DoubleCake

Results 10 comments of DoubleCake

把配置写好,比如在batchTrain文件夹里写好a.ps1,b.ps1 然后再写个ps1脚本依次运行文件夹里的脚本就行了

I copied the code from inference and replaced modelscope's model loading in gradio.py. So simply adjust it yourself.

When i us wsl in windows10 .I got the same issue. Then I solved this problem by using ubuntu 22.04 。

我遇到了类似的问题,是在提取SSL的时候没有提取到合适的音频文件,导致我在 SoVITS模型训练的时候就报该错。 我想GPT模型训练报这个错误也是这个原因 ![image](https://github.com/RVC-Boss/GPT-SoVITS/assets/23249887/26c18308-654d-43b7-81a3-2dc62332bf02)

> 我遇到了类似的问题,是在提取SSL的时候没有提取到合适的音频文件,导致我在 SoVITS模型训练的时候就报该错。 我想GPT模型训练报这个错误也是这个原因 ![image](https://private-user-images.githubusercontent.com/23249887/297750729-26c18308-654d-43b7-81a3-2dc62332bf02.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.QjMn6brG5ng6f3MHyWL8lW6iQ_zm26MqtCFKjPnfRA4) 使用相同的数据下,4-cnhubert 同样数据为空。 我使用其他的语音素材,这些文件夹中都是有 对应的预处理文件的。并且可以完整的进行训练

> ## 前面的步骤都没问题,SoVITS模型都训练完了,然后点GPT模型训练时出了问题 > "runtime\python" GPT_SoVITS/s1_train.py --config_file "TEMP/tmp_s1.yaml" > Seed set to 1234 > Using 16bit Automatic Mixed Precision (AMP) > GPU available: True (cuda), used: True > TPU available:...

> *\6-name2semantic.tsv 文件里没有正确的内容 请问这个问题主要是哪个环节可能会导致的呢?我的也是6-name2semantic.tsv文件夹是你左边显示的那种空的,然后4和5文件夹是空的。 ![image](https://private-user-images.githubusercontent.com/22678173/297925891-82f3c723-129f-444e-9cc7-223b1999cd7a.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.wJvnkGhFztko_Ux7EwPVFMcOtCmI62RJlAl735dTH_8) 不了解音频处理的逻辑和算法代表的含义,所以我也不太清楚具体的原因,我重新更换了音源暂时避开了这个问题。

> 清理训练任务预处理的结果,然后重新生成数据集格式化文件,注意生成后看看文件对不对。 > > ``` > (GPTSoVits) ➜ first git:(main) ✗ ls -alh > total 36K > drwxr-xr-x 6 daemonzhao users 4.0K Jan 19 10:40 . > drwxr-xr-x 3 daemonzhao...

I only have a 4090. I modified the order in which the models were loaded。 Cuda memory was freed after each phase of computation.

[app_low_varm.zip](https://github.com/TencentARC/InstantMesh/files/15397554/app_low_varm.zip) I hope this helps you. Extract the files to the same directory as app.py and you will be able to use them.