Repo

AMEVA-STT-Trainer

@uno-kmby Eunho Kim · AMEVA Open-Source Foundation

0

A Whisper-based Korean STT trainer featuring LoRA fine-tuning for high-accuracy speech recognition with minimal resources. It offers a full pipeline—from data scraping and audio preprocessing to training, evaluation, and model merging. Optimized for Korean NLP, it’s a ready-to-use toolkit for researchers and developers.

Built withPythonstt

See what other members are building and what each project is looking for.