训练VOCODER问题
Open
- Dominant language
- Python
- Stars
- 36.9k
- Forks
- 5.2k
- PR merge metrics
- No merged PRs in 30d
Description
按照作者说方法训练VOCODER，自动生成的两个码器
DO的完全电流杂音。G可以用，但是G和G2500没分别？
这样情况是正常的吗
请问VOCODER怎么算训练好了？
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reviewing the author's VOCODER training method and the reported outputs from the two generated encoders, including G and G2500. Reproduce the training result if possible, then determine whether the electrical noise and lack of visible difference indicate a failed training run or expected behavior, and document how training completion is judged.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100