Joseph Sefara's repositories
AfricanWordNet
AfricanWordNet: Implementation of WordNets for African languages. Citation paper "Practical Approach on Implementation of WordNets for South African Languages" https://www.aclweb.org/anthology/2021.gwc-1.3.pdf
yoruba-gender-recognition
Development of Yorùbá gender recognition system.
AI_ML_Workshops
AI_ML_Workshops
automatic-pronunciation-assistant
To be uploaded.
Flite-TTS-Engine-for-Android
Port of the Festival-lite (Flite TTS) speech-synthesis engine to Android
language-detection
Automatically exported from code.google.com/p/language-detection
preprocessor
Elegant and Easy Tweet Preprocessing in Python
projecteuler
Solutions for projecteuler
PythonTest
Small python programs that I wrote to pass the test.
smart_open
Utils for streaming large files (S3, HDFS, gzip, bz2...)
SpeechTech-ChatBot
A chatbot developed by SpeechTech SA for under-resourced languages.
tts-lid
Text-to-speech (TTS) synthesis systems are of benefit towards learning new or foreign languages. These systems are currently available for various major languages but not available for low-resourced languages. Scarcity of these systems may lead to challenges in learning new languages specifically low-resourced languages. Development of language-specific systems like TTS and Language identification (LID) have an important task to address in mitigating the historical linguistic effects of discrimination and domination imposed onto low-resourced indigenous languages. This paper presents the development of a multi-language LID+TTS synthesis system that generate audio of input text using the predicted language in four South African languages, namely: Tshivenda, Sepedi, Xitsonga and IsiNdebele. On the front-end, is the LID module that detects language of the input text before the TTS synthesis module produces output audio. The LID module is trained on a 4 million words dataset resulted with 99% accuracy outperforming the state-of-the-art systems. A robust method for building TTS voices called hidden Markov model method is used to build new voices in the selected languages. The quality of the voices is measured using the mean opinion score and word error rate metrics that resulted with positive results on the understandability, naturalness, pleasantness, intelligibility and overall impression of the system of the newly created TTS voices. The system is available as a website service.
Voice-Emotion-Detector
Voice Emotion Detector that detects emotion from audio speech using one dimensional CNNs (convolutional neural networks) using keras and tensorflow on Jupyter Notebook.
what-if-tool
Webpage/demos for the What-If Tool