search

Text-to-Audio / Make-An-Audio

PyTorch Implementation of Make-An-Audio (ICML'23) with a Text-to-Audio Generative Model
MIT License
737 stars 107 forks source link

can the project run on windows? #9

Open ZHONET opened 4 months ago

ZHONET commented 4 months ago

i got the bug about nccl when i try to train ,so can i run it on window without nccl

ZHONET commented 4 months ago

@Darius-H

Darius-H commented 4 months ago

i got the bug about nccl when i try to train ,so can i run it on window without nccl

I haven't tried running it on windows. You say there is a problem with nccl, this could be caused by the code for multi-gpu training, maybe you need to remove torch.distributed training.

ZHONET commented 4 months ago

i got the bug about nccl when i try to train ,so can i run it on window without nccl

I haven't tried running it on windows. You say there is a problem with nccl, this could be caused by the code for multi-gpu training, maybe you need to remove torch.distributed training.

我试了试还是不行，我冒昧的请求一下能不能帮我训练一下我的数据集，一个很小的数据集。

ZHONET commented 4 months ago

@Darius-H