问题
Is Google Cloud Speech API support speaker Diarization? as like Watson ? If so what the steps to get the transcript with speaker labled?
More Info: https://www.ibm.com/blogs/watson/2016/12/look-whos-talking-ibm-debuts-watson-speech-text-speaker-diarization-beta/
回答1:
Google has introduced this feature and as on writing it's on BETA.
More info - https://cloud.google.com/speech-to-text/
回答2:
Per the group discussion at Recording, Splitting Audio for Transcribing Two People Conversation using Google Speech API, it looks that you'll have to use the speaker diarization libraries for your use case.
来源：https://stackoverflow.com/questions/50023951/speaker-diarization-support-in-google-speech-api