Kyle Gorman

textgrid. A Python module for interacting with Praat TextGrid files. Also includes a class for reading HTK .mlf files into Praat

pynini. Read-only mirror of Pynini

swipe. A pitch tracker using Camacho's SWIPE' algorithm, written in C

syllabify. Python module for syllabifying English ARPABET transcriptions

EditTransducer. Python implementation of Levenshtein distance and Levenshtein automata matching

pytrie. An efficient implementation of a prefix tree ("trie") using Python dictionaries, with autocompletion

perceptronix. Sparse and dense linear models, for C++ and Python, with funny optimizations

hayes2009. Hayes 2009 phonological feature tables

SOTA-taggers. Code for Gorman & Bedrick's "We need to talk about standard splits" (ACL '19)

ELP-annotations. Morphological annotations from the English Lexicon Project

wikipron. Massively multilingual pronunciation mining

citylex. An English lexical database from the Big 🍎, let's go Mets baby love da Mets

lingtex. Macros for linguistics research in TeX

whatq. Counts quoting style in different languages and scripts

swc. A simple threaded wave length counter for Python

childes_processing. Python code for processing CHILDES XML files

ptbtok. Penn Treebank tokenizer with no dependencies

elevator.js. Elevator effect in pure Javascript

tlgu_resources. C

dissertation. My University of Pennsylvania dissertation

smartquote. 🧠 substitute or remove “smart” quotes 🤯

pair_ngram_model. Python