Zhengxi Liu (刘正曦)
Zhengxi Liu (刘正曦)
You can refer https://github.com/xcmyz/FastVocoder/blob/main/bin/synthesize.py#L79
> hi, I try and find that the trick could not solve this problem. Because of the random value of synthesized sound in two synthesis, this minus could be "over"....
> Hi, an error occured to me when running preprocess.py with the latest code version. It seems the processing is jammed as shown in the following picture. Have you had...
> It seems because there are torch tensor operations in multi processing. I located that the code came to a deadlock when running the line as shown in the following...
> I saw [history updates](https://github.com/xcmyz/FastSpeech/commit/1f5aa2a33be2e7fab3a9c2fb8666a08c1240bdcc#diff-93ff136fae812392eb0f68d1ce89b7fe) replace the Postnet using CBHG. Is there any speed or performance enhancement after changing the structure? postnet in fastspeech is not necessary
> In my knowledge, postnet is added to enhance the performance of mel output, is CBHG plays the same role? What about remove this module? yes, cbhg is the part...
你可以去检查中文语料alignment的正确性，或者处理音频方式是否一致
> The text feature I used before diff from the origin English version, when I change back to the orgin text feature (one phone-one id), the pronunciation improve much. >...