distributions and target architectures](https://docs.microsoft.com/azure/cognitive-services/speech-service/speech-sdk?tabs=linux). -* On Ubuntu or Debian, run the following commands for the installation of required packages: - ```sh - sudo apt-get update - sudo apt-get install libssl-dev libasound2 - ``` - +* On Linux, see the [Linux platform requirements](https://learn.microsoft.com/azure/ai-services/speech-service/quickstarts/setup-platform?tabs=linux&pivots=programming-language-python#platform-requirements) for installing the required dependencies. * On Windows you need the [Microsoft Visual C++ Redistributable for Visual Studio 2017](https://support.microsoft.com/help/2977003/the-latest-supported-visual-c-downloads) for your platform. ## Get the Speech SDK Python Package diff --git a/quickstart/python/intent-recognition/quickstart.ipynb b/quickstart/python/intent-recognition/quickstart.ipynb index bf390f10c..eaaafa282 100644 --- a/quickstart/python/intent-recognition/quickstart.ipynb +++ b/quickstart/python/intent-recognition/quickstart.ipynb @@ -117,7 +117,7 @@ "metadata": {}, "source": [ "Starts speech recognition, and returns after a single utterance is recognized. The end of a\n", - "single utterance is determined by listening for silence at the end or until a maximum of 15\n", + "single utterance is determined by listening for silence at the end or until a maximum of about 30\n", "seconds of audio is processed. The task returns the recognition text as result. \n", "Note: Since `recognize_once()` returns only a single utterance, it is suitable only for single\n", "shot recognition like command or query. \n", diff --git a/quickstart/python/intent-recognition/quickstart.py b/quickstart/python/intent-recognition/quickstart.py index e23025c90..5607d702e 100644 --- a/quickstart/python/intent-recognition/quickstart.py +++ b/quickstart/python/intent-recognition/quickstart.py @@ -39,7 +39,7 @@ # intent_recognizer.add_all_intents(model) # Starts intent recognition, 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 +# single utterance is determined by listening for silence at the end or until a maximum of about 30 # seconds of audio is processed. It 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. diff --git a/quickstart/python/text-to-speech/README.md b/quickstart/python/text-to-speech/README.md index 329d3c58b..4c5ea6b21 100644 --- a/quickstart/python/text-to-speech/README.md +++ b/quickstart/python/text-to-speech/README.md @@ -11,12 +11,7 @@ Before you get started, here's a list of prerequisites: * A subscription key for the Speech service. See [Try the speech service for free](https://docs.microsoft.com/azure/cognitive-services/speech-service/get-started). * On Windows and Linux Python 3.6 or later needs to be installed. On Mac, minimum version for Python is 3.7. Downloads are available [here](https://www.python.org/downloads/). * The Python Speech SDK package is available for Windows (x64 and x86), Mac x64 (macOS X version 10.14 or later), Mac arm64 (macOS version 11.0 or later), and [specific Linux distributions and target architectures](https://docs.microsoft.com/azure/cognitive-services/speech-service/speech-sdk?tabs=linux). -* On Ubuntu or Debian, run the following commands for the installation of required packages: - ```sh - sudo apt-get update - sudo apt-get install libssl-dev libasound2 - ``` - +* On Linux, see the [Linux platform requirements](https://learn.microsoft.com/azure/ai-services/speech-service/quickstarts/setup-platform?tabs=linux&pivots=programming-language-python#platform-requirements) for installing the required dependencies. * On Windows you need the [Microsoft Visual C++ Redistributable for Visual Studio 2017](https://support.microsoft.com/help/2977003/the-latest-supported-visual-c-downloads) for your platform. ## Get the Speech SDK Python Package diff --git a/samples/cpp/embedded-speech/samples/packages.config b/samples/cpp/embedded-speech/samples/packages.config index e3fd96589..ca927e1d9 100644 --- a/samples/cpp/embedded-speech/samples/packages.config +++ b/samples/cpp/embedded-speech/samples/packages.config @@ -1,9 +1,9 @@ - - - - - + + + + + \ No newline at end of file diff --git a/samples/cpp/embedded-speech/samples/samples.vcxproj b/samples/cpp/embedded-speech/samples/samples.vcxproj index b65112f56..559d8dc79 100644 --- a/samples/cpp/embedded-speech/samples/samples.vcxproj +++ b/samples/cpp/embedded-speech/samples/samples.vcxproj @@ -77,11 +77,11 @@ - - - - - + + + + + @@ -241,11 +241,11 @@ This project references NuGet package(s) that are missing on this computer. Use NuGet Package Restore to download them. For more information, see http://go.microsoft.com/fwlink/?LinkID=322105. The missing file is {0}. - - - - - + + + + + \ No newline at end of file diff --git a/samples/cpp/linux/compressed-audio-input/README.md b/samples/cpp/linux/compressed-audio-input/README.md index eed9e7556..8268dc34c 100644 --- a/samples/cpp/linux/compressed-audio-input/README.md +++ b/samples/cpp/linux/compressed-audio-input/README.md @@ -12,13 +12,10 @@ The compressed audio input stream should be either in MP3 or Opus format. * A subscription key for the Speech service. See [Try the speech service for free](https://docs.microsoft.com/azure/cognitive-services/speech-service/get-started). * A PC with a [supported Linux distribution](https://docs.microsoft.com/azure/cognitive-services/speech-service/speech-sdk?tabs=linux). -* On Ubuntu or Debian, install these packages to build and run this sample: - - ```sh - sudo apt-get update - sudo apt-get install build-essential libssl-dev libasound2 wget - sudo apt-get install libgstreamer1.0-0 gstreamer1.0-plugins-base gstreamer1.0-plugins-good gstreamer1.0-plugins-bad gstreamer1.0-plugins-ugly - ``` +* See +the [Linux platform requirements](https://learn.microsoft.com/azure/ai-services/speech-service/quickstarts/setup-platform?tabs=linux&pivots=programming-language-cpp#platform-requirements) +and [how to use compressed audio](https://learn.microsoft.com/azure/ai-services/speech-service/how-to-use-codec-compressed-audio-input-streams?tabs=linux&pivots=programming-language-cpp) +for installing the required dependencies. ## Build the sample diff --git