Add explanatory tooltips for Examples

Add sample audio and Gradio examples UI

Add Hugging Face Space metadata to README

updated screenshots

Transition model pipeline and data generator to purely English-only and display audio transcription in UI

Add robust exception handlers for audio/video processing and clear instructions for system FFmpeg PATH issues

Configure app for cloud deployment (Hugging Face Spaces, auto-training, system packages)

Restore detailed README with clean formatting

Update README to be minimal

Initial commit