Kinyarwanda TTS: Using a multi-speaker dataset to build a Kinyarwanda TTS model

Samuel Rutunda, Kleber Kabanda, Adriana Stan

Keywords: TTS, text to speech, low-ressrouces language, kinyarwanda, bible

TL;DR: We use a multi-speaker bible dataset to create kinyarwanda TTS model

Abstract: The field of text-to-speech (TTS) technology has been rapidly advancing in recent years, and has become an increasingly important aspect of our lives. This presents an opportunity for Africa, especially in facilitating access to information to many vulnerable socio-economic groups. However, the lack of availability of high-quality datasets is a major hindrance. In this work, we create a dataset based on recordings of the Bible. Using an existing Kinyarwanda speech-to-text model we were able to segment and align the speech and the text, and then created a multi-speaker Kinyarwanda TTS model.