- Notifications
You must be signed in to change notification settings - Fork5
🔭 Speaker diarization via transfer learning
NotificationsYou must be signed in to change notification settings
ubclaunchpad/minutes
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
Jotting things down, so you don't have to.
Minutes is a speaker diarisation library.Speaker diarisation is the processof identifying different speakers in an audio segment. It is useful formaking transcriptions of conversations meaningful by tagging homogenoussections of the conversation with the appropriate speaker.
For more information about Minutes, and how it works, check out ourMediumpost!
Requires Python 3.6!
# Currently we recommend running using the pipenv shell below.python setup.py installDependencies are managed using aPipfile andPipenv:
pipenv installpipenv shell
pytest --cov=minutes -vvvtestfromminutesimportSpeaker,Minutes,Conversationminutes=Minutes(parent='cnn')# Create some speakers, add some audio.s1,s2=Speaker('s1'),Speaker('s2')s1.add_audio('path/to/audio1')s2.add_audio('path/to/audio2')# Add speakers to the model.minutes.add_speakers([s1,s2])# Fit the model.minutes.fit()# Collect a new conversation for prediction.conversation=Conversation('/path/to/conversation.wav')# Create phrases from the conversation.phrases=minutes.phrases(conversation)