This repo contains code for training and evaluation phonotactic language models for a final project for Linguistics 215 at Harvard: "Analyzing Phonological Surfeit of the Stimulus in Neural Models".
Most of the core model code is forked from the Phonotactic_LM repo by Mayer and Nelson (2020). Most of my contributions come in model fine-tuning in src/fine_tune.py and data pre-processing of the wug data as described in my paper.