whisper

A fast CPU-first video/audio transcriber for generating caption files with Whisper and CTranslate2, hosted on Hugging Face Spaces.

AOI: a model-agnostic perception layer giving computer-use agents adaptive video + audio perception with zero retraining, plus DynaCU-Bench (100 dynamic browser tasks). Paper + benchmark + code.

EduMIND — Multimodal Bilingual Lecture Assistant with Anti-Forget RAG, Whisper ASR, VietMix NMT (CMI-aware), and Human-in-the-Loop Active Learning via Label Studio. Built for code-mixed Vietnamese–English academic environments.

A voice assistant with local LLM as a backend

Perl Framework for AI - Langertha - the viking of AI

Synthetic data augmentation technique via LLM for Automatic Speech Recognition fine tuning.