feat[cv2-1]: CosyVoice2 integration skeleton, setup script, and smoke inference
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 0
- Forks
- 0
- PR merge metrics
- No merged PRs in 30d
Description
Goal
Iteration 1 of SPADE-on-CosyVoice2: scaffold the integration package, script the environment setup (CosyVoice upstream repo + deps + pretrained checkpoint), and verify the official CosyVoice2 checkpoint loads and performs zero-shot synthesis.
Acceptance
-
spade_cosyvoice2/package exists with path/config helpers -
setup.shprepares CosyVoice upstream, Python deps, and downloads CosyVoice2-0.5B (modelscope, with HF fallback) -
smoke.pyloads CosyVoice2 and synthesizes one zero-shot utterance to a wav (exit 0) - Existing pytest suite still passes
Notes
Iteration 1 for: SPADE applied to CosyVoice 2 (arXiv:2509.20802 Table 1: 24 -> 12/9 layers + distillation)
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 by inspecting the existing repository and pytest suite, then map the required spade_cosyvoice2/ package, setup.sh, and smoke.py entry points. Implement the package scaffolding, environment and checkpoint setup, and zero-shot synthesis smoke path described in the acceptance criteria. Done means the smoke script exits 0 and the existing pytest suite still passes.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, shell
- 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
- 50/100