Skip to content

A project that analyzes character archetypes in TV shows and movies using BERT.

Notifications You must be signed in to change notification settings

l-newbould/bert-archetype-classification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 

Repository files navigation

ArchetypeAI

A project that analyzes character descriptions and classifies them into 12 archetypes in TV shows and movies using BERT.

Using the Hugging Face Transformers library, the project fine-tunes the distilbert-base-uncased model to achieve high accuracy and deploy a robust classification pipeline.

Features

  • Fine-tune a pre-trained model (distilbert-base-uncased) for text classification.
  • Hyperparameter optimization using Optuna.
  • Deploy model with Gradio.

Installation

To set up this project, ensure the following packages are installed.

transformers (4.47.1) datasets (3.2.0) numpy (1.26.4) optuna (4.1.0) torch (2.0.1)

About

A project that analyzes character archetypes in TV shows and movies using BERT.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published