a/samples/cpp/linux/compressed-audio-input/compressed-audio-input.cpp b/samples/cpp/linux/compressed-audio-input/compressed-audio-input.cpp index c1ea60b0b..ee1a3a253 100644 --- a/samples/cpp/linux/compressed-audio-input/compressed-audio-input.cpp +++ b/samples/cpp/linux/compressed-audio-input/compressed-audio-input.cpp @@ -93,7 +93,7 @@ void recognizeSpeech(const std::string& compressedFileName) std::cout << "Recognizing ..." << std::endl; // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. diff --git a/samples/cpp/windows/console/samples/intent_recognition_samples.cpp b/samples/cpp/windows/console/samples/intent_recognition_samples.cpp index 50765ba4d..a267d8c54 100644 --- a/samples/cpp/windows/console/samples/intent_recognition_samples.cpp +++ b/samples/cpp/windows/console/samples/intent_recognition_samples.cpp @@ -41,7 +41,7 @@ void IntentRecognitionWithMicrophone() std::cout << "Say something..." << std::endl; // Starts intent recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. @@ -105,7 +105,7 @@ void IntentRecognitionWithLanguage() std::cout << "Say something in " << lang << "..." << std::endl; // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end, or until a maximum of about 30 // seconds of audio is processed. The future returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. @@ -281,7 +281,7 @@ void IntentRecognitionWithPatternMatchingAndMicrophone() std::cout << "Say something..." << std::endl; // Starts intent recognition, 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 + // single utterance is determined by listening for silence at the end, or until a maximum of about 30 // seconds of audio is processed. The future returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. diff --git a/samples/cpp/windows/console/samples/packages.config b/samples/cpp/windows/console/samples/packages.config index 01bc6219d..52ced3a4e 100644 --- a/samples/cpp/windows/console/samples/packages.config +++ b/samples/cpp/windows/console/samples/packages.config @@ -1,6 +1,6 @@ - - + + \ No newline at end of file diff --git a/samples/cpp/windows/console/samples/samples.vcxproj b/samples/cpp/windows/console/samples/samples.vcxproj index daf7b9274..c34599f17 100644 --- a/samples/cpp/windows/console/samples/samples.vcxproj +++ b/samples/cpp/windows/console/samples/samples.vcxproj @@ -56,8 +56,8 @@ - - + + @@ -215,8 +215,8 @@ This project references NuGet package(s) that are missing on this computer. Use NuGet Package Restore to download them. For more information, see http://go.microsoft.com/fwlink/?LinkID=322105. The missing file is {0}. - - + + \ No newline at end of file diff --git a/samples/cpp/windows/console/samples/speech_recognition_samples.cpp b/samples/cpp/windows/console/samples/speech_recognition_samples.cpp index b660c1b36..e5fd72940 100644 --- a/samples/cpp/windows/console/samples/speech_recognition_samples.cpp +++ b/samples/cpp/windows/console/samples/speech_recognition_samples.cpp @@ -31,7 +31,7 @@ void SpeechRecognitionWithMicrophone() cout << "Say something...\n"; // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. @@ -86,7 +86,7 @@ void SpeechRecognitionWithLanguageAndUsingDetailedOutputFormat() cout << "Say something in " << lang << "...\n"; // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. @@ -233,7 +233,7 @@ void SpeechRecognitionUsingCustomizedModel() cout << "Say something...\n"; // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. @@ -854,7 +854,7 @@ void SpeechRecognitionAndLanguageIdWithMicrophone() cout << "Say something in English or German...\n"; // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. @@ -914,7 +914,7 @@ void SpeechRecognitionAndLanguageIdWithCustomModelsWithMicrophone() cout << "Say something in either English or French...\n"; // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. @@ -1130,7 +1130,7 @@ void SpeechRecognitionFromMicrophoneWithMASEnabledAndPresetGeometrySpecified() cout << "Say something..." << std::endl; // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. @@ -1297,7 +1297,7 @@ void SpeechRecognitionFromPullStreamWithSelectMASEnhancementsEnabled() auto recognizer = SpeechRecognizer::FromConfig(config, audioInput); // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. diff --git a/samples/cpp/windows/console/samples/standalone_language_detection_samples.cpp b/samples/cpp/windows/console/samples/standalone_language_detection_samples.cpp index 101075709..2d61ce6d6 100644 --- a/samples/cpp/windows/console/samples/standalone_language_detection_samples.cpp +++ b/samples/cpp/windows/console/samples/standalone_language_detection_samples.cpp @@ -31,7 +31,7 @@ void StandaloneLanguageDetectionWithMicrophone() cout << "Say something in German, Chinese or English...\n"; // Starts Standalone language detection, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. @@ -83,7 +83,7 @@ void StandaloneLanguageDetectionWithFileInput() auto recognizer = SourceLanguageRecognizer::FromConfig(config, autoDetectSourceLanguageConfig, audioInput); // Starts Standalone language detection, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. diff --git a/samples/cpp/windows/console/samples/translation_samples.cpp b/samples/cpp/windows/console/samples/translation_samples.cpp index c38be060e..ccfdce0c3 100644 --- a/samples/cpp/windows/console/samples/translation_samples.cpp +++ b/samples/cpp/windows/console/samples/translation_samples.cpp @@ -40,7 +40,7 @@ void TranslationWithMicrophone() 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // 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. @@ -188,7 +188,7 @@ void TranslationAndLanguageIdWithMicrophone() cout << "Say something in English or German...