---
language: en
tags:
  - cinematic
  - music-generation
  - movie-scripts
  - multi-task
license: apache-2.0
---

# Cinematic Music Descriptor — Module 3 – Music Descriptor Heads

Multi-head MLP that takes Module2 context vectors and predicts all music descriptors for a scene: tempo, tonality, orchestration, etc.

## Label Schema

### Regression
- **tempo_bpm**: 45–170 BPM
- **musical_valence**: -0.93 to 0.68

### Classification
- **tonality**: ['atonal', 'major', 'minor']
- **harmonic_style**: ['atonal', 'chromatic', 'cluster', 'diatonic', 'modal', 'pentatonic', 'whole_tone']
- **dynamic_shape_m4**: ['crescendo', 'diminuendo', 'flat', 'subito_forte', 'subito_piano', 'sustained', 'swell', 'terraced']
- **rhythm_style**: ['drive', 'off', 'ostinato', 'pulse', 'rubato', 'sparse']
- **texture**: ['ambient', 'chamber', 'full', 'hybrid', 'solo']

### Multi-label
- **orchestration**: ['ambient_pad', 'brass', 'choir', 'electronic', 'ethnic', 'guitar', 'harp', 'organ', 'percussion', 'piano', 'solo_voice', 'strings', 'synth', 'woodwinds']


## Training Details

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

## Usage

```python
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.