This repository focuses on leveraging OpenAI's Whisper model for speech recognition in Chinese (Mandarin) and Taiwanese Hokkien languages. It includes tools and scripts for data preprocessing, model training, and evaluation, tailored to improve speech recognition accuracy for these languages.
Taiwanese Hokkien (Taigi) speech-to-text transcriber - MediaTek Breeze-ASR-26 with faster-whisper, tuned for RTX 3050 4GB low-VRAM GPUs. Gradio UI, CLI, Docker, SRT/VTT/TXT/JSON.
