Views
No views yet
1from tribev2 import TribeModel
2
3model = TribeModel.from_pretrained("facebook/tribev2", cache_folder="./cache")
4
5df = model.get_events_dataframe(video_path="path/to/video.mp4")
6preds, segments = model.predict(events=df)
7print(preds.shape) # (n_timesteps, n_vertices)text_path or audio_path to model.get_events_dataframe — text is automatically converted to speech and transcribed to obtain word-level timings.pip install -e .pip install -e ".[plotting]"pip install -e ".[training]"tribev2/grids/defaults.py directly):1export DATAPATH="/path/to/studies"
2export SAVEPATH="/path/to/output"
3export SLURM_PARTITION="your_partition"huggingface-cli loginread access token and paste it when prompted.python -m tribev2.grids.test_run1python -m tribev2.grids.run_cortical
2python -m tribev2.grids.run_subcorticaltribev2/
├── main.py # Experiment pipeline: Data, TribeExperiment
├── model.py # FmriEncoder: Transformer-based multimodal→fMRI model
├── pl_module.py # PyTorch Lightning training module
├── demo_utils.py # TribeModel and helpers for inference from text/audio/video
├── eventstransforms.py # Custom event transforms (word extraction, chunking, …)
├── utils.py # Multi-study loading, splitting, subject weighting
├── utils_fmri.py # Surface projection (MNI / fsaverage) and ROI analysis
├── grids/
│ ├── defaults.py # Full default experiment configuration
│ └── test_run.py # Quick local test entry point
├── plotting/ # Brain visualization (PyVista & Nilearn backends)
└── studies/ # Dataset definitions (Algonauts2025, Lahner2024, …)1@article{dAscoli2026TribeV2,
2 title={A foundation model of vision, audition, and language for in-silico neuroscience},
3 author={d'Ascoli, St{\'e}phane and Rapin, J{\'e}r{\'e}my and Benchetrit, Yohann and Brookes, Teon and Begany, Katelyn and Raugel, Jos{\'e}phine and Banville, Hubert and King, Jean-R{\'e}mi},
4 year={2026}
5}