resources

Various Praat scripts for phonetic and speech analysis.

Various Python scripts for speech, language and data-processing tasks.

R package for calculating and visualising speech rhythm and timing metrics, including ΔC/ΔV, Varco, %V, rPVI-C and nPVI-V.

Zero-install interface for citation-tone workflows: f0 extraction, inspection, normalisation, contour visualisation, modelling and Chao tone summaries.

Local R package for citation-tone analysis, supporting scripted and batch workflows as well as launching the Shiny interface offline.

A multilingual phonetic aligner supporting both forced alignment and textless phonetic alignment.

Transformer-based grapheme-to-phoneme resources and models for more than 100 languages.

An interactive flashcard tool for learning IPA symbols, labels, pronunciation and examples.

An IPA keyboard for phonetics exams that deliberately hides three-term labels, so it does not give away answers.

Pronunciation dictionaries for over 100 languages, collected for the CharsiuG2P project.

Feature-to-phone mapping data used to train the FeatureTTS system.

Step-by-step guide for installing Montreal Forced Aligner 2.0 on Windows, including Linux-on-Windows setup.

Guide for compiling and installing REAPER (Robust Epoch And Pitch EstimatoR) on Windows.

Tutorial for installing and using the Penn Forced Aligner for Mandarin Chinese on Windows.

Multilingual G2P training data for over 100 languages, compiled for the CharsiuG2P project.