teakettel/hy_transcribe
Playground for testing the quality of speech recognition models for Armenian-language speech
A personal playground repository for testing and comparing Armenian speech recognition models. Contains Jupyter notebooks evaluating Whisper and other ASR models on Armenian audio, with utilities for dataset preparation and transcription quality assessment.
ArmSpeechTT is a fine-tuned Whisper model for Armenian speech-to-text, trained on Common Voice data with a webcam dem...
ArmSpeech is an offline Armenian speech recognition library and CLI tool built on Coqui STT, trained on a 15.7-hour A...
A robust Speech-to-Text (STT) service with multi-provider API integration (Google Gemini, ElevenLabs, Whisper, HiSpee...
A speech-to-text model for Armenian language using Wav2Vec2-BERT, fine-tuned on the Armenian Common Voice dataset. Th...
A full-stack Armenian speech recognition system with React frontend, Spring Boot backend, and Azure deployment. Inclu...
An end-to-end pipeline for Armenian-to-English speech and text conversion, featuring Armenian automatic speech recogn...