Issues · br-pki/detectLanguage · GitHub

Labels Milestones

identify bottlenecks in code execution to speed up generation of sample(s)

#15

· br-pki opened

on Aug 4, 2021

implement data augmentation option

#14

· br-pki opened

on Aug 3, 2021

implement pycountry (or similar) instead of using language_mappings.csv

good first issue

#11

· br-pki opened

on Jul 30, 2021

argparse: implement option to specify train size: float between 0 & 1

good first issue

#8

· br-pki opened

on Jul 26, 2021

argparse: implement option to specify where to save test-train (if outputted)

good first issue

#7

· br-pki opened

on Jul 26, 2021

argparse: implement option to specify where to save sentences.csv (if downloaded)

good first issue

#6

· br-pki opened

on Jul 26, 2021

implement a better way of limiting total sample size while considering the size of individual languges in subset of corpus

#5

· br-pki opened

on Jul 26, 2021