LEXI AI-Powered Captioning Toolkit

Description

The LEXI AI-Powered Captioning Toolkit leverages AI advancements to provide a comprehensive suite covering live and recorded captioning, translation, display, archiving, and search. It includes LEXI Automatic Captioning, delivering AI-powered automatic captions with quality rivalling human captions at a fraction of the cost. LEXI Recorded makes captioning recorded content quick and easy with fully automated, fast turnaround times. LEXI Translate offers efficient and cost-effective solutions for global reach through automatic translation. LEXI Local provides on-premises solutions for live, automatic captions, ensuring elevated security and greater control. LEXI Library offers a caption archive and search tool for easy viewing, searching, editing, and archiving of live captions.

URL

• Visit resource

Related resources

• VQMTK: Video Quality Metrics ToolkitOpen-source cross-platform tool bundling 14 VQA metrics plus SI/TI spatial/temporal indicators, CLI or Jupyter web UI.
• SubalignerAutomatic subtitle synchronization tool using deep neural networks and forced alignment, with translation support.
• Evaluating Video Quality Metrics for Neural and Traditional Codecs (4K/UHD-1)Academic comparison of VMAF, AVQBits, and FasterVQA no-reference quality metrics on 4K content.
• GHVQ: Benchmark and Metric for AI-Generated Human-Activity Video QualityAcademic paper introducing a benchmark dataset and objective quality metric for AI-generated human-activity video, with companion code.
• QCTools Playback Filters (BAVC)Documentation for QCTools histogram, vectorscope, waveform, and CIE scope filters used in archival video quality control.
• CompressedVQA: Full/No-Reference VQA for Compressed UGC VideoICME 2021 grand challenge-winning full-reference and no-reference video quality models for compressed user-generated content.
• Bitrate Ladder Construction via Transfer Learning and Spatio-Temporal FeaturesML-based bitrate ladder optimization achieving 94.1% complexity reduction at only 1.71% BD-rate cost using transfer learning.
• 2BiVQA: Double Bi-LSTM No-Reference Video Quality AssessmentNo-reference VQA model for UGC video using double Bi-LSTM, companion code to arXiv:2208.14774.
• nr-vqa-consumervideoNo-reference video quality metric tuned for consumer video capture artifacts (sensor noise, motion blur, shake) rather than compression art…
• VMAF-torchPyTorch reimplementation of VMAF metric, GPU/gradient-friendly for use in learned codec optimization loops.