Skip to content

hassonlab/podcast-benchmark

Repository files navigation

Podcast Benchmark

A benchmarking framework for neural decoding from podcast listening data.

Documentation

📚 Full documentation available at: https://hassonlab.github.io/podcast-benchmark/

Quick Start

# Setup environment and download data
./setup.sh

# Train all tasks using the CNN baseline.
make train-all MODEL=baselines/neural_conv_decoder

Features

  • Flexible model architecture: Register custom models with simple decorators
  • Multiple tasks: Word embeddings, classification, or custom prediction targets
  • Configurable training: YAML-based configs with cross-validation and early stopping
  • Multiple metrics: ROC-AUC, perplexity, top-k accuracy, and custom metrics
  • Time lag analysis: Automatically find optimal temporal offsets

Learn More

About

benchmarking project for podcast decoding

Resources

Stars

9 stars

Watchers

1 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors