Ethio-ASR 🎙️ Multilingual Speech Recognition for Languages of Ethiopia 🇪🇹

Developed with ❤ by the Ethio-ASR team led by Badr al-Absi, in close collaboration with native speakers who provided continuous feedback and evaluation.

Hi there 👋🏼

This is a demo for a Ethio-ASR, a suite of multilingual Automatic Speech Recognition (ASR) models based on connectionist temporal classification (CTC) decoding for the languages of Ethiopia. The supported languages are Amharic, Tigrinya, Afaan Oromo, Sidama, and Wolaytta.

Simply upload an audio file 📤 or record yourself speaking 🎙️⏺️ to try out the model!