docs[cv2-8]: CosyVoice2.md reproduction guide + one-command scripts
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 0
- Forks
- 0
- PR merge metrics
- No merged PRs in 30d
Description
Goal
Document the full SPADE-on-CosyVoice2 reproduction process in CosyVoice2.md and provide beginner-friendly scripts so anyone can reproduce from zero.
Acceptance
- CosyVoice2.md: step-by-step Chinese guide (env, data, WLI, prune, distill, averaging, eval, FAQ, artifacts)
- scripts/reproduce_cosyvoice2.sh: one-command driver (with FAST smoke mode + env knobs)
- scripts/download_cosyvoice2_data.sh: resumable data download
- config defaults resolve paths automatically; existing pytest suite passes
- FAST mode verified end-to-end (all 6 stages complete)
Notes
Iteration 8 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 existing CosyVoice2 workflow and config defaults, then outline the stages required by CosyVoice2.md. Add scripts/reproduce_cosyvoice2.sh and scripts/download_cosyvoice2_data.sh, and run the existing pytest suite. Done means the Chinese guide covers all requested topics and FAST mode completes all six stages end to end.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, shell
- Domain
- documentation, machine-learning, testing, tooling
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Clearly specified
- Newbie friendliness
- 52/100