ubclaunchpad / minutes

:telescope: Speaker diarization via transfer learning
https://medium.com/ubc-launch-pad-software-engineering-blog/speaker-diarisation-using-transfer-learning-47ca1a1226f4
27 stars 5 forks source link

Added model class and GBM implementation #72

Closed chadlagore closed 7 years ago

chadlagore commented 7 years ago

:construction_worker: Changes

:flashlight: Testing Instructions

You may need to run python3 pipeline.py Xz3btMhdQ6Y to get your training data for this.

import numpy as np

from app.predict import GBM

X = np.load('app/collector/Xz3btMhdQ6Y/Xz3btMhdQ6Y-features.npy')
y = np.load('app/collector/Xz3btMhdQ6Y/Xz3btMhdQ6Y-labels.npy')

model = GBM()
model.train(X, y)

print(model.predict(X))

:hourglass: Status: Work in Progress :tickets: Ticket(s): #71