跑的好像收敛了，试听也还行，但是打开程序合成音频效果很差，是不是因为没有解压aidatatang_200zh的数据
Open
- Dominant language
- Python
- Stars
- 36.9k
- Forks
- 5.2k
- PR merge metrics
- No merged PRs in 30d
Description
要不要解压aidatatang_200zh数据之后重新预处理然后训练，我自己的数据有350条，识别出了261条，时长应该有10分钟
前面有一两次损失是0.4附近的
Contributor guide
No contributing guide indexed for this repository
Research direction
No file, test, or entry point is identified. First verify whether aidatatang_200zh is extracted before preprocessing, then compare the resulting training data and audio quality; done means determining whether extraction and reprocessing account for the poor synthesized audio.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- ai, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100