ZixuanNi
ZixuanNi
> In my case, there might be the problem with g++ and the compiler Pytorch was built. Seems like Pytorch was built with clang++ by default, and ctcdecode extension was...
Using torch 1.31.1+cu161 can solve this.
So, has the DER implementation with mask been released? Thanks.
> > > after full training, i use zero_to_fp32.py convert *.pt to *.safetensors, when inference, i load the model, I also not report the log: No wan_video_dit models available. We...