Alidaling

> @yaodada1RVC 本身不支持多重训练。对我有用的是设置`hps.model.spk_embed_dim`扬声器数量（在您的情况下为 4），然后`emb_g.weight`用新的替换（因此它开始从头开始训练扬声器嵌入层） - 我通过像这样的简单行来做到这一点`tmp["emb_g.weight"] = nn.Embedding(NUMBER_OF_SPEAKERS, 256).weight.data`： 您想在 train_nsf_sim_cache_sid_load_pretrain.py 中进行这两项更改 "I didn't find the script train_nsf_sim_cache_sid_load_pretrain. Where can I find it? Looking forward to your reply."Thank you！

> 您好~感谢您对我们工作训练的兴趣。 对于数据生成，我们没有CFW，所以我们实际上设置w=0。 此时，只需设置w=1即可。 Okay, thank you very much for your response! To ensure better experimental results, I have three more detailed questions to ask. 1、The first question is about...

Thank you! > You can download test data in https://drive.google.com/drive/folders/1-19UG1Ov2iZ0JMAw0JPuQwj0HsC8c3sJ > > Then generate LR images in https://github.com/XPixelGroup/BasicSR/blob/master/scripts/matlab_scripts/generate_bicubic_img.m