Summerxu86
Summerxu86
在gen_voice.py最后合成音频时报了这个错误: RuntimeError: CUDA error: out of memory CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1....
下载的aidatatang_200zh.tgz数据集,在pre.py预处理之后,进行生成器训练。下面是部分图:   step=155000⬆  step=143000⬆ 总觉得不对劲,这种情况是正常的吗?若不正常应该如何处理?
我想请问一下,MockingBird相比于SV2TTS,具体新增了哪些部分内容,可以进行中文数据集的预处理,导入以及最终的合成讷?非常需要您的帮助,谢谢!!!
When you can publish the code? Thanks
Hello, if we want to realize Aishell3 Chinese multi-person dataset, which part should be changed?
After training, PhnCls Loss and SpkCls Loss are both very high with almost no attenuation. When reasoning, given the target speaker's voice, but the timbre is not the same. You...