I am working on a requirement where I have created a custom speech model for Azure Chatbot. I have uploaded some audio files in https://speech.microsoft.com , created a model and then deployed it manually for getting model id and speech recognition endpoint id. I have done all these steps manually in speech studio, but I want to know if there is any way to automate this process for updating the files. ie. if the audio files would be in some azure blob storage, is there any way if these would be uploaded to azure speech studio automatically through some azure function, so that model is created and deployed.
I have earlier automated Luis model similarly by uploading file to azure blob and then created an azure function to upload to Luis for updating the utterances. So, can anyone guide me if there is any way in Custom Speech model?
Please have a look at the swagger API reference here: https://westus.dev.cognitive.microsoft.com/docs/services/speech-to-text-api-v3-0/operations/CreateModel You can create data sets/models/endpoints using the above REST API. Thanks!