feat[cv2-6]: End-to-end pipeline wiring, real-data results, config defaults
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 0
- Forks
- 0
- PR merge metrics
- No merged PRs in 30d
Description
Goal
Iteration 6 of SPADE-on-CosyVoice2: verify the one-command pipeline (data -> WLI -> prune -> distill -> evaluate), set config defaults that reproduce the reported real-data result, and document it in the README.
Acceptance
-
python -m spade_cosyvoice2.run_pipelineruns all stages and writes pipeline_report.json - README documents the CosyVoice2 flow + real-data result table
- pipeline.yaml defaults reproduce the result (1500 train / 7 epochs)
- Existing pytest suite passes
Notes
Iteration 6 for: SPADE applied to CosyVoice 2 (arXiv:2509.20802)
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the python -m spade_cosyvoice2.run_pipeline entry point and inspect pipeline.yaml for the 1500-train/7-epoch defaults. Read the README and existing pytest suite to understand the CosyVoice2 flow. Done means the command writes pipeline_report.json, the README includes the flow and real-data result table, the defaults reproduce the result, and pytest passes.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- audio-video-rtc, machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 52/100