search

SJTUwxz / LoCoNet_ASD

code repo for LoCoNet: Long-Short Context Network for Active Speaker Detection
16 stars 4 forks source link

预训练权重只能支持说话人为3个的？ #3

Open Yangnengqun opened 1 month ago

SJTUwxz commented 1 month ago

我们模型是用三个讲话人训练的(一个target speaker和两个context speaker）。但是也可以接受不同说话人数量，只要确保最后输入给模型的是三个讲话人。