Predict brain responses to video, audio, and text.
Predicts fMRI brain responses from video, audio, and text using TRIBE v2.
When to use it
Use for predicting brain responses to naturalistic stimuli or working with TRIBE v2 inference and training.
Give it video, audio, or text files; it returns predicted brain responses and segment metadata.
What you provide
Requires Python to run the inference examples and training entry points; no version is specified.
Training requires Hugging Face authentication and approved access to LLaMA 3.2.
This skill
HuggingFace
Downloads pretrained model weights
tribev2
Installs TRIBE v2