faseAlign Documentation

faseAlign is a Python-based suite for doing automatic forced alignment of text to audio for Spanish data using the HTK Speech Recognition Toolkit. The included acoustic models and dictionary are appropriate for many varieties of Latin American Spanish (see development for more details).


  • force-aligned .TextGrid output files
  • support for .txt or .TextGrid input transcriptions
  • custom dictionaries
  • support for stereo audio
  • automatic phonemicization of unknown words
  • automatic syllabification and tonicity


Wilbanks, E. (2022). faseAlign (Version 1.1.14) [Computer software]. Retrieved Oct 14, 2022 from https://github.com/EricWilbanks/faseAlign.


If you’re experiencing issues or have questions about the usage or installation of faseAlign, please feel free to contact me at wilbanks.ericw@gmail.com