收敛效果问题
Open
- Dominant language
- Python
- Stars
- 36.9k
- Forks
- 5.2k
- PR merge metrics
- No merged PRs in 30d
Description
目前运行了50小时左右 Step255k
运行起来仍然是胡言乱语的状态
总共识别14000条降噪语音 自己检查了差不多3000条
现在的loss是在0.42-0.44之间徘徊
请问这个效率是正常的还是有些出问题呢
(plot看起来是对角线居多)
看到有一些成品100-200k就已经差不多了
Contributor guide
No contributing guide indexed for this repository
Research direction
No files, tests, or entry points are named. Start by reviewing the training configuration and logs for the reported 50-hour, 255k-step run, then inspect generated samples and the loss plot. Done means determining whether the loss and output quality are expected or identifying a reproducible training problem.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- ai, machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100