[Bug]:

[anakein]

Project Version

lastest version 3.2.8

Platform and OS Version

windwos 10 64bit

Affected Devices

all

Existing Issues

No response

What happened?

Only when i use pretrained models. same in all pretrained models issue

Using HiFi-GAN vocoder
Starting training...
Loaded pretrained (G) 'rvc\models\pretraineds\pretraineds_custom\G_Snowie-X-Rin_40k.pth'
Loaded pretrained (D) 'rvc\models\pretraineds\pretraineds_custom\D_Snowie-X-Rin_40k.pth'
Process Process-1:
Traceback (most recent call last):
File "D:\Applio\env\lib\multiprocessing\process.py", line 314, in _bootstrap
self.run()
File "D:\Applio\env\lib\multiprocessing\process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "D:\Applio\rvc\train\train.py", line 548, in run
train_and_evaluate(
File "D:\Applio\rvc\train\train.py", line 663, in train_and_evaluate
wave = commons.slice_segments(
File "D:\Applio\rvc\lib\algorithm\commons.py", line 65, in slice_segments
ret[i] = x[i, :, idx_str:idx_end]
RuntimeError: The expanded size of the tensor (12800) must match the existing size (0) at non-singleton dimension 1. Target sizes: [1, 12800]. Tensor sizes: [0]

Steps to reproduce

...

Expected behavior

start training

Attachments

No response

Screenshots or Videos

No response

Additional Information

No response

[blaisewf]

you are not using v3.2.3

[anakein]

git pull yesterday. 3.2.8, sorry

[AznamirWoW]

Something is not right with your slicing / selected sample rate /etc

[blaisewf]

git pull yesterday. 3.2.8, sorry

not 3.2.8, probably main branch

[anakein]

Something is not right with your slicing / selected sample rate /etc

without pretrained models work fine.

[anakein]

The problem appears when you select a subdirectory, when the previous directory also has audio files. The solution is to move the files to a new directory.