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

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.

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

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