Search
Now showing items 1-10 of 90
Format Normaliser 1.0.
(North-West University; Centre for Text Technology (CTexT), 2015-01-30) ~ - Resource Index
Normalises input files to txt, utf8, replaces smart quotes with straight quotes, removes empty lines, etc.
NCHLT Optical Character Recognition for South African Languages
(North-West University; Centre for Text Technology (CTexT), 2017-02-23) ~ - Resource Catalogue
An OCR system is an application that enables one to convert scanned paper documents into editable and searchable texts. The engine analyses the structure ...
Setswana multi-speaker TTS corpus
(MuST, NWU, 2018-02-28) ~ - Resource Index
The aim of this corpus was to investigate the implementation of a high-quality TTS system using multiple voices recorded using a low-cost process (i.e. ...
Fannie Sebolela Oral Corpus
(Department of African Languages - University of Pretoria, 2015-01-27) ~ - Resource Index
Tape recordings and transcriptions of 13 mother tongue speakers. Transcribed orthographically.
UNISA Multilingual Corpus
(University of South Africa, 2018-02-28) ~ - Resource Index
The resource comprises a diverse selection of TEI P5 marked up documents from institutional origin, written in Tswana, Afrikaans and English. This is ...
Openphone Health Helpline (vApr 2008)
(Meraka Institute, CSIR, 2013-07-01) ~ - Resource Index
A telephone-based IVR service (DTMF access) for providing health-related information on various topics such as medication, nutrition, hygiene, common ...
NCHLT Tagger
(North-West University; Centre for Text Technology (CTexT), 2016-04-29) ~ - Resource Catalogue
A graphical user interface and command line tool to automatically annotate running text with one or more linguistic tags:\n* Part of Speech\n* Named ...
Phonetic aligner
(Meraka Institute, CSIR, 2013-07-01) ~ - Resource Index
Scripts for automatic phonetic alignment of speech corpora using hidden markov models (HMMs).
South African Fonts
(Translate.org.za, 2015-01-28) ~ - Resource Index
The South African fonts collection is a set of open fonts that cover all characters needed by all 11 South African languages. The fonts ensure that all ...
NCHLT South African Language Identifier
(North-West University; Centre for Text Technology (CTexT), 2016-04-29) ~ - Resource Catalogue
A graphical user interface and command line tool to automatically classify a document, paragraph, sentence or phrase as one of the eleven official South ...