Go to file
2025-05-16 14:04:20 -04:00
.riahub/workflows released the binary to riahub, deleted the whl folder under the repo, added requirements.txt to download dependencies 2025-05-16 14:00:27 -04:00
recordings Track .npy and recordings/ in Git LFS 2025-05-16 11:24:52 -04:00
scripts formatted code, added setup.py file to install packages 2025-05-16 11:31:37 -04:00
.gitattributes added LFS tracking to the .whl files 2025-05-16 13:23:13 -04:00
.gitignore Ignore virtual environment folder 2025-05-15 09:44:20 -04:00
README.md Add ReadME 2025-05-14 15:36:31 -04:00
requirements.txt Revised the requirements.txt file 2025-05-16 14:04:20 -04:00

RIA Hub Technical Demo

This repository demonstrates a full ML pipeline via Gitea Actions:

  • Recordings
    A collection of raw .npy radio recordings stored via Git LFS.

  • Workflows
    A CI pipeline that automatically:

    1. Builds a labeled dataset from raw recordings
    2. Trains a model on that dataset
    3. Optimizes the model and packages an inference application
  • Scripts

    • scripts/build_dataset.sh
      Reads through recordings/, applies preprocessing, and outputs training .npz or .csv files into data/.
    • scripts/train_model.sh
      Consumes data/, trains a PyTorch model, and writes checkpoints to checkpoints/.
    • scripts/build_app.sh
      Takes the best checkpoint and builds a small inference CLI or server in dist/.