suyashnpande/cinematic-music-descriptor-module2

Cinematic Music Descriptor — Module 2 – Cross-Scene Context Transformer

4-layer transformer trained from scratch over sequences of Module1 scene vectors. Learns narrative arc, pacing flow, and scene-to-scene transitions.

Label Schema

Classification

• narrative_arc_position: 5 classes (Setup/Rising/Climax/Falling/Resolution)
• foreshadowing_type: 4 classes
• transition_type: 5 classes

Regression

• scene_valence_continuous: -1.0 to 1.0
• tension_level: 1–10
• arousal_level: 1–10

Training Details

• Base model: roberta-base
• Dataset: ~11,000 scenes from 60–80 movies
• Framework: PyTorch + HuggingFace Transformers
• Logging: Weights & Biases

Usage

import torch
from huggingface_hub import hf_hub_download

# Download weights
path = hf_hub_download(repo_id="suyashnpande/cinematic-music-descriptor-module3",
                       filename="module3.pt")

Citation

If you use this model, please cite the project.