Jason's Lab

I met the same issue not solve yet. If anybody know how to work well please leave your method. Thank you very much.

Hi, I met the same problem and tried to fix it according to the 2nd solution in https://github.com/tensorflow/tensorflow/issues/29911#issuecomment-505688141 but it didn't work the bug is here. Traceback (most recent call...

> Hi, > > We didn't use LM during decoding. If you want to use a language model, you can follow [the fairseq LM instructions](https://github.com/facebookresearch/fairseq/tree/main/examples/language_model) for training. Thank you for...

Thank you for your reply. I think maybe the reason why the result of AV-HuBERT I trained didn't surpass A-HuBERT in your paper is that I used 8 A-100 for...

Hi I pretrained AV-HuBERT in LRS3 by appending optimization.update_freq=[4] still using 8 GPUs. The epoch number changes to 275 from 69. The 1st iteration costs 102 hours and after finetuning...

This is the config file I used in the 1st pretrain iteration. Is this the right file to use in the 1st iteration? https://github.com/facebookresearch/av_hubert/blob/main/avhubert/conf/pretrain/base_lrs3_iter1.yaml I first used 10% of trainset...

> Yes. It is the correct config file for 1st iter in LRS3 pretraining. Hi, thanks for your reply. I have a question about pertaining. After I finish the 1st...

我也遇到了同样的问题，请问找到解决方法了吗

把auto_gptq版本更新到github上的最新版本就可以了，他们解决了这个问题