FrameReader is a full-fledged service for recognizing text on frames of video materials in Russian, training, deployment of computer vision models to solve the OCR problem. Optimization of models on the tensorrt engine
react mysql tracking computer-vision detection video-annotation yolo donut ocr-recognition video-analysis fastapi triton-inference-server tensorrt-engine trocr
-
Updated
Sep 22, 2025 - JavaScript