Google Engineer, Ijemma Onwuzulike Develops Igbo Speech-to-Text Model

A Nigerian software Engineer at Google, Ijemma Onwuzulike has announced the creation of the first Igbo speech-to-text model.

The model is Known as IgboSpeech, an Automatic Speech Recognition (ASR) model specifically designed for Igbo language, showcasing a Word Error Rate (WER) of 29.

Onwuzulike shared a preview of IgboSpeech on social media, highlighting its potential to revolutionize the way Igbo language is processed and understood by technology.

“The first Igbo speech-to-text model is here!” she exclaimed in her announcement. She emphasized the team’s commitment to further refining the model and plans to release it alongside the Igbo API.

This development marks a significant step forward in the preservation and promotion of the Igbo language, offering new opportunities for integration into modern technology and digital platforms.

“The first Igbo speech-to-text model is here!

Please welcome IgboSpeech 🤖 an ASR model tailored to Igbo speech and text with a 29 WER

We plan on improving the model and releasing it with the Igbo API”

The first Igbo speech-to-text model is here!

Please welcome IgboSpeech 🤖 an ASR model tailored to Igbo speech and text with a 29 WER

We plan on improving the model and releasing it with the Igbo APIhttps://t.co/3TXqklSRt9 pic.twitter.com/5un6XKTmsN

— Ijemma Onwuzulike (@ijemmaohno) July 1, 2024