will wasm sdk support getting voice embedding

[wanghsinche]

hi dear team, i'm working on building a real-time asr and i want to add online speaker diarization feature on it.
The offline diarization demo worked well on my machine. I thought i could use it for my online diarization, but I just found that i can't get the voice embedding from it.

Do you have any plan to expose the function to get the embedding from an audio in the wasm SDK? or could you tell how to implement it by myself?

Many thanks!