Using R and Python to syllabify Praat textgrids, using a syllabification algorithm fit for English
Load up syllabify.R in your favorite R environment to use this tool.
The R script depends on three things
syllabify-core.pyin the same directory- This is the syllabification algorithm for English, as found at https://github.com/kylebgorman/syllabify
- .Textgrid files in a folder called
input/in the same directory - those TextGrids MUST have a "Words" tier and a "Phones" tier, with the "Phones" tier containing ARPABET transcriptions
- (ARPABET Phones can be added through a forced aligner like the Montreal Forced Aligner: https://montreal-forced-aligner.readthedocs.io/)
The R script then creates two things
- modified textgrids in a subdirectory called
syllabified/ - an R dataframe called
syllableDFthat contains all the syllable information
Attribution-ShareAlike 2.5 license