Information about the Data

google / uis-rnn

This is the library for the Unbounded Interleaved-State Recurrent Neural Network (UIS-RNN) algorithm, corresponding to the paper Fully Supervised Speaker Diarization.

https://arxiv.org/abs/1810.04719

Apache License 2.0

1.55k stars 320 forks source link

Information about the Data #1

Closed dsleo closed 5 years ago

dsleo commented 5 years ago

Hello,

Thank you for open sourcing this ! I haven't found information regarding the data you provide. What is it/ where does it come from ?

wq2012 commented 5 years ago

The files under data/ are toy data that are manually generated. Its only purpose is to show how to use the API.

The docstrings of fit() and predict() will give you a better idea.

MuruganR96 commented 5 years ago

@wq2012 sir how can i form that kind of structure data like train.npz.

from scipy.io.wavfile import read
a = read("adios.wav")
numpy.array(a[1],dtype=float)
np.savez_compressed('train.npz', array1=a[1])
b = np.load('train.npz')

this is k or not for test the demo.py utterences ? help me sir?

wq2012 commented 5 years ago

tests/integration_test.py is the best example for you to understand the APIs.