\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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // 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. diff --git a/samples/csharp/dotnet-windows/console/samples/packages.config b/samples/csharp/dotnet-windows/console/samples/packages.config index 8e4086e88..22e2761c2 100644 --- a/samples/csharp/dotnet-windows/console/samples/packages.config +++ b/samples/csharp/dotnet-windows/console/samples/packages.config @@ -1,5 +1,5 @@ - - + + \ No newline at end of file diff --git a/samples/csharp/dotnet-windows/console/samples/samples.csproj b/samples/csharp/dotnet-windows/console/samples/samples.csproj index 9fb755d93..832cd59a2 100644 --- a/samples/csharp/dotnet-windows/console/samples/samples.csproj +++ b/samples/csharp/dotnet-windows/console/samples/samples.csproj @@ -144,9 +144,9 @@ 1.7.1 - - - + + + \ No newline at end of file diff --git a/samples/csharp/dotnet-windows/speechtotext-naudio/speechtotext-naudio/packages.config b/samples/csharp/dotnet-windows/speechtotext-naudio/speechtotext-naudio/packages.config index b5f521b19..0cebe8324 100644 --- a/samples/csharp/dotnet-windows/speechtotext-naudio/speechtotext-naudio/packages.config +++ b/samples/csharp/dotnet-windows/speechtotext-naudio/speechtotext-naudio/packages.config @@ -1,6 +1,6 @@ - + diff --git a/samples/csharp/dotnet-windows/speechtotext-naudio/speechtotext-naudio/speechtotext-naudio.csproj b/samples/csharp/dotnet-windows/speechtotext-naudio/speechtotext-naudio/speechtotext-naudio.csproj index bbc4cd687..a893679d1 100644 --- a/samples/csharp/dotnet-windows/speechtotext-naudio/speechtotext-naudio/speechtotext-naudio.csproj +++ b/samples/csharp/dotnet-windows/speechtotext-naudio/speechtotext-naudio/speechtotext-naudio.csproj @@ -55,8 +55,8 @@ true - - ..\packages\Microsoft.CognitiveServices.Speech.1.40.0\lib\net462\Microsoft.CognitiveServices.Speech.csharp.dll + + ..\packages\Microsoft.CognitiveServices.Speech.1.41.1\lib\net462\Microsoft.CognitiveServices.Speech.csharp.dll ..\packages\Microsoft.Win32.Registry.4.7.0\lib\net461\Microsoft.Win32.Registry.dll @@ -106,11 +106,11 @@ - + This project references NuGet package(s) that are missing on this computer. Use NuGet Package Restore to download them. For more information, see http://go.microsoft.com/fwlink/?LinkID=322105. The missing file is {0}. - + \ No newline at end of file diff --git a/samples/csharp/dotnetcore/console/README.md b/samples/csharp/dotnetcore/console/README.md index 50c6cdf00..bf7c71aaa 100644 --- a/samples/csharp/dotnetcore/console/README.md +++ b/samples/csharp/dotnetcore/console/README.md @@ -15,12 +15,7 @@ It runs under .NET 6.0 or later on Windows or Linux (see the list of [supported * On Windows or Linux: * [.NET 6.0](https://dotnet.microsoft.com/download/dotnet/6.0) * On Windows you also need the [Microsoft Visual C++ Redistributable for Visual Studio 2015, 2017 and 2019](https://support.microsoft.com/help/2977003/the-latest-supported-visual-c-downloads) for your platform. -* On Ubuntu or Debian, run the following commands for the installation of required packages: - - ```sh - sudo apt-get update - sudo apt-get install libssl-dev libasound2 - ``` +* On Linux, see the [Linux platform requirements](https://learn.microsoft.com/azure/ai-services/speech-service/quickstarts/setup-platform?tabs=linux&pivots=programming-language-csharp#platform-requirements) for installing the required dependencies. ## Build the sample diff --git a/samples/csharp/dotnetcore/console/samples/samples.csproj b/samples/csharp/dotnetcore/console/samples/samples.csproj index 65498edd2..612cf724f 100644 --- a/samples/csharp/dotnetcore/console/samples/samples.csproj +++ b/samples/csharp/dotnetcore/console/samples/samples.csproj @@ -53,9 +53,9 @@ - - - + + + diff --git a/samples/csharp/dotnetcore/embedded-speech/samples/samples.csproj b/samples/csharp/dotnetcore/embedded-speech/samples/samples.csproj index 0285039f4..67e737adb 100644 --- a/samples/csharp/dotnetcore/embedded-speech/samples/samples.csproj +++ b/samples/csharp/dotnetcore/embedded-speech/samples/samples.csproj @@ -24,11 +24,11 @@ - - - - - + + + + + diff --git a/samples/csharp/maui/embedded-speech/embedded-speech/embedded-speech.csproj b/samples/csharp/maui/embedded-speech/embedded-speech/embedded-speech.csproj index 633fb47fb..3dbd15140 100644 --- a/samples/csharp/maui/embedded-speech/embedded-speech/embedded-speech.csproj +++ b/samples/csharp/maui/embedded-speech/embedded-speech/embedded-speech.csproj @@ -55,11 +55,11 @@ - - - - - + + + + + diff --git a/samples/csharp/maui/speech-to-text/speech-to-text/MainPage.xaml.cs b/samples/csharp/maui/speech-to-text/speech-to-text/MainPage.xaml.cs index 4672c1067..322a648ae 100644 --- a/samples/csharp/maui/speech-to-text/speech-to-text/MainPage.xaml.cs +++ b/samples/csharp/maui/speech-to-text/speech-to-text/MainPage.xaml.cs @@ -47,7 +47,7 @@ private async void OnRecognitionButtonClicked(object sender, EventArgs e) using (var recognizer = new SpeechRecognizer(config)) { // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. diff --git a/samples/csharp/maui/speech-to-text/speech-to-text/speech-to-text.csproj b/samples/csharp/maui/speech-to-text/speech-to-text/speech-to-text.csproj index 0352c9a91..ff1e45f3d 100644 --- a/samples/csharp/maui/speech-to-text/speech-to-text/speech-to-text.csproj +++ b/samples/csharp/maui/speech-to-text/speech-to-text/speech-to-text.csproj @@ -60,7 +60,7 @@ - + diff --git a/samples/csharp/sharedcontent/console/intent_recognition_samples.cs b/samples/csharp/sharedcontent/console/intent_recognition_samples.cs index 9e2fda7a2..cc0c8fe39 100644 --- a/samples/csharp/sharedcontent/console/intent_recognition_samples.cs +++ b/samples/csharp/sharedcontent/console/intent_recognition_samples.cs @@ -44,7 +44,7 @@ public static async Task RecognitionWithMicrophoneAsync() Console.WriteLine("Say something..."); // Starts intent recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. @@ -208,7 +208,7 @@ public static async Task RecognitionWithMicrophoneUsingLanguageAsync() Console.WriteLine("Say something in " + language + "..."); // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. @@ -309,7 +309,7 @@ public static async Task IntentPatternMatchingWithMicrophoneAsync() Console.WriteLine("Say something..."); // Starts intent recognition, 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 + // utterance is determined by listening for silence at the end, or until a maximum of about 30 seconds of audio // is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single shot // recognition like command or query. diff --git a/samples/csharp/sharedcontent/console/speech_recognition_samples.cs b/samples/csharp/sharedcontent/console/speech_recognition_samples.cs index d1bcbef71..d08e4ba83 100644 --- a/samples/csharp/sharedcontent/console/speech_recognition_samples.cs +++ b/samples/csharp/sharedcontent/console/speech_recognition_samples.cs @@ -38,7 +38,7 @@ public static async Task RecognitionWithMicrophoneAsync() Console.WriteLine("Say something..."); // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. @@ -97,7 +97,7 @@ public static async Task RecognitionWithLanguageAndDetailedOutputAsync() Console.WriteLine($"Say something in {language} ..."); // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. @@ -161,7 +161,7 @@ public static async Task RecognitionUsingCustomizedModelAsync() Console.WriteLine("Say something..."); // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. @@ -1626,7 +1626,7 @@ public static async Task RecognitionFromMicrophoneWithMASEnabledAndPresetGeometr Console.WriteLine("Say something..."); // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. @@ -1769,7 +1769,7 @@ public static async Task RecognitionFromPullStreamWithSelectMASEnhancementsEnabl using (var recognizer = new SpeechRecognizer(config, audioInput)) { // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. diff --git a/samples/csharp/sharedcontent/console/speech_recognition_with_language_id_samples.cs b/samples/csharp/sharedcontent/console/speech_recognition_with_language_id_samples.cs index b06d0ad60..71b29b632 100644 --- a/samples/csharp/sharedcontent/console/speech_recognition_with_language_id_samples.cs +++ b/samples/csharp/sharedcontent/console/speech_recognition_with_language_id_samples.cs @@ -35,7 +35,7 @@ public static async Task RecognitionWithMicrophoneAsync() Console.WriteLine("Say something in English or German..."); // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text and the detected language as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. diff --git a/samples/csharp/tts-text-stream/console/TtsTextStreamSample.csproj b/samples/csharp/tts-text-stream/console/TtsTextStreamSample.csproj index 207b33bd3..75eaf9109 100644 --- a/samples/csharp/tts-text-stream/console/TtsTextStreamSample.csproj +++ b/samples/csharp/tts-text-stream/console/TtsTextStreamSample.csproj @@ -9,7 +9,7 @@ - + diff --git a/samples/csharp/uwp/speechtotext-uwp/speechtotext-uwp/MainPage.xaml.cs b/samples/csharp/uwp/speechtotext-uwp/speechtotext-uwp/MainPage.xaml.cs index 1895c9449..d782ff267 100644 --- a/samples/csharp/uwp/speechtotext-uwp/speechtotext-uwp/MainPage.xaml.cs +++ b/samples/csharp/uwp/speechtotext-uwp/speechtotext-uwp/MainPage.xaml.cs @@ -77,7 +77,7 @@ private async void SpeechRecognitionFromMicrophone_ButtonClicked(object sender, using (var recognizer = new SpeechRecognizer(config)) { // Starts speech recognition, 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 + // single utterance is determined by listening for silence at the end or until a maximum of about 30 // seconds of audio is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single // shot recognition like command or query. diff --git a/samples/csharp/uwp/speechtotext-uwp/speechtotext-uwp/speechtotext-uwp.csproj b/samples/csharp/uwp/speechtotext-uwp/speechtotext-uwp/speechtotext-uwp.csproj index 5a2cd78fd..56105f48c 100644 --- a/samples/csharp/uwp/speechtotext-uwp/speechtotext-uwp/speechtotext-uwp.csproj +++ b/samples/csharp/uwp/speechtotext-uwp/speechtotext-uwp/speechtotext-uwp.csproj @@ -108,7 +108,7 @@ - 1.40.0 + 1.41.1 6.2.8 diff --git a/samples/csharp/uwp/texttospeech-uwp/texttospeech-uwp/texttospeech-uwp.csproj b/samples/csharp/uwp/texttospeech-uwp/texttospeech-uwp/texttospeech-uwp.csproj index f207706aa..2aff6b975 100644 --- a/samples/csharp/uwp/texttospeech-uwp/texttospeech-uwp/texttospeech-uwp.csproj +++ b/samples/csharp/uwp/texttospeech-uwp/texttospeech-uwp/texttospeech-uwp.csproj @@ -107,7 +107,7 @@ - 1.40.0 + 1.41.1 6.2.8 diff --git a/samples/csharp/uwp/virtualassistant-uwp/VirtualAssistantPreview.csproj b/samples/csharp/uwp/virtualassistant-uwp/VirtualAssistantPreview.csproj index 1f0122d4c..1751f828e 100644 --- a/samples/csharp/uwp/virtualassistant-uwp/VirtualAssistantPreview.csproj +++ b/samples/csharp/uwp/virtualassistant-uwp/VirtualAssistantPreview.csproj @@ -165,7 +165,7 @@ 4.3.2 - 1.40.0 + 1.41.1 6.2.8 diff --git a/samples/csharp/web/avatar/Avatar.csproj b/samples/csharp/web/avatar/Avatar.csproj index a958ab7ba..32468e216 100644 --- a/samples/csharp/web/avatar/Avatar.csproj +++ b/samples/csharp/web/avatar/Avatar.csproj @@ -9,7 +9,7 @@ - + diff --git a/samples/ingestion/ingestion-client/Connector/Extensions/AppInsightsServiceCollectionExtensions.cs b/samples/ingestion/ingestion-client/Connector/Extensions/AppInsightsServiceCollectionExtensions.cs index 302742547..877626fe4 100644 --- a/samples/ingestion/ingestion-client/Connector/Extensions/AppInsightsServiceCollectionExtensions.cs +++ b/samples/ingestion/ingestion-client/Connector/Extensions/AppInsightsServiceCollectionExtensions.cs @@ -29,7 +29,7 @@ public static IServiceCollection ConfigureIngestionClientLogging(this IServiceCo services.Configure(options => { // The Application Insights SDK adds a default logging filter that instructs ILogger to capture only Warning and more severe logs. Application Insights requires an explicit override. - // Log levels can also be configured using appsettings.json. For more information, see https://learn.microsoft.com/en-us/azure/azure-monitor/app/worker-service#ilogger-logs + // Log levels can also be configured using appsettings.json. For more information, see https://learn.microsoft.com/azure/azure-monitor/app/worker-service#ilogger-logs LoggerFilterRule toRemove = options.Rules.FirstOrDefault(rule => rule.ProviderName == "Microsoft.Extensions.Logging.ApplicationInsights.ApplicationInsightsLoggerProvider"); if (toRemove is not null) diff --git a/samples/java/android/SpeechSynthesis/app/build.gradle b/samples/java/android/SpeechSynthesis/app/build.gradle index 1dbf23377..56463b3ea 100644 --- a/samples/java/android/SpeechSynthesis/app/build.gradle +++ b/samples/java/android/SpeechSynthesis/app/build.gradle @@ -28,7 +28,7 @@ android { dependencies { // Speech SDK - implementation 'com.microsoft.cognitiveservices.speech:client-sdk:1.40.0' + implementation 'com.microsoft.cognitiveservices.speech:client-sdk:1.41.1' implementation 'androidx.appcompat:appcompat:1.6.1' implementation 