ZJ-CAI
ZJ-CAI
作者你好,请问在哪可以下在ppg2mel.yaml? > > 你好,我想问一下ppg提取的预训练模型作者是在librispeech上训练的,并不是纯中文的,如果去做中文的迁移是需要重新训练嘛,谢谢 > > 不重新训练也可以用的,但是效果一般般
@dosu-bot, If i`d like to use self.create_blob_message() to show the audio player in the front page , what will the arguments be? Can you give me an example? As the...
@dosu-bot how to use self.create_blob_message() to show the audio player in the frontpage?
@nakasako Hey dude, has your issue been solved yet?
10 hours seems to be a little too long. I used 2-hour one-speaker dataset and get a good result with 270K step(batch size 16). Maybe the quality of your dataset...
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117 先把之前安装的torch torchvision torchaudio 都删了,然后试试用上面这个命令安装torch
@adelacvg 请问我自己录一段2分钟左右的音频,把这2分钟音频和开源的AiShell数据集还有原神数据集放一起训练,能否让我的声音得到好的效果?谢谢
> @ZJ-CAI 其他音色转到你的音色会有比较好的效果,你的音色转到一些集外音色还要看训练集大小。想要更好的集外泛化性可以尝试训练v4模型。 明白了,谢谢老哥