Eleanor456
Eleanor456
the result obtained by eval_model or synthesis is much worse than which is obtained by train process
> 您正在使用哪些数据集和预设？ Chinese datasets with 61 speakers, and the preset I have modified according to the deepvoice3_vctk.json
the result obtained by eval_model or synthesis is much worse than which is obtained by train process
> What frontend selected? > I'm trying to train on spanish speakers and the results are a litte gibberish, but not noise. I convert the transcript to pinyin form, so...
the result obtained by eval_model or synthesis is much worse than which is obtained by train process
> Shouldn't be so noisy. This is what i get with 40000 steps on 13 speaker dataset. >  > > es frontend, so no phonetics dictionary This is the...
请问您解决这个问题了么
请问你解决了这个问题嘛
请问这个问题解决了吗，我也遇到了这个问题
请问各位知道怎么训练了嘛
My batch size is set to be 1. But the version of DALI is 0.11.0. ------------------ Original ------------------ From: Janusz Lisiecki ***@***.***> Date: Tue,Dec 28,2021 5:58 PM To: NVIDIA/DALI ***@***.***>...
> Hi > The output has been through nms layer. Invalid boxes will be filled with 0 and cls_id will be filled with -1. But all the value of my...