qoherent/icc-demo
21
0
Fork 1
Code Issues Pull Requests Workflows Packages Projects Releases Wiki Activity
ICC demo workspace: recordings, curated datasets, training workflows
4 Commits 1 Branch 0 Tags 116 MiB
Python 100%
Push Tracker
Go to file

Push Tracker

ash pushed to main at qoherent/icc-demo 2026-05-28 11:52:06 -04:00
673323b155 Training run - 2026-05-28 11:52:05
ash pushed to main at qoherent/icc-demo 2026-05-28 11:52:06 -04:00
673323b155 Training run - 2026-05-28 11:52:05
ash pushed to main at qoherent/icc-demo 2026-05-28 11:52:06 -04:00
673323b155 Training run - 2026-05-28 11:52:05
ash pushed to main at qoherent/icc-demo 2026-05-28 11:52:06 -04:00
673323b155 Training run - 2026-05-28 11:52:05
ash pushed to main at qoherent/icc-demo 2026-05-28 11:52:06 -04:00
673323b155 Training run - 2026-05-28 11:52:05
Files 5 items
R Roman Pope 501a8c5e1c
Some checks are pending
WavesFM Fine-Tuning / WavesFM-Training (push) Waiting to run
Details
Add adapt_dataset.py + re-trigger training canary 
Previous run (2577) was waiting; missing scripts/adapt_dataset.py.
Adds the WAC-side adapter so the workflow's actions/checkout@v5
sparse-checkout finds the file at /scripts/adapt_dataset.py.
2026-05-28 01:48:03 -04:00
.riahub/workflows Add adapt_dataset.py + re-trigger training canary 2026-05-28 01:48:03 -04:00
scripts Add adapt_dataset.py + re-trigger training canary 2026-05-28 01:48:03 -04:00
.gitattributes Initialize ICC demo workspace with LFS tracking + README 2026-05-28 01:35:31 -04:00
icc_canary_2026_05_28-v1.0.0.h5 Radio Dataset Add canary dataset: icc_canary_2026_05_28 v1.0.0 (3 recs, 144 slices) 2026-05-28 01:40:55 -04:00
README.md Initialize ICC demo workspace with LFS tracking + README 2026-05-28 01:35:31 -04:00

README.md

ICC Demo Workspace

Recordings, curated datasets, and training workflows for the WavesFM ICC presentation.

Workflow

  1. Upload recordings — drop .sigmf-data + .sigmf-meta pairs. Git LFS tracks them automatically via .gitattributes.
  2. Curate — open the Curator UI, select recordings from this repo, configure slicer + qualifier, produce an HDF5 dataset.
  3. Commit dataset — use the Curator's "Commit to Repository" button to land the curated .h5 back here.
  4. Train — open the Model Trainer, select this repo + WavesFM Linear Probe (or LoRA), pick the dataset, submit the run.
  5. Watch action_run — the trainer renders .riahub/workflows/train.yaml and triggers a runner job. Progress lives under the Actions tab.

Notes

  • WavesFM foundation model: qoherent/wavesfm-base/wavesfm-v1p0.pth — injected into the workflow automatically.
  • If you upload a binary format not in .gitattributes, add it BEFORE the first commit of that file (LFS can't retroactively un-track).