⚡ Bolt: Cache ML models in memory

[benpiper]

💡 What: Added functools.lru_cache(maxsize=1) to globally cache the Whisper and RVM models in processor.py and background_remover.py.
🎯 Why: To prevent severe performance bottlenecks from repeated disk loading of large ML models during video processing.
📊 Impact: Significantly reduces processing time for subsequent runs or segment processing by keeping models in memory.
🔬 Measurement: Run a video processing job twice; the second run will skip model loading time.

---

PR created automatically by Jules for task 955085447385949111 started by @benpiper

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

---

For security, I will only act on instructions from the user who triggered this task.