'com.google.android.material:material:1.8.0' diff --git a/samples/java/android/SpeechSynthesis/app/src/main/java/com/microsoft/cognitiveservices/speech/samples/speechsynthesis/MainActivity.java b/samples/java/android/SpeechSynthesis/app/src/main/java/com/microsoft/cognitiveservices/speech/samples/speechsynthesis/MainActivity.java index d314fa636..f981038c3 100644 --- a/samples/java/android/SpeechSynthesis/app/src/main/java/com/microsoft/cognitiveservices/speech/samples/speechsynthesis/MainActivity.java +++ b/samples/java/android/SpeechSynthesis/app/src/main/java/com/microsoft/cognitiveservices/speech/samples/speechsynthesis/MainActivity.java @@ -94,8 +94,8 @@ protected void onDestroy() { // Release speech synthesizer and its dependencies if (synthesizer != null) { - synthesizer.close(); connection.close(); + synthesizer.close(); } if (speechConfig != null) { speechConfig.close(); @@ -112,8 +112,8 @@ protected void onDestroy() { public void onCreateSynthesizerButtonClicked(View v) { if (synthesizer != null) { speechConfig.close(); - synthesizer.close(); connection.close(); + synthesizer.close(); } // Reuse the synthesizer to lower the latency. diff --git a/samples/java/android/avatar/app/build.gradle b/samples/java/android/avatar/app/build.gradle index 780ab6d50..71579e3c8 100644 --- a/samples/java/android/avatar/app/build.gradle +++ b/samples/java/android/avatar/app/build.gradle @@ -26,7 +26,7 @@ android { dependencies { // Speech SDK - implementation 'com.microsoft.cognitiveservices.speech:client-sdk:1.40.0' + implementation 'com.microsoft.cognitiveservices.speech:client-sdk:1.41.1' implementation 'androidx.appcompat:appcompat:1.7.0' implementation 'com.google.android.material:material:1.12.0' diff --git a/samples/java/android/compressed-input/app/build.gradle b/samples/java/android/compressed-input/app/build.gradle index 6f4a250b3..ab1efa874 100644 --- a/samples/java/android/compressed-input/app/build.gradle +++ b/samples/java/android/compressed-input/app/build.gradle @@ -25,7 +25,7 @@ android { dependencies { // Speech SDK - implementation 'com.microsoft.cognitiveservices.speech:client-sdk:1.40.0' + implementation 'com.microsoft.cognitiveservices.speech:client-sdk:1.41.1' implementation 'androidx.appcompat:appcompat:1.3.1' implementation 'com.google.android.material:material:1.4.0' diff --git a/samples/java/android/embedded-speech/README.md b/samples/java/android/embedded-speech/README.md index 1c5721ebc..27257ae88 100644 --- a/samples/java/android/embedded-speech/README.md +++ b/samples/java/android/embedded-speech/README.md @@ -77,7 +77,7 @@ Do **not** add [client-sdk](https://mvnrepository.com/artifact/com.microsoft.cog **Note:** Make sure that `@aar` suffix is used when the dependency is specified in `build.gradle`. For example, ``` dependencies { - implementation 'com.microsoft.cognitiveservices.speech:client-sdk-embedded:1.40.0@aar' + implementation 'com.microsoft.cognitiveservices.speech:client-sdk-embedded:1.41.1@aar' ... ``` diff --git a/samples/java/android/embedded-speech/app/build.gradle b/samples/java/android/embedded-speech/app/build.gradle index 2a8d9fd04..3d3a65f32 100644 --- a/samples/java/android/embedded-speech/app/build.gradle +++ b/samples/java/android/embedded-speech/app/build.gradle @@ -25,7 +25,7 @@ dependencies { implementation fileTree(include: ['*.jar'], dir: 'libs') // Speech SDK - implementation 'com.microsoft.cognitiveservices.speech:client-sdk-embedded:1.40.0@aar' + implementation 'com.microsoft.cognitiveservices.speech:client-sdk-embedded:1.41.1@aar' implementation 'androidx.appcompat:appcompat:1.3.1' implementation 'androidx.constraintlayout:constraintlayout:2.1.0' diff --git a/samples/java/android/sdkdemo/app/build.gradle b/samples/java/android/sdkdemo/app/build.gradle index b419af94b..4054baaba 100644 --- a/samples/java/android/sdkdemo/app/build.gradle +++ b/samples/java/android/sdkdemo/app/build.gradle @@ -25,7 +25,7 @@ android { dependencies { // Speech SDK - implementation 'com.microsoft.cognitiveservices.speech:client-sdk:1.40.0' + implementation 'com.microsoft.cognitiveservices.speech:client-sdk:1.41.1' // Diff lib for pronunciation assessment implementation "io.github.java-diff-utils:java-diff-utils:4.11" diff --git a/samples/java/jre/console/README.md b/samples/java/jre/console/README.md index f74fb46d1..f43650aea 100644 --- a/samples/java/jre/console/README.md +++ b/samples/java/jre/console/README.md @@ -11,12 +11,7 @@ This sample demonstrates various forms of speech recognition, intent recognition * A PC (Windows x64 or a supported Linux distribution) capable to run Eclipse,[[1]](#footnote1) some sample scenarios require a working microphone. * Java 8 or 11 JRE/JDK. * Version 4.8 of [Eclipse](https://www.eclipse.org), 64-bit.[[1]](#footnote1) -* On Ubuntu or Debian, run the following commands for the installation of required packages: - - ```sh - sudo apt-get update - sudo apt-get install libssl-dev libasound2 - ``` +* On Linux, see the [Linux platform requirements](https://learn.microsoft.com/azure/ai-services/speech-service/quickstarts/setup-platform?tabs=linux&pivots=programming-language-java#platform-requirements) for installing the required dependencies. 1. This sample has not been verified with Eclipse on ARM platforms. diff --git a/samples/java/jre/console/pom.xml b/samples/java/jre/console/pom.xml index 32a95466c..c5904afdd 100644 --- a/samples/java/jre/console/pom.xml +++ b/samples/java/jre/console/pom.xml @@ -56,7 +56,7 @@ com.microsoft.cognitiveservices.speech client-sdk - 1.40.0 + 1.41.1 jakarta.json diff --git a/samples/java/jre/console/src/com/microsoft/cognitiveservices/speech/samples/console/IntentRecognitionSamples.java b/samples/java/jre/console/src/com/microsoft/cognitiveservices/speech/samples/console/IntentRecognitionSamples.java index e5b2599e9..70729f7be 100644 --- a/samples/java/jre/console/src/com/microsoft/cognitiveservices/speech/samples/console/IntentRecognitionSamples.java +++ b/samples/java/jre/console/src/com/microsoft/cognitiveservices/speech/samples/console/IntentRecognitionSamples.java @@ -251,7 +251,7 @@ public static void IntentPatternMatchingWithMicrophone() throws InterruptedExcep System.out.println("Say something..."); // Starts