Orthographically transcribed broadband speech corpus of approximately 56 hours, including a test suite of 8 speakers.

Orthographic and phonemically aligned transcriptions

General phonemic pronunciations for frequently occurring words in SA languages. Dictionaries were developed to be practically usable for speech technology ...

Lwazi is a robust telephony platform aiming to facilitate speedy development of experimental applications without sacrificing power by combining Asterisk ...

Morphological decomposer developed during the NCHLT Text project.

An OCR system is an application that enables one to convert scanned paper documents into editable and searchable texts. The engine analyses the structure ...

Part of speech taggers developed during the NCHLT Text project. Available for the following languages: Afrikaans, English, isiNdebele, isiXhosa, isiZulu, ...

Phrase chunk annotated data for the NCHLT Text Resource Development: Phase II Project. The phrase chunk annotated data is a subset of the 50,000 tokens ...

Named entity annotated data from the NCHLT Text Resource Development: Phase II Project, annotated with PERSON, LOCATION, ORGANISATION and MISCELLANEOUS tags.

A graphical user interface and command line tool to automatically classify a document, paragraph, sentence or phrase as one of the eleven official South ...