训练vocoder会自动停止
Open
- Dominant language
- Python
- Stars
- 36.9k
- Forks
- 5.2k
- PR merge metrics
- No merged PRs in 30d
Description
训练vocoder，在3000 epoch以后每次训练几个就会自动停止，没有任何报错信息
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reproducing vocoder training beyond 3000 epochs and record the training configuration, environment, and the point at which it stops. Compare the run with the screenshot and determine whether the stop is reproducible without an error; done means identifying a cause and verifying that training continues normally.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100