intent recognition, 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 + // utterance is determined by listening for silence at the end, or until a maximum of about 30 seconds of audio // is processed. The task returns the recognition text as result. // Note: Since RecognizeOnceAsync() returns only a single utterance, it is suitable only for single shot // recognition like command or query. diff --git a/samples/java/jre/embedded-speech/pom.xml b/samples/java/jre/embedded-speech/pom.xml index 9ed68c713..b7649efbe 100644 --- a/samples/java/jre/embedded-speech/pom.xml +++ b/samples/java/jre/embedded-speech/pom.xml @@ -56,7 +56,7 @@ com.microsoft.cognitiveservices.speech client-sdk-embedded - 1.40.0 + 1.41.1 org.json diff --git a/samples/js/browser/package.json b/samples/js/browser/package.json index 0bd314014..eda5da87e 100644 --- a/samples/js/browser/package.json +++ b/samples/js/browser/package.json @@ -8,7 +8,7 @@ "axios": "^0.21.1", "bootstrap": "^4.5.3", "dotenv": "^8.2.0", - "microsoft-cognitiveservices-speech-sdk": "^1.18", + "microsoft-cognitiveservices-speech-sdk": "^1.41", "universal-cookie": "^4.0.4", "web-vitals": "^0.2.4" }, diff --git a/samples/js/node/package.json b/samples/js/node/package.json index bc8c0a13f..9965c5f0f 100644 --- a/samples/js/node/package.json +++ b/samples/js/node/package.json @@ -17,7 +17,7 @@ "lodash.foreach": "^4.5.0", "lodash.sum": "^4.0.2", "mic-to-speech": "^1.0.1", - "microsoft-cognitiveservices-speech-sdk": "^1.40.0", + "microsoft-cognitiveservices-speech-sdk": "^1.41.0", "readline": "^1.3.0", "segment": "^0.1.3", "wav": "^1.0.2" diff --git a/samples/kotlin/android/continuous-reco/app/build.gradle b/samples/kotlin/android/continuous-reco/app/build.gradle index 0353b0c65..3a573ac10 100644 --- a/samples/kotlin/android/continuous-reco/app/build.gradle +++ b/samples/kotlin/android/continuous-reco/app/build.gradle @@ -36,5 +36,5 @@ dependencies { implementation 'androidx.appcompat:appcompat:1.4.2' implementation 'com.google.android.material:material:1.6.1' implementation 'androidx.constraintlayout:constraintlayout:2.1.4' - implementation "com.microsoft.cognitiveservices.speech:client-sdk:1.40.0" + implementation "com.microsoft.cognitiveservices.speech:client-sdk:1.41.1" } \ No newline at end of file diff --git a/samples/kotlin/android/tts-pause-example/app/build.gradle b/samples/kotlin/android/tts-pause-example/app/build.gradle index a6562a553..bf2fcf5b5 100644 --- a/samples/kotlin/android/tts-pause-example/app/build.gradle +++ b/samples/kotlin/android/tts-pause-example/app/build.gradle @@ -36,6 +36,6 @@ dependencies { implementation 'com.google.android.material:material:1.6.1' implementation 'androidx.constraintlayout:constraintlayout:2.1.4' - implementation "com.microsoft.cognitiveservices.speech:client-sdk:1.40.0" + implementation "com.microsoft.cognitiveservices.speech:client-sdk:1.41.1" } \ No newline at end of file diff --git a/samples/objective-c/ios/speech-samples/speech-samples.xcodeproj/project.pbxproj b/samples/objective-c/ios/speech-samples/speech-samples.xcodeproj/project.pbxproj index d37bc37e9..2639a312d 100644 --- a/samples/objective-c/ios/speech-samples/speech-samples.xcodeproj/project.pbxproj +++ b/samples/objective-c/ios/speech-samples/speech-samples.xcodeproj/project.pbxproj @@ -53,7 +53,7 @@ 3C00A32B25F8727100512312 /* AudioRecorder.m */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.objc; path = AudioRecorder.m; sourceTree = ""; }; 3C1B8BC92679C50600706BB3 /* pronunciation-assessment.wav */ = {isa = PBXFileReference; lastKnownFileType = audio.wav; path = "pronunciation-assessment.wav"; sourceTree = ""; }; 52CF43E62AEF743E00227EF3 /* pronunciation_assessment_fall.wav */ = {isa = PBXFileReference; lastKnownFileType = audio.wav; path = pronunciation_assessment_fall.wav; sourceTree = ""; }; - 52FC64F929CACB27000C8918 /* MicrosoftCognitiveServicesSpeech.xcframework */ = {isa = PBXFileReference; lastKnownFileType = wrapper.xcframework; name = MicrosoftCognitiveServicesSpeech.xcframework; path = "../../../../../../../../MicrosoftCognitiveServicesSpeech-XCFramework-1.40.0/MicrosoftCognitiveServicesSpeech.xcframework"; sourceTree = ""; }; + 52FC64F929CACB27000C8918 /* MicrosoftCognitiveServicesSpeech.xcframework */ = {isa = PBXFileReference; lastKnownFileType = wrapper.xcframework; name = MicrosoftCognitiveServicesSpeech.xcframework; path = "../../../../../../../../MicrosoftCognitiveServicesSpeech-XCFramework-1.41.1/MicrosoftCognitiveServicesSpeech.xcframework"; sourceTree = ""; }; DC2CBA03227047EA007EB18A /* wreck-a-nice-beach.wav */ = {isa = PBXFileReference; lastKnownFileType = audio.wav; name = "wreck-a-nice-beach.wav"; path = "./wreck-a-nice-beach.wav"; sourceTree = ""; }; F3184E46214674D60096193E /* speech-samples.app */ = {isa = PBXFileReference; explicitFileType = wrapper.application; includeInIndex = 0; path = "speech-samples.app"; sourceTree = BUILT_PRODUCTS_DIR; }; F3184E49214674D60096193E /* AppDelegate.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; path = AppDelegate.h; sourceTree = ""; }; diff --git a/samples/objective-c/macos/speech-keyword-recognition/helloworld/Podfile b/samples/objective-c/macos/speech-keyword-recognition/helloworld/Podfile index 6f5257e09..6a8080e85 100644 --- a/samples/objective-c/macos/speech-keyword-recognition/helloworld/Podfile +++ b/samples/objective-c/macos/speech-keyword-recognition/helloworld/Podfile @@ -1,4 +1,4 @@ target 'helloworld' do platform :osx, '10.13' - pod 'MicrosoftCognitiveServicesSpeech-macOS', '~> 1.40.0' + pod 'MicrosoftCognitiveServicesSpeech-macOS', '~> 1.41.1' end diff --git a/samples/python/console/.flake8 b/samples/python/console/.flake8 index 6f2eaf25c..ac1db61b4 100644 --- a/samples/python/console/.flake8 +++ b/samples/python/console/.flake8 @@ -1,6 +1,6 @@ [flake8] max-line-length = 125 -ignore = ANN101, ANN201 +ignore = ANN101, ANN201, W503, W504 per-file-ignores = __init__.py: F401,F403,F405 mypy-init-return = True \ No newline at end of file diff --git a/samples/python/console/README.md b/samples/python/console/README.md index 0877a2451..b4a842fdd 100644 --- a/samples/python/console/README.md +++ b/samples/python/console/README.md @@ -6,12 +6,7 @@ This sample demonstrates various forms of