Open yygg678 opened 1 year ago
1,音色泄漏应该没有吧,可以用发布的模型进行测试,模型使用56个发音人训练 2,不支持语音转换,但是支持用语音数据训练歌声转换
用发布的模型进行测试,singer0001 唱高音时破音了,音高pitch是1000多,针对这种情况,有什么好的方法吗?
https://github.com/PlayVoice/lora-svc/blob/main/svc_preprocess_f0.py#L13 模型训练的时候,设置了最高音为900,需要根据您的实际数据修改这个参数来训练模型
https://github.com/PlayVoice/lora-svc/blob/main/svc_preprocess_f0.py#L13 During model training, the highest pitch is set to 900. You need to modify this parameter according to your actual data to train the model
how do you find the highest pitch in your model and how do you find the number to use (eg. 900) that the pitch corresponds to in order to modify the parameter
@yygg678 请问你实际对比操作了不,该方法和Diff-svc, so-vits-svc对比效果如何?
@yygg678 请问你实际对比操作了不,该方法和Diff-svc, so-vits-svc对比效果如何? 看数据集吧,我数据集比较脏,so-vits-svc 好些,diff-svc 没有试试