v3ucn / bert-vits2_v202_train Goto Github PK

Please what is the torch version of this project?

我将预训练模型放到 ’Data\keqing\models‘， 然后开始训练会报 models:Loaded checkpoint 'Data\keqing\models\DUR_0.pth' (iteration 0)
loaded state dict contains a parameter group that doesn't match the size of optimizer's group

然后又生成了新的预训练模型
Evaluating ...
INFO:models:Saving model and optimizer state at iteration 1 to Data\keqing\models\G_0.pth
INFO:models:Saving model and optimizer state at iteration 1 to Data\keqing\models\D_0.pth
INFO:models:Saving model and optimizer state at iteration 1 to Data\keqing\models\DUR_0.pth
50it [02:01, 1.09s/it]INFO:models:Train Epoch: 1 [54%]
INFO:models:[2.4450833797454834, 2.5289080142974854, 10.062331199645996, 19.771923065185547, 2.0650529861450195, 2.132744550704956, 50, 0.0001]
Evaluating ...
INFO:models:Saving model and optimizer state at iteration 1 to Data\keqing\models\G_50.pth
INFO:models:Saving model and optimizer state at iteration 1 to Data\keqing\models\D_50.pth
INFO:models:Saving model and optimizer state at iteration 1 to Data\keqing\models\DUR_50.pth

这会有影响吗？

python .\transcribe_genshin.py
Data\keqing\raw
Enter a letter to choose language.

C = Chinese ; J = Japanese ;E = English;
e.g: C

Enter language: C
Data\keqing\raw\keqing
588it [00:17, 33.03it/s]
Traceback (most recent call last):
File "G:\AI\audio\Bert-VITS2_V202_Train-main\transcribe_genshin.py", line 94, in
with open(config.preprocess_text_config.transcription_path, 'w', encoding='utf-8') as f:
FileNotFoundError: [Errno 2] No such file or directory: 'Data\keqing\filelists/short_character_anno.list'

How did this directory "Data/keqing/filelists" come from? It's not included in the project