This is the library for the Unbounded Interleaved-State Recurrent Neural Network (UIS-RNN) algorithm, corresponding to the paper Fully Supervised Speaker Diarization.
Although the whole idea of UIS-RNN is to handle unbounded number of speakers by learning from data, some people may still want to enforce the max number of speakers in predict.
Although the whole idea of UIS-RNN is to handle unbounded number of speakers by learning from data, some people may still want to enforce the max number of speakers in predict.
Consider adding this option in the future.