Moonmore
Moonmore
> RuntimeError: cannot reshape tensor of 0 elements into shape [0, 39, -1] because the unspecified dimension size -1 can be any value and is ambiguous 我也碰到这个一摸一样的问题，按照@ranchlai 的做法没得到解决，请问你现在解决了吗？
> sure. Pls leave me you email or wechat wechat is smileMoonmore, please.
> Hi @Moonmore > Please check the training voice, it should be 22050Hz, 1 channel (mono) and 16 bit-depth. I refer to the aishell3 dataset used by the author. Then...
> i have same problem Refactoring the code.
I solved this problem. The cause of this problem is caused by the python environment. Similarly, pipreqs is installed in /path/to/pipreqs, but after switching to the virtual environment or conda...
> Thanks @Moonmore for the comment. > > I was not using an environment. Maybe I should. If you don't have an environment to use, but have multiple python versions....
> 如何保证数据不包含低质量的tts数据，以及考虑高质量的tts数据来进行更好的覆盖，这两个事情都比较重要，现在网络上低质量tts数据太多了 我们之前尝试过DeepFakeDetection检测合成的数据，效果还挺好的，TTS的数据这个可以检测到。
请问下后续有开放模型的训练和优化的计划吗 =-=
> @Moonmore Could you run the newest version on Windows platform? I compiled the previous version, haven't tried the latest version yet.