v3ucn / bert-vits2-v2.3

Bert-vits2-V2.3 训练和推理

              

bert-vits2-v2.3's Issues

short_audio_transcribe.py IndexError: list index out of range

您好，分割完音檔執行下一步驟時一直遇到問題:
python.exe short_audio_transcribe.py
Data/ada\audios/raw
Traceback (most recent call last):
File "D:\AIprojects\Bert-vits2-V2.3\short_audio_transcribe.py", line 81, in
for i, wavfile in enumerate(list(os.walk(parent_dir))[0][2]):
IndexError: list index out of range

煩請協助解決問題，謝謝!

webui调取出错

您好啊，我用你的notebook训练自己的一个声音，跑到最后webui的时候报这个错，是需要修改哪里的配置文件么？谢谢

| numexpr.utils | INFO | NumExpr defaulting to 2 threads.
/usr/local/lib/python3.10/dist-packages/torch/nn/utils/weight_norm.py:30: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.
warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.")
Traceback (most recent call last):
File "/content/Bert-vits2-V2.3.1/webui.py", line 380, in
net_g = get_net_g(
File "/content/Bert-vits2-V2.3.1/infer.py", line 98, in get_net_g
_ = utils.load_checkpoint(model_path, net_g, None, skip_optimizer=True)
File "/content/Bert-vits2-V2.3.1/utils.py", line 66, in load_checkpoint
assert os.path.isfile(checkpoint_path)
AssertionError