armenian-nlp

This repository contains the complete reproduction code for the research paper "From Zero to Hero: An Open LLM Ecosys...

Ar-Lex Graph is a multi-agent Graph-RAG system designed for statutory interpretation of Armenian law. It constructs a...

ArmTriage AI is a clinical safety-focused medical navigation system designed for the Armenian healthcare ecosystem. I...

ArmBench-LLM is a specialized evaluation framework for benchmarking large language models on Armenian language tasks....

ArmBench-TextEmbed is a specialized Python benchmark for evaluating the performance of text embedding models on the A...

A Western Armenian NLP augmentation layer designed to improve LLM output quality by providing structured linguistic d...

This repository presents a benchmark for evaluating multilingual sentence embedding models on a real-world task: cros...

A web application for finding Armenian rhymes using IPA phoneme similarity analysis with feature-aware algorithms. It...

A voice AI customer support agent for Armenian banks that uses LiveKit for real-time audio, OpenAI Whisper for Armeni...

An end-to-end voice AI customer support agent for Armenian banks that understands and speaks Eastern Armenian. It use...

A project for parsing and structuring Armenian addresses from raw text, featuring a Flask web interface for manual an...

A real-time voice AI customer support agent for Armenian banks, built with the open-source LiveKit Agents framework. ...

A voice assistant for Armenian banks that uses LiveKit for real-time audio, scrapes bank websites for data, employs R...

A project to create a bilingual Western Armenian-English large language model using QLoRA fine-tuning on Qwen 2.5 1.5...

A Python package for collecting, processing, and normalizing a Western Armenian language corpus. It provides a full E...

An end-to-end Voice AI customer support agent for Armenian banks that understands and speaks Armenian, using LiveKit ...

This repository contains a political science research project comparing machine learning methods for classifying gove...

A Retrieval-Augmented Generation (RAG) system designed to answer questions about Armenian Labor Law in Armenian. It i...

A speech-to-text model for Armenian language using Wav2Vec2-BERT, fine-tuned on the Armenian Common Voice dataset. Th...

An Armenian-language voice assistant for banking queries that integrates LiveKit for real-time audio and Google Gemin...

A voice AI customer support agent for Armenian banks that answers queries in Armenian using a RAG pipeline over bank ...

An Armenian-language voice AI customer support agent for banking, using LiveKit for real-time audio, OpenAI models fo...

ArmGPT is a student-friendly implementation of a GPT language model specifically trained on Armenian text. It's built...

An implementation of Hidden Markov Models for Part-of-Speech tagging, specifically designed for the Armenian language...

A research project focused on improving NLP for the low-resource Armenian language by analyzing tokenizer inefficienc...

Python training pipeline for an Armenian text recogniser built around synthetic data generation, CTC model training, ...

An end-to-end voice AI customer support agent for Armenian banks, built with the open-source LiveKit framework. It un...

A detailed Python/Windows terminal application for live Armenian-to-English call transcription using local speech rec...

A local real-time Armenian-to-English call transcriber for macOS that captures microphone and system audio, performs ...

A Python Telegram bot for transcribing voice messages and audio/video files using swappable local ASR engines such as...

A Python macOS terminal tool for live Armenian-to-English transcription and translation of Zoom calls, using local sp...

Live Armenian-to-English speech translator for the terminal that captures microphone and system call audio, transcrib...

hy-bridge is a Windows Python CLI that performs real-time Armenian speech transcription and English translation from ...

Decoder-only Armenian GPT trained from scratch on ArmWeb and Wikipedia corpora, with BPE tokenization, notebooks for ...

A local CPU-only Windows terminal application for live Eastern Armenian to English call translation. It combines micr...

A local Windows-based real-time Armenian speech transcription and English translation tool that captures microphone a...

A small GPT model trained from scratch to generate Armenian poetry in the style of poet Paruyr Sevak. The project doc...

A project exploring Armenian language autocomplete using multiple NLP approaches including Word2Vec, LSTM, BERT trans...

A voice AI agent for Armenian bank customer support using LiveKit OSS. It scrapes official Armenian bank websites (Am...

A voice AI customer support agent for Armenian banks that uses LiveKit to process Armenian speech, retrieve bank info...

A voice AI agent for Armenian banking queries using LiveKit for real-time audio, OpenAI Whisper for Armenian speech-t...

An AI-powered system for analyzing scanned Armenian newspapers using computer vision (YOLO for section detection, Ope...

A Python package for clustering and deduplicating Armenian news articles using NLP and machine learning techniques. I...

A pipeline for Armenian Named Entity Recognition (NER) and network analysis. Downloads Armenian text data, preprocess...

A student project implementing multiple tokenization methods (BPE, WordPiece, SentencePiece, tiktoken) for Armenian l...

