DiffSinger

DiffSinger copied to clipboard

Please Add requirements_4090.txt File

1

Please Add requirements_4090.txt File

djt-dev

用A卡怎么训练

2

mengdalida

IndexError: index 0 is out of bounds for axis 0 with size 0

1

大佬，我在执行CUDA_VISIBLE_DEVICES=0 python tasks/run.py --config usr/configs/lj_ds_beta6.yaml --exp_name lj_ds_beta6_1213 --reset --infer时报如下错误，是什么原因呢？我的环境是win10+python3.8+cuda11.5 

huajian197

Inference audio generated at higher speed than training files

4

Finally, after a lot of labor, I got a decent English singer out of the model, which is great. But the audio generated during inference consistently plays back about 1.3...

firelex

RuntimeError: index 155 is out of bounds for dimension 1 with size 155

5

I try to run training on my dataset. Valid data is processed correctly and this error does not occur at this stage. But when training data is used, a RuntimeError...

ElizavetaSedova

请问训练的batchsize怎么设置呢？

he-shuwei

如题

Aionrichman

什么叫声学模型？ 什么叫唱法模型？这两个模型是什么关系？

1

小白不明白。我也看过相关的文字和视频，但我还是不明白。谁能把这些基本的事情解释清楚吗？非常感谢！ 如上，声学和唱法模型都要做吗？还是只做一个就行，最佳实践是什么呢？ 原文中有这样一段话： 简单地说，歌唱模型的输出是具有可用于声学模型推理的歌唱参数的DS文件。 因此，在训练变奏曲歌唱模型之前，训练声学模型进行模型推理 更加困惑 我认为这是一个伟大的项目，非常感谢大家！

liangcaihua

Hi, I really appreciate your work and now I'm going to train the model on [this](https://github.com/MoonInTheRiver/DiffSinger/blob/master/docs/README-SVS-opencpop-cascade.md) pipeline. My issues are as follows: 1. I note that you have adapted the...

X-Drunker

我发的数据集申请邮件没人回复

1

wlf0322