Model description

A toy model, trained on toy data generated from spikeinterface.

Intended use

Used to try out the download features of hugging face hub.

How to Get Started with the Model

This can be used to automatically label a sorting in spikeinterface. Provided you have a sorting_analyzer, it is used as follows

from huggingface_hub import hf_hub_download
import skops.io as skio
from spikeinterface.curation import auto_label_units

new_model_path = hf_hub_download(repo_id="chrishalcrow/toy_data_model", filename="best_model.skops")
pipeline = skio.load(new_model_path, trusted='numpy.dtype')

auto_label_units(sorting_analyzer = sorting_analyzer, pipeline = pipeline)

or you can download the entire repositry to a_folder_for_a_pipeline, and use

from spikeinterface.curation import auto_label_units, load_pipeline

pipeline = load_pipeline('a_folder_for_a_pipeline')
auto_label_units(sorting_analyzer = sorting_analyzer, pipeline = pipeline)

Authors

Chris Halcrow