speech recognition, intent recognition * On Windows and Linux Python 3.7 or later needs to be installed. Downloads are available [here](https://www.python.org/downloads/). * The Python Speech SDK package is available for Windows (x64 and x86), Mac x64 (macOS X version 10.14 or later), Mac arm64 (macOS version 11.0 or later), and Linux (see the list of [supported Linux distributions and target architectures](https://docs.microsoft.com/azure/cognitive-services/speech-service/speech-sdk?tabs=linux)). -* On Ubuntu or Debian, run the following commands for the installation of required packages: - ```sh - sudo apt-get update - sudo apt-get install libssl-dev libasound2 - ``` - +* On Linux, see the [Linux platform requirements](https://learn.microsoft.com/azure/ai-services/speech-service/quickstarts/setup-platform?tabs=linux&pivots=programming-language-java#platform-requirements) for installing the required dependencies. * On Windows you also need the [Microsoft Visual C++ Redistributable for Visual Studio 2017](https://support.microsoft.com/help/2977003/the-latest-supported-visual-c-downloads) for your platform. diff --git a/samples/python/console/chatting/README.md b/samples/python/console/chatting/README.md index aa90b7d07..1998e9f96 100644 --- a/samples/python/console/chatting/README.md +++ b/samples/python/console/chatting/README.md @@ -20,7 +20,7 @@ Update the following strings before running the sample: * `YourServiceRegion`: replace with the [region](https://aka.ms/csspeech/region) your subscription is associated with. * `YourOaiResourceName`: replace with the name of your Azure OAI Resource. * `YourOaiDeploymentName`: replace with the name of your model deployment. You're required to first deploy a model before you can make calls. -* `YourOaiApiVersion`: replace with the [API version](https://learn.microsoft.com/en-US/azure/ai-services/openai/reference#chat-completions) to use for this operation. For example, `2023-05-15`. +* `YourOaiApiVersion`: replace with the [API version](https://learn.microsoft.com/azure/ai-services/openai/reference#chat-completions) to use for this operation. For example, `2023-05-15`. * `YourOaiApiKey`: replace with the Azure OAI resource key. To run the app, navigate to the `samples/python/console/chatting` directory in your local copy of the samples repository. diff --git a/samples/python/console/chatting/chatting_sample.py b/samples/python/console/chatting/chatting_sample.py index 8e03874d4..3643759c6 100644 --- a/samples/python/console/chatting/chatting_sample.py +++ b/samples/python/console/chatting/chatting_sample.py @@ -31,7 +31,7 @@ sys.exit(1) -Set up the subscription info for the Speech Service +# Set up the subscription info for the Speech Service speech_key, service_region = "YourSubscriptionKey", "YourServiceRegion" # Set up the parameters for Azure OAI Services @@ -103,7 +103,7 @@ def get_mispronunciation_clip(offset, duration, save_path, merged_audio_path): def strip_end_silence(file_path): - y, _ = sf.read(file_path, start=0, stop=-int(sample_rate*0.8), dtype=np.float32) + y, _ = sf.read(file_path, start=0, stop=-int(sample_rate * 0.8), dtype=np.float32) sf.write(file_path, y, sample_rate) @@ -380,11 +380,11 @@ def get_prosody_error(error_type, word, last_word): def set_error_dict(json_words): for idx, word in enumerate(json_words): - if get_prosody_error("MissingBreak", word, json_words[idx-1]): + if get_prosody_error("MissingBreak", word, json_words[idx - 1]): error_dict["Missing break"].append(word) - elif get_prosody_error("UnexpectedBreak", word, json_words[idx-1]): + elif get_prosody_error("UnexpectedBreak", word, json_words[idx - 1]): error_dict["Unexpected break"].append(word) - elif get_prosody_error("Monotone", word, json_words[idx-1]): + elif get_prosody_error("Monotone", word, json_words[idx - 1]): error_dict["Monotone"].append(word) def get_error_message(error_types): diff --git a/samples/python/console/intent_sample.py b/samples/python/console/intent_sample.py index f820f6298..b4f3327f9 100644 --- a/samples/python/console/intent_sample.py +++ b/samples/python/console/intent_sample.py @@ -57,7 +57,7 @@ def recognize_intent_once_from_mic(): intent_recognizer.add_intents(intents) # Starts intent recognition, 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 + # single utterance is determined by listening for silence at the end or until a maximum of about 30 # seconds of audio is processed. It 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. @@ -102,7 +102,7 @@ def recognize_intent_once_from_file(): intent_recognizer.add_intents(intents) # Starts intent recognition, 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 + # single utterance is determined by listening for silence at the end or until a maximum of about 30 # seconds of audio is processed. It 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. @@ -180,7 +180,7 @@ def recognizing_callback(evt: speechsdk.intent.IntentRecognitionEventArgs): # Starts non-blocking intent recognition and stop after a single utterance has been 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. + # maximum of about 30 seconds of audio is processed. # Note: Since recognize_once() stops after 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. diff --git a/samples/python/console/speech_language_detection_sample.py b/samples/python/console/speech_language_detection_sample.py index e645073b2..67e36cf8c 100644 --- a/samples/python/console/speech_language_detection_sample.py +++ b/samples/python/console/speech_language_detection_sample.py @@ -51,7 +51,7 @@ def speech_language_detection_once_from_mic(): print("Say something in English or German...") # Starts speech language detection, 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 + # single utterance is determined by listening for silence at the end or until a maximum of about 30 # seconds of audio is processed. It 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. @@ -93,7 +93,7 @@ def speech_language_detection_once_from_file(): audio_config=audio_config) # Starts speech language detection, 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 + # single utterance is determined by listening for silence at the end or until a maximum of about 30 # seconds of audio