README.md

metadata

title: Marlin 2B Video Understanding
emoji: 🎬
colorFrom: blue
colorTo: indigo
sdk: gradio
sdk_version: 6.10.0
app_file: app.py
short_description: Dense video captions and timestamp search
python_version: '3.10'
startup_duration_timeout: 1h
models:
  - NemoStation/Marlin-2B

Marlin 2B Video Understanding

ZeroGPU Gradio Server demo for NemoStation/Marlin-2B, a 2B video VLM for dense video captioning and natural-language temporal grounding.

The app exposes two model-card workflows:

• Caption: returns Marlin's parsed scene paragraph plus timestamped events.
• Find: resolves an event query into a parsed start/end time span.

The model is loaded once at module startup. Inference runs through Gradio Server @app.api endpoints backed by ZeroGPU, and the custom frontend turns timestamped results into a synced video timeline.