OCR Time Machine
π
67
Extract text from images and XML files using OCR models
A humble space for trying EGTTS V0.1
Extract text from images or PDFs into Markdown
Track, rank and evaluate open Arabic LLMs and chatbots
Apply the motion of a video on a portrait
Benchmark and compare Arabic tokenizers with live leaderboard
Extract and label True/False answers from scanned images
Segment objects in images or videos using text prompts