MilenAyvazyan/azure-armenian-speech-transcription
This repository documents a research project evaluating Azure AI Speech Services for Armenian audio transcription, focusing on accuracy with standard Armenian and regional dialects (Yerevan slang, Gyumri dialect). It includes analysis of Azure's capabilities, model comparisons (including Whisper Large V2), and considerations for data security and custom model training.
A full-stack Armenian speech recognition system with React frontend, Spring Boot backend, and Azure deployment. Inclu...
ArmSpeech is an offline Armenian speech recognition library and CLI tool built on Coqui STT, trained on a 15.7-hour A...
ArmSpeechTT is a fine-tuned Whisper model for Armenian speech-to-text, trained on Common Voice data with a webcam dem...
A personal playground repository for testing and comparing Armenian speech recognition models. Contains Jupyter noteb...
A speech-to-text model for Armenian language using Wav2Vec2-BERT, fine-tuned on the Armenian Common Voice dataset. Th...
A robust Speech-to-Text (STT) service with multi-provider API integration (Google Gemini, ElevenLabs, Whisper, HiSpee...