is processed. It returns the detection text as result. # Note: Since recognize_once() returns only a single utterance, it is suitable only for single # shot detection like command or query. diff --git a/samples/python/console/speech_sample.py b/samples/python/console/speech_sample.py index b377617c7..08260f823 100644 --- a/samples/python/console/speech_sample.py +++ b/samples/python/console/speech_sample.py @@ -50,7 +50,7 @@ def speech_recognize_once_from_mic(): speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config) # Starts speech recognition, 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 + # single utterance is determined by listening for silence at the end or until a maximum of about 30 # seconds of audio is processed. It 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. @@ -80,7 +80,7 @@ def speech_recognize_once_from_file(): speech_config=speech_config, language="de-DE", audio_config=audio_config) # Starts speech recognition, 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 + # single utterance is determined by listening for silence at the end or until a maximum of about 30 # seconds of audio is processed. It 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. @@ -122,7 +122,7 @@ def speech_recognize_once_from_file_with_detailed_recognition_results(): speech_config=speech_config, language="en-US", audio_config=audio_config) # Starts speech recognition, 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 + # single utterance is determined by listening for silence at the end or until a maximum of about 30 # seconds of audio is processed. It 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. @@ -205,7 +205,7 @@ def close(self) -> None: speech_recognizer = speechsdk.SpeechRecognizer(speech_config, audio_config) # Starts speech recognition, 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 + # single utterance is determined by listening for silence at the end or until a maximum of about 30 # seconds of audio is processed. It 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. @@ -241,7 +241,7 @@ def speech_recognize_once_from_file_with_customized_model(): speech_config=speech_config, source_language_config=source_language_config, audio_config=audio_config) # Starts speech recognition, 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 + # single utterance is determined by listening for silence at the end or until a maximum of about 30 # seconds of audio is processed. It 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. @@ -276,7 +276,7 @@ def speech_recognize_once_from_file_with_custom_endpoint_parameters(): speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_config) # Starts speech recognition, 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 + # single utterance is determined by listening for silence at the end or until a maximum of about 30 # seconds of audio is processed. It 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. diff --git a/samples/python/console/translation_sample.py b/samples/python/console/translation_sample.py index 66a654932..fe0a5073e 100644 --- a/samples/python/console/translation_sample.py +++ b/samples/python/console/translation_sample.py @@ -46,7 +46,7 @@ def translation_once_from_mic(): translation_config=translation_config, audio_config=audio_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 + # single utterance is determined by listening for silence at the end or until a maximum of about 30 # seconds of audio is processed. It returns the recognized text as well as the translation. # Note: Since recognize_once() returns only a single utterance, it is suitable only for single # shot recognition like command or query. @@ -88,7 +88,7 @@ def translation_once_from_file(): translation_config=translation_config, audio_config=audio_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 + # single utterance is determined by listening for silence at the end or until a maximum of about 30 # 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. diff --git a/samples/swift/macos/speech-keyword-recognition/helloworld/Podfile b/samples/swift/macos/speech-keyword-recognition/helloworld/Podfile index 3d95c1e77..abcdfb2fd 100644 --- a/samples/swift/macos/speech-keyword-recognition/helloworld/Podfile +++ b/samples/swift/macos/speech-keyword-recognition/helloworld/Podfile @@ -1,5 +1,5 @@ target 'helloworld' do platform :osx, 10.14 - pod 'MicrosoftCognitiveServicesSpeech-macOS', '~> 1.40' + pod 'MicrosoftCognitiveServicesSpeech-macOS', '~> 1.41.1' use_frameworks! end diff --git a/scenarios/cpp/windows/captioning/captioning/captioning.vcxproj b/scenarios/cpp/windows/captioning/captioning/captioning.vcxproj index fbc79f689..592c8de38 100644 --- a/scenarios/cpp/windows/captioning/captioning/captioning.vcxproj +++ b/scenarios/cpp/windows/captioning/captioning/captioning.vcxproj @@ -159,12 +159,12 @@ - + This project references NuGet package(s) that are missing on this computer. Use NuGet Package Restore to download them. For more information, see http://go.microsoft.com/fwlink/?LinkID=322105. The missing file is {0}. - + \ No newline at end of file diff --git a/scenarios/cpp/windows/captioning/captioning/packages.config b/scenarios/cpp/windows/captioning/captioning/packages.config index b2fd9e72f..e51eea91b 100644 --- a/scenarios/cpp/windows/captioning/captioning/packages.config +++ b/scenarios/cpp/windows/captioning/captioning/packages.config @@ -1,4 +1,4 @@ - + \ No newline at end of file diff --git a/scenarios/csharp/dotnetcore/captioning/captioning/captioning.csproj b/scenarios/csharp/dotnetcore/captioning/captioning/captioning.csproj index 25ecc11cd..15470d50b 100644 --- a/scenarios/csharp/dotnetcore/captioning/captioning/captioning.csproj +++ b/scenarios/csharp/dotnetcore/captioning/captioning/captioning.csproj @@ -8,7 +8,7 @@ - + \ No newline at end of file diff --git a/scenarios/java/jre/console/captioning/pom.xml b/scenarios/java/jre/console/captioning/pom.xml index 0f22430f1..2619e06fa 100644 --- a/scenarios/java/jre/console/captioning/pom.xml +++ b/scenarios/java/jre/console/captioning/pom.xml @@ -46,7 +46,7 @@ mvn clean dependency:copy-dependencies com.microsoft.cognitiveservices.speech client-sdk - 1.40.0 + 1.41.1 \ No newline at end of file