训练vocoder的hifigan时出错
Open
- Dominant language
- Python
- Stars
- 36.9k
- Forks
- 5.2k
- PR merge metrics
- No merged PRs in 30d
Description
训练vocoder的hifigan时出错，好像是显存爆了，这咋解决？我看readme中说改batch_size，但是改的好像是wavernn的batch_size，我改了wavernn下的hparams.py，把batch_size改成6，一样提示爆了，这咋解决？
报错图如下
Contributor guide
No contributing guide indexed for this repository
Research direction
The report points to HiFi-GAN training, README guidance, and wavernn/hparams.py; start by locating which HiFi-GAN configuration owns batch_size and reproduce the CUDA out-of-memory error. Done means the correct setting is identified and the README or configuration is corrected so training fits the available GPU memory.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- ai, machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100