The Western Armenian Corpus (Հիմնադարան) is a newly founded initiative aiming at the development of Speech-to-Text (STT) and Text-to-Speech (TTS) engines for Western Armenian speakers around the world.
The initiative has already achieved considerable success in developing the necessary engines for Eastern Armenian, which include Automatic Speech Recognition and Neural Machine Translation. Also, there are endeavors to include Classical Armenian (Գրաբար).
More than 200 volunteers currently operate within two main fields, technical (IT) and recording. The Western Armenian Corpus provides texts from renowned author Shavarsh Misakian for volunteers to read and record themselves for an average of 15-20 minutes only. Others can also read texts according to their preferences.
Educational institutions from the United States, France, Armenia, Artsakh, and Lebanon have already become part of this initiative providing the necessary diversity in tones and dialects to enrich and empower the automated engines.
Anyone interested in participating can visit the website and become part of this innovative project.
Menu
