feat[1]: 项目脚手架与 LJSpeech 数据预处理流水线
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1
- Forks
- 0
- Avg merge
- 1m
- Merged PRs (30d)
- 1
Description
Goal
建立 DSFlow 的可安装 Python 工程骨架，并实现 LJSpeech 数据预处理：文本音素化（g2p-en，字符级回退）、梅尔谱提取、带比例时长对齐的数据集与 DataLoader。
Acceptance
- pyproject.toml 与依赖清单存在，pip install -e . 可安装
- 预处理模块能下载/解压 LJSpeech 并产出 mel + 音素序列缓存
- 数据集类可迭代返回 (text_tokens, durations, mel) 批次
- pytest 冒烟测试通过
- 不依赖 espeak-ng
Notes
Iteration 1 for: DSFlow 双监督 + 步感知单步流匹配语音合成
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 project scaffold and pyproject.toml, then locate the preprocessing module and dataset/DataLoader entry points described in the issue. Run the pytest smoke tests while checking LJSpeech download, mel and phoneme caching, duration alignment, and editable installation. Done means the listed acceptance checks pass without espeak-ng.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- data, machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 38/100