Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

1B微调训练和ASR中的报错麻烦处理一下 #1915

Closed
AkebiKomichi opened this issue Jan 3, 2025 · 1 comment
Closed

1B微调训练和ASR中的报错麻烦处理一下 #1915

AkebiKomichi opened this issue Jan 3, 2025 · 1 comment

Comments

@AkebiKomichi
Copy link

1.SOVITS训练无法进行,报错如下:
-- Process 0 terminated with the following error:
Traceback (most recent call last):
File "G:\GPT_Sovits\御坂美琴\GPT-SoVITS-v2-240821\runtime\lib\site-packages\torch\multiprocessing\spawn.py", line 69, in _wrap
fn(i, *args)
File "G:\GPT_Sovits\御坂美琴\GPT-SoVITS-v2-240821\GPT_SoVITS\s2_train.py", line 86, in run
train_dataset = TextAudioSpeakerLoader(hps.data) ########
File "G:\GPT_Sovits\御坂美琴\GPT-SoVITS-v2-240821\GPT_SoVITS\module\data_utils.py", line 103, in init
assert len(audiopaths_sid_text_new) > 1 # 至少能凑够batch size,这里todo
AssertionError

"G:\GPT_Sovits\御坂美琴\GPT-SoVITS-v2-240821\runtime\python.exe" GPT_SoVITS/s1_train.py --config_file "G:\GPT_Sovits\御坂美琴\GPT-SoVITS-v2-240821\TEMP/tmp_s1.yaml"

image

image

2.GPT训练也无法进行,报错如下:
File "G:\GPT_Sovits\御坂美琴\GPT-SoVITS-v2-240821\GPT_SoVITS\AR\data\dataset.py", line 190, in init_batch
for _ in range(max(2, int(min_num / leng))):
ZeroDivisionError: division by zero

image

3.音源是纯日语的,在Faster Whisper中选择V3large,单精度,如果选择自动语言会默认成中文。已经选择了日文,反复复现上述SOVITS和GPT训练中的错误,大概10月份的版本中没有这样的错误。

image

@RVC-Boss
Copy link
Owner

RVC-Boss commented Jan 6, 2025

日文训练要求训练集完整路径和整合包完整路径都不能包含中文或空格

@RVC-Boss RVC-Boss closed this as completed Jan 6, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants
@RVC-Boss @AkebiKomichi and others