Testing ASR for Video Subtitles
A small Korean-language comparison showed why transcript coverage, timestamps, and manual review matter as much as model output.
Tag
A small Korean-language comparison showed why transcript coverage, timestamps, and manual review matter as much as model output.
A follow-cam design that combines face recognition with person tracking, appearance, pose, segmentation review, and hybrid framing.
A short fraud-detection project helped me revisit class imbalance, Random Forest, SMOTETomek, and precision-recall metrics.