This repository contains a collection of resources for Uyghur linguistics, mostly constructed to assist in the initial data-gathering and data-organizing stages of a larger project, the goal of which is the construction of an automated speech-recognition system for the Uyghur language.
-
IPATranscriber contains a Python script which outputs broad phonemic transcriptions (in the International Phonetic Alphabet) of Uyghur words in Latin orthography.
-
UyghurTransliterator contains a Python script which transliterates an input file (in Uyghur) from one writing system to another. Nine writing systems are currently supported.
-
WiktionaryScraper contains a Python script which fetches English translations of Mandarin words from Wiktionary.