smeylan Goto Github PK

articulationgan

batch_w2v

Train sets of Word2Vec models with gensim

big_lm

Automate setup and extend (Google) big_lm

cdl_asr

An automatic speech recognition system with (PLL) neural rescoring from a BERT model of child language

cdl_r21_powercalc

child-directed-listening

Codebase for "How adults understand what young children say" (ms under review), "Child-directed Listening:How Caregiver Inference Enables Children's Early Verbal Communication" (CogSci 2021), "Characterizing Child-Directed Listening with Corpus and Model-based Analyses" (ICIS 2020)

childes-db-derived

Django app for populating derived datasets in childes-db

childes_db_tutorial

Materials for childes-db tutorial

ciwganfiwgan-pytorch

clearpond

A python reader for the English Clearpond database

creaky

analysis script(s) for detecting creaky voice

dc_tts

A TensorFlow Implementation of DC-TTS: yet another text-to-speech model

determiner_learning

data preparation, model, and analysis for "The emergence of an abstract grammatical category in children’s early speech"

detlearn

Codebase for "The emergence of an abstract grammatical category in children's early speech"

espeak-py

simple python abstraction for espeak text-to-speech engine

extractpdf

Minimal Python utility for breaking a single PDF into multiple smaller PDF based on start and end page indices

fiwgan-ciwgan

fiwGAN/ciwGAN (Featural and Categorical InfoWaveGAN): Generative Adversarial Phonology and Semantics

frequency-vs-info-content

gensim

Topic Modelling for Humans

ggplot2_tutorial

a brief tutorial focusing on using ggplot2

gibbs_lda

Gibbs Sampler for LDA topic modeling, using Numba

heroku-buildpack-geolite

lexsig

ling290r

lm-scorer

📃Language Model based sentences scoring library

lmzoo

Language Modeling Zoo

measuring-grammatical-productivity

codebase for "Measuring Grammatical Productivity" workshop

muybridge

Code to generate submission for 2019 Art in AI competition at Duke

ngram_hangman

ngrawk

Library for creating and manipulating ngram counts from large corpora