An Armenian-language voice AI assistant for bank customer support, specialized in answering queries about loans, depo...

A real-time Armenian voice AI agent for banking customer support, built with LiveKit for WebRTC communication. It use...

A voice AI customer support agent for Armenian banks that provides real-time voice interaction in Armenian. It uses L...

A specialized voice AI agent for Armenian banks that handles Armenian-language queries about credits, deposits, and b...

MediaSanitar is a hybrid AI system for automated credibility assessment of news articles, combining Selenium web scra...

A portfolio project demonstrating a fully offline, local voice AI receptionist system for Armenian dental clinics. It...

A machine learning project for classifying Armenian news articles into politics, culture, and sport categories. It in...

A Python terminal application for live Armenian-to-English speech transcription and translation using local models, s...

Armenian Live Transcriber is a local Python pipeline that captures microphone and system audio, segments speech, tran...

A local Windows terminal prototype that captures microphone and system audio, transcribes Armenian speech, translates...

A curated list of Armenian language datasets, corpora, models, and digital resources for NLP and computational lingui...

A Western Armenian language model project using transformer architecture, implemented in Jupyter notebooks. Includes ...

A Telegram bot that classifies Armenian news articles into four categories (Political, Social, Educational, Health) u...

hy-text is an open-source reference tool for evaluating and ensuring text quality in modern Eastern Armenian for AI a...

AzgIntel is an AI-powered NLP pipeline for Armenian text classification using a BERT-based multilingual model. It pro...

A small NLP project that trains classifiers to distinguish between Eastern and Western Armenian dialects using Wikipe...

An Armenian-language voice AI assistant for banking support, answering questions about credits, deposits, and branch ...

A Python-based OpenClaw skill that monitors Armenian Telegram channels for power/water outage announcements. It scrap...

A web application built with Next.js that translates Modern Literary Armenian (Grakan) to Classical Armenian (Grabar)...

A machine learning project for detecting AI-generated text in Armenian. It includes a custom dataset, fine-tuned tran...

A research project exploring machine learning approaches for detecting loanwords in Armenian and predicting their lan...

A dataset of 30,000 Armenian news articles scraped from websites, categorized into six topics (Army, Political, Econo...

A translated version of the DailyDialog dataset into Eastern Armenian, formatted as sequential sentence pairs (input/...

A dataset containing 100,000 Armenian sentences, formatted as a CSV or text file, intended for training and evaluatin...

An OCR project for Armenian handwritten text using the Mashtots dataset, implemented in TensorFlow/Keras and trained ...

A Python project that extracts and visualizes character co-occurrence networks from Armenian literary texts. It uses ...

A complete pipeline for training Word2Vec embeddings on Armenian text, including data preprocessing, model training w...

A demonstration repository for a pre-trained Armenian text embedding model, showcasing applications in text classific...

A Python tool for sentiment analysis on Armenian literary texts from the Eastern Armenian National Corpus (EANC). It ...

A capstone project evaluating GPT-3.5-Turbo's performance on Armenian language tasks, including extractive QA, multip...

A Python library for transliterating Armenian text written in Latin script (Romanized Armenian) back to the Armenian ...

A thesis project analyzing Armenian political discourse on Twitter using NLP techniques including sentiment analysis,...

An Armenian-language voice AI agent for banking information, using LiveKit for real-time voice processing, Groq for A...

A BiLSTM-based text classification system for mapping Armenian/Latin retail product names to ADG codes (brand categor...

A BiLSTM-based text classification system for mapping Armenian/Latin retail product names to ADG codes (brand/industr...

A training repository for a workshop on lightweight NLP models for under-resourced languages, specifically Armenian. ...

A Streamlit web application that uses Groq's LLM API to provide simplified, plain-language Armenian explanations of A...

A small character-level GPT trained on Armenian Wikipedia, implemented in PyTorch with data preparation, training, sa...

An experimental community initiative providing writing guidelines and skills to improve the quality, naturalness, and...

This repository provides a ~181k English–Armenian parallel sentence dataset for machine translation, hosted on Huggin...

A curated list of 316 Armenian stopwords for NLP text preprocessing, provided as a JSON file with usage examples for ...

A product overview for an AI-assisted workspace designed to organize, review, and analyze Armenian-language lending d...

A Python tool for Armenian speech-to-text conversion and task extraction from transcribed text. It records Armenian s...

A Streamlit web application for scraping e-commerce reviews (Amazon, Ozon, etc.) and performing sentiment analysis on...

Personal portfolio repository for Sona Mansuryan, an AI/ML Engineer and NPUA graduate specializing in Computer Vision...

A Python web scraping tool that fetches synonyms and definitions for Armenian words from the bararan.ru online dictio...

An experimental autocorrect engine specifically for the Armenian language, aiming to improve accuracy and typing expe...