
Here is an overview of what we released
Text-to-speech model
Currently the highest-quality synthetic voice for Kinyarwanda.
lnkd.in/dvNtsebd
KinyaCOLBERT Free
The first Kinyarwanda embedding/information retrieval model, essential for building RAG chatbots such as Tunga.
lnkd.in/d2D6HUxH
Voice Dataset
A dataset for training TTS and Speech-to-Text (STT) models.
lnkd.in/dk_Azir8
Information Retrieval Dataset
The data used to train the KinyaColBERT model.
lnkd.in/d5ZEF96D
KinyaBERT
A foundational BERT-style model serving as the backbone for various Kinyarwanda NLP tasks.
lnkd.in/dHuDwMDz
Source Code
All relevant code for the models and datasets mentioned above.
lnkd.in/dTuSd-Vv
English





















