Deon

@bayartsogt-ya the storage bucket used to pull the Mongolian Bible dataset no longer has the Mongolian version available for download. if you still has a copy of the original .zip...

> I found that when there is only ONE speaker in training dataset, when I changed the batch_size = 16 * num(GPU), the result wavform would contains some noise like...

> @yyggithub I do not realy know the reason. But I noticed that HifiGAN MelDataset "shuffle" is down on multi-GPU training. On torch distributed multi-GPU training method, traning process on...

> 我用自己微调的模型，去推理目标文字时，发现会有一些小片段会不读或者重复读的情况；觉得是不是微调有问题，后面直接用基准模型去推理，发现也是一样的。有人有碰到类似问题吗，哪里可以寻找其他基准模型？ 我发现了跟你一样的问题呢？有啥解决方案吗？