Add demo link to README for showcasing Marquee functionality

Refactor code structure for improved readability and maintainability

Remove loading screen implementation and related logic from Marquee

Enhance Gradio backend detection and loading screen management in marquee.js

Refactor code structure for improved readability and maintainability

Remove max_model_len parameter from Orpheus model initialization and simplify prompt in generate_orpheus function

Add GPU decorator to Orpheus generation function and improve logging message

Update README and requirements; add new tags and include orpheus-speech dependency

Refactor face detection and tracking in faces.py; optimize performance by reducing redundant detections and using a dictionary for track lookups. Update OpenVINO model usage and remove unused models. Enhance logging for better visibility.

Add export functionality for broadcast as MP4 with progress indication

Enhance API generation with retry logic for GPU errors and implement session restoration for user convenience

Refactor TTS WAV encoding to use standard library; remove torchaudio dependency

Remove Dockerfile and update README to reflect SDK change; implement chatterbox-tts installation in app.py to avoid dependency conflicts

Switch SDK from Gradio to Docker for improved dependency management and add Dockerfile for deployment

Integrate Chatterbox TTS for audio commentary generation and enhance video playback with synchronized voiceovers

Remove outdated debugging spots from README for clarity and relevance

chores

Refactor commentary and event selection logic for improved clarity and performance

Update Gradio version to 6.18.0 in requirements.txt and README

Update Gradio version in requirements.txt to 6.5.1

Update dependencies and refactor backend to use gradio.Server with ZeroGPU support

Update short description in README for clarity

Add OpenVINO face models, video normalization, and Qwen multimodal model

initial commit

Duplicate from gradio-templates/chatbot