aalto-speech/morfessor

Issues

• Is the tokenizer.model deterministic?

  #23 opened 3 years ago by somniumism
  1

• Is your trained English model available?

  #17 opened 6 years ago by colingoldberg
  3

• Where's the detail specific document of training data rules?

  #20 opened 4 years ago by jarodtang
  1

• tarball on website out of date

  #22 opened 4 years ago by pabs3
  1

• Sample data lines for Turkish or English

  #7 opened 8 years ago by ahmetax
  1

• The `--atom-separator` option doesn't work on Python 3

  #8 opened 7 years ago by rspeer
  2

• UnicodeDecodeError when install via pip

  #9 opened 7 years ago by dvinegla
  1

• How to save the segmented word to file?

  #11 opened 7 years ago by yapingzhao
  1

• Unpickling a binary model fails

  #12 opened 6 years ago by thammegowda
  2

• Is there a trained model for Kazakh available for download somewhere?

  #14 opened 6 years ago by prigioni
  1

• How do I control dictionary size

  #18 opened 5 years ago by HanelYuki
  1

• Segmented output format

  #16 opened 5 years ago by valentinmace
  2

• KeyError

  #10 opened 7 years ago by Gldkslfmsd
  6

• Trained models

  #3 opened 7 years ago by gartenfeld
  2

• Morfessor Models Sizes

  #1 opened 7 years ago by aboSamoor
  8

• --output-newlines squeezes multiple newlines

  #2 opened 7 years ago by flammie
  2

• Fix version check in io.py

  #5 opened 8 years ago by anmolgulati
  4

• commend line Vs. API

  #4 opened 9 years ago by kaharjan
  2