search

microsoft / SynapseML

Simple and Distributed Machine Learning
http://aka.ms/spark
MIT License
5.07k stars 831 forks source link

Cognitive Services - Speaker Recognition #1025

Open ericchansen opened 3 years ago

ericchansen commented 3 years ago

Is your feature request related to a problem? Please describe. Speaker Recognition is now available in preview. I'd like to be able to call this API using mmlspark.

Describe the solution you'd like I'd like to be able to call the Speaker Recognition API using mmlspark.cognitive.

Additional context Until this feature is developed, what is the best work around? Should I call the Speaker Recognition API using HttpOnSpark?

Please let me know if any additional info would be helpful.

AB#1984583

welcome[bot] commented 3 years ago

👋 Thanks for opening your first issue here! If you're reporting a 🐞 bug, please make sure you include steps to reproduce it.

ericchansen commented 3 years ago

Anyone out there?

imatiach-msft commented 3 years ago

I think this is a question for @mhamilton723

mhamilton723 commented 3 years ago

Sorry @ericchansen for the delay. Thanks for this feedback, we have support for ConversationTranscription with Speaker Profiles in latest master (Use the version from the GH badge). We will also look into supporting Speaker recognizer outright. @xuwq1993

In the interim, it would also work to use HTTP on Spark and the REST API (https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/get-started-speaker-recognition?tabs=script&pivots=programming-language-curl)

Hope this helps and will update this issue when we have created bindings for speaker rec

ericchansen commented 3 years ago

Can you provide a bit more details on the appropriate use case for ConversationTranscription with speaker profiles? How does this compare and contrast with Speaker Recognition?

If this is outside your scope, that's okay. I'll just have to do digging to figure out why I'd use one vs the other and then determine which is best for my use case.

dsu4rez commented 3 years ago

Sorry @ericchansen for the delay. Thanks for this feedback, we have support for ConversationTranscription with Speaker Profiles in latest master (Use the version from the GH badge). We will also look into supporting Speaker recognizer outright. @xuwq1993

In the interim, it would also work to use HTTP on Spark and the REST API (https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/get-started-speaker-recognition?tabs=script&pivots=programming-language-curl)

Hope this helps and will update this issue when we have created bindings for speaker rec

Do we know when this would be available in this repo? I saw references in the fork of @xuwq1993