These projects focus on developing machine learning models and pipelines for processing and generating Armenian language and cultural data, including speech, text, typography, and music.
Silero Models is a popular open-source repository providing pre-trained text-to-speech models for multiple languages,...
ArmenianWhisper is an open-source summer project focused on creating an AI-powered pipeline for Armenian speech recog...
Master's thesis project comparing LSTM and Transformer models for generating Armenian folk music in MIDI format. Incl...
This repository implements an unconditional Denoising Diffusion Probabilistic Model (DDPM) trained on a custom datase...
This repository implements a machine learning model to convert English phonetic spellings of Armenian words into Arme...
A research project exploring how unsupervised pre-training on untranscribed audio from different language families af...
A tutorial repository for building an Armenian Automatic Speech Recognition (ASR) system using the Kaldi toolkit. It ...
A research project aiming to develop a state-of-the-art Automatic Speech Recognition (ASR) model for the Armenian lan...