hdmjdp

machine noise on 4k frequency

8

I encouner a bad case: there is machine soud(a line) in the 4k frequency as below. this is breathing part. I try to solve it, Can you give some advice,...

个人感觉论文大体的思路跟这2篇论文很相似，主要创新是怎么采用小参数的flow保证效果不下降。 不知道作者有没有试过中文的效果，vae+glow模型（vits and glow tts）音调会出现不准的问题（偶现）

How do you train the vocoder? Have you used the GTA training?

what is this

1

https://github.com/CMsmartvoice/One-Shot-Voice-Cloning/blob/091bfefaa34427abad0653621d412a1886a71a58/TensorFlowTTS/tensorflow_tts/models/unetts.py#L69 sheng? yun?

can gen wav in realtime in an A53 chip?

can your offer the log? Epoch 2, loss value is 12, is it right?

https://github.com/jaywalnut310/vits/blob/2e561ba58618d021b5b8323d3765880f7e0ecfdb/models.py#L369 such as and another question, sometimes train used FP16 may cause loss=NaN? How can I fix it? thanks

do your test it in cpu?

1

whether it can run in realtime?

how about the quality of this net

4

Have you got good audio?