More details about Whisper model via Azure AI Speech
Hello, I'm trying to integrate the whisper model via Azure AI Speech. Here are somethings I already know: https://video2.skills-academy.com/en-us/azure/ai-services/speech-service/whisper-overview Whisper model via Azure OpenAI Service is available in the…
How to deploy Live chat avatar based on the sample code in azure?
Hi, I follow this guide on how to setup Live Chat Avatar https://github.com/Azure-Samples/cognitive-services-speech-sdk/tree/yinhew/avatar/samples/js/browser/avatar and managed to setup it locally in my machine. Right how exactly do I deploy it into my…
Speech-to-Text batch transcribe API in germanycentralwest doesn't work
Last Friday (May 31 2024) we started getting the following errors on all transcripts sent to the batch transcription API on our speech resource in…
How to collect user voice in real-time from the browser and then send it to Azure Speech-to-Text via WebSocket?
I'm almost driven crazy by this problem. The audio stream I capture with MediaRecorder on Chrome only supports the webm format, while the Azure API only supports wav and ogg formats. And there is no complete example telling me how to create a support for…
![](https://techprofile.blob.core.windows.net/images/x5BBvkiJIESoIYJSvJDfWg.png?8DA639)
Linux App service running fastAPI Application using Azure Speech SDK doesnt produce recognition and translation results
I Built a Fast API application on a local development environment on Windows, python and Azure Speech SDK and Azure Translation Service. the application will transcribe videos and translate text to another language as desired. it is working fine, and the…
![](https://techprofile.blob.core.windows.net/images/x5BBvkiJIESoIYJSvJDfWg.png?8DA639)
Azure Cognitive Speech to Text Duplicate Sentences returned on Channel 0 and Channel 1
We are developing a solution using Azure Cognitive Speech to Text service and have an issue with duplicate sentences being returned. We have some cases with dual channel audio which appear to transcribe correctly with speaker channels. We have stereo…
How to use both pronunciation file and a structured file in custom speech to text and speech studio?
I am using Microsoft's speech studio's Custom speech to text service. I have created a project and when uploading the data files there are different format in which I can upload. For my project I am using multiple formats of data, I want to use both…
Pause and Resume Azure Ai Continuous Speech to Text Recognition
Hi, I'm trying figurin' out how to pause the speech recognition api, while is in its continuous mode. Pretty much same situation described…
How to prepare plain text data for speech service custom model training
Hi, I'm trying to train my custom speech-to-text model to improve its accuracy in recognizing industry-specific jargon(computer science). Q1: For example, some domain specific terminologies like 'LinkedList', 'HashMap', is it better to format as it is or…
What are the HW or sound limitations for the echo cancellation algorithm in SpeechSDK
hi, I'm having some issues with the echo cancellation on my device, and I'm trying to use speech SDK, when I was analyzing the sounds that I record with microphone it seems that there are present higher harmonics which are 24dB less then primary…
How to have the control over the audio playing when text is converted to speech using Azure Speech Service?
Below is the code I am using to convert text to audio for a button click using Azure speech service, but I am unable to stop the audio that is playing, I would like to use the same button to stop the audio while it is playing. How to have the…
Do we have a batch transcription in microsoft Azure speech to text cognitive services using java sdk or java Rest API ?
we have a embedded speech(microphone) speech to text cognitive service support in java but I want to implement a batch transcription using microsoft Azure cognitive services using java language, do we java sdk or java Rest API support for batch…
Can't preview a sound on Speech Studio
It happens on East US, S0
Seeking Optimal Speech Transcription Service for Mixed Chinese and English Scenarios
Our speech recognition scenario mainly involves a mix of Chinese and English. Currently, we have chosen the Chinese language recognition type (as there is no specific type for mixed Chinese and English). Besides manually adding hotwords and conducting…
Improving Speech to Text Accuracy for Industry-Specific Terminology with Azure AI Service
Hi all, I want to improve the accuracy of reading industry-specific terminology(in Japanese) using Azure AI service's Speech to Text. The challenge is that these terms can have different meanings in general contexts versus industry-specific contexts. How…
no voice when I click "play" button to create speech from text
no voice when I click "play" button to create speech from text, my laptop voice turned on already.
How to fix an issue where my 3D Blendshapes do not align with the audio.
I'm trying to apply viseme 3D Blend Shapes to drive my 3d avatar. When the result is returned, the audio plays before the response's FrameIndex and BlendShape. I received event.animation and used it to set the weight for each blend shape name. However,…
Can I use phonetic language to create perfect speech
Can I use International Phonetic alphabetic translation in azure text to speech to come out with a near perfect speech? If so, how?
How can I use Whisper on Azure AI Speech
Hi, I recently switched from using the whisper model via Azure OpenAI to using Azure AI Speech. However, I noticed that the quality of some transcriptions is worse on Azure AI Speech. On the below page it says that it is possible to use the whisper model…
How to get sentence word timestamp results for real-time speech recognition ?
I am using Golang's SDK this is my golang code func (m *microsoft) Do(ctx context.Context, path string) (string, error) { defer os.Remove(path) accessKeyConfig := AccessKeyList[rand.Intn(len(AccessKeyList))] subscription := accessKeyConfig.Key region…