shihuai

Thank you for open sourcing this project, we are also very interested in your project. Now, we want to fine-tune the model with customized dataset, but there are some problem...

HI, Thank you for your open source work. I am also very interested in your work. Regarding your work, I have a question: When you use Covnext as the image...

Greate work！ I am also very interested in your work. Recently, I tried to reproduce the work on video modality alignment. I used the pre-trained ViT-b32 of OpenAI for initialization....

Pretrain Hubert on english and chinese speech dataset.

6

Hi~I'm trying pretrain hubert from scratch on english and chinese speech dataset. During pretrain, the 1st iteration loss dropped from 6.7 to 3.3, the 2nd iteration loss dropped from 11.2...

模型训练loss变化是什么样的？

16

感谢你们把这么好的工作开源。最近我们的尝试在复现模型的效果，模型一阶段训练loss收敛还可以，但模型二阶段训练过程中loss从12下降到3.0左右，就无法在降低了。所以想问一下，你们当时训练的时候，两个训练阶段的loss是如何变化的，训练过程中有什么需要注意的地方吗？