How to use customized model with Speech Translate?
We are trying to create speech translation app using customized models for speech recgonition and translation. We have created a custom speech recognition model that performs quite well on our domain. We have also trained some custom translation models…
speech to text batch API + python exception
Hi, Im trying to use Speech to text Batch API. Currently im getting the error below. Also, the audio file content URI provided is publicly accessible. HTTP response body: { "code": "InvalidRequest", "message": "A…
Error API Diarization Speech v3- Azure Cognitives Services
Hello, We ask a question because we are having some errors with Diarization API of Microsoft. The url of the web where Microsoft explains that is: …
Azure Cognitive Service - API Speech Diarization v3 in spanish
Hello, We are trying to transcribe (with diarization) an audio files with two speakers in spanish, but we are not capable of doing in spanish. We tried in english and it runs ok. Is there any service API available in spanish? API:…
Handling my company firewall exceptions for using Azure Speech
Azure Speech sample does not work due to an internal firewall problem. For communication, the ip or url, port to be input for exception handling is required.
![](https://techprofile.blob.core.windows.net/images/k3pGvNqV6k28ggaVHaTPrQ.png?8D803E)
Mic not detecting. Getting Unhandled exception (Exception with an error code: 0xe (SPXERR_MIC_NOT_AVAILABLE))
I have been executing code as per Microsoft Learn : https://video2.skills-academy.com/en-us/learn/modules/transcribe-speech-input-text/7-optional-exercise-listen-incoming-data?pivots=csharp My Earphone/Audio is totally fine. I'm using Visual…
Azure custom keyword
Is thare any option provided to feed custom data to train the keyword detection model in azure speech services custom keyword creation. In the instructions document there is a screenshot with this option. But cannot find this while creating a model. And…
Question on questions
Hi, I've noticed that in about 50% of the voices asking a question has no effect on the voice. In the example bellow I have used all English voices to have each voice say the same sentence with and without a question mark. The problem is mainy in the…
Is is possible to use Batch Transcription with a Custom Endpoint?
Hi, I've set up a custom model in the cognitive services speech studio and I'd like to use it with batch transcription - but I'm not sure how/where to put the 'cid' I have into the post request:…
Error uploading data Speech Studio
On 2/23/21 we now get this error when we try to upload training data to Speech Studio. Failed to upload data Failed to upload data Model_Data_2. Error: "The page was not displayed because the request entity is too large." Try again in a few…
Error rate increasing after training model
I have trained the Pronunciation model on Cognitive Service Speech Studio, but after training the Error Rate of trained model has increased from Base Model - error rate (27.59% , model = (20201019)) Trained Model- error rate (31.47% ) Dataset used…
![](https://techprofile.blob.core.windows.net/images/k3pGvNqV6k28ggaVHaTPrQ.png?8D803E)
Access Dinied Windows.Media.SpeechRecognition.SpeechRecognizer
I have two Application as- MVC Web Application Console Application Now i am opening Console app from Web Application so it's opening in background Process. that is fine. but it giving me exception like Access Denied on below line of code - …
Batch transcription Azure Speech API
Hello, We are using this API to transcript an audio file placed in a blob storage (https://westus.api.cognitive.microsoft.com/speechtotext/v3.0). Is it working properly? Because the output we are receiving is not the one w were receiving two days ago. …
![](https://techprofile.blob.core.windows.net/images/k3pGvNqV6k28ggaVHaTPrQ.png?8D803E)
Data Uploading Errors on Speech Service ( Internal Server Error / Entity too large error / web server received invalid response
We are trying to upload audio files in Azure Speech Service for Speech to text. getting continuous errors of 3 kinds . . sometimes we get Internal Server Error, sometimes we get "Entity is too large" and sometimes we get " Invalid response…
Audio Content Creation: Easier Way to Repeatedly Alternate Between Languages?
I am using audio content creation to create language learning resources. What I am I trying to do is the following: a list of English sentences, each sentence immediately followed by its translation in Spanish. As in, Example Sentence 1 in English …
Custom Speech model Training Error
I have faced below error When Training Custom Speech model . Data uploading and testing were successful. Training Data is one audio file 1 hour 41 min 5 sec long along with transcript. I have S0 subscription. Is there any way to check what…
Fehlermeldunden beim der Audioinhaltserstellung
Wenn ich über Speechstudio -> Audioinhaltserstellung eine "Neue Datei" erstellen möchte, kommt die Meldung "Fehler beim Abrufen von Arbeitsdateien", dann wird versucht, die Website zu laden. Erfolglos. Bei Refresh kommen dann…
![](https://techprofile.blob.core.windows.net/images/k3pGvNqV6k28ggaVHaTPrQ.png?8D803E)
Availability of MicrosoftCognitiveServicesSpeech.framework build for arm64 (Apple M1 SOC)
Hi, when build of 'MicrosoftCognitiveServicesSpeech.framework' for arm64 (for Apple M1 SOC) will be available? Thanks.
How to set varibles for ssml messages and speech style in Text-to-Speech
Hello. I am quite new as it is probably quite apparent. Currently am trying to set a variable for ssml Text-to-Speech, however, after going through every documentation I could find, I still have no solution. Using Python. I would be greatful if anyone…