About Yorlect
Yorlect is a cutting-edge research lab dedicated to advancing the fields of speech technology, natural language processing and machine learning for all Yoruba Dialects. Our objective is to give digital footprint to all dialectal forms of Yoruba language given them the opportunity to compete in the field of machine learning and artificial intelligence.
We are a community of linguists, computer scientists and researchers with passion to preserve and advance Yoruba dialectal forms in machine learning and artificial intelligence. Our team brings expertise from linguistics and computer science to collaborate and create high-quality datasets and tools for the Yoruba dialects.
Available Datasets
High-quality, curated datasets for advancing Yoruba language technology
Speech Recognition
Native Yoruba speech recordings with transcriptions for ASR model training.
Text Corpus
Annotated text samples for NLP tasks including translation and sentiment analysis.
Parallel Translation
Yoruba-English parallel corpus for machine translation research and development.
Our Mission
To give digital footprint to all dialectal forms of Yoruba language, enabling them to compete in the field of machine learning and artificial intelligence through open research, high-quality datasets, and collaborative innovation.
Bridging the Technology Gap
Yoruba is spoken by over 40 million people, yet it remains underrepresented in language technology. We are creating the datasets and tools needed to change that.
Preserving Cultural Heritage
By advancing Yoruba language technology, we help preserve and promote Yoruba culture for future generations through digital means.
Research Focus Areas
Our research spans multiple domains of language technology
Speech Technology
Developing automatic speech recognition, text-to-speech synthesis, and speaker identification systems for Yoruba language and its dialects.
- Building ASR models for Yoruba with support for multiple dialects
- Developing natural-sounding TTS systems using neural networks
- Creating speaker identification systems for forensic and security applications
Natural Language Processing
Building NLP tools for Yoruba dialects including machine translation, sentiment analysis, and named entity recognition.
- Developing Yoruba-English machine translation systems
- Creating named entity recognition systems for information extraction
Machine Learning
Models and frameworks specifically designed for Yoruba dialects and low-resource languages.
- Adapting multilingual models for Yoruba dialects using transfer learning
- Optimizing models for resource-constrained environments
- Developing few-shot learning techniques for low-resource scenarios
Our Team
A dedicated group of researchers, linguists, and technologists working to advance Yoruba language technology
Yusuf Ismail Abayomi
Founder/Language Data Manager
Linguistics graduate and researcher dedicated to preserving and promoting Yoruba language in the digital space.
Joy Naomi Olusanya
NLP/ML Lead Engineer
Leading NLP research for low-resource languages with expertise in text and speech processing.
Kehinde Husseinah
Human Resources Manager
Dynamic HR professional skilled in recruitment, employee relations, and people development.
Owolabi Ridwan Adesola
Data Manager
Linguistics alumnus with expertise in collating and preserving African language data for research.
Oladosu Oluwamayowa Olamide
Web Developer
Building innovative web solutions and user interfaces for Yoruba language technology platforms.
Ogundipe Olulowo Adebayo
Product Designer & Creative Strategist
Crafting intuitive digital products and compelling brand experiences with design thinking and strategy.