Thuy Tran

> @ljj7975 What do you mean about second filtering?

@leminhnguyen Hello, I'm interested in your experiment in Vietnamese task. Have you ever compared the synthesized audio quality made by VITS to FastSpeech2? If yes, which one do you think...

@leminhnguyen Thanks. Mis-puntutation in ur case means bad duration or tone issues? Btw, can I ask you more personally in private email or other chat platforms?

> > 光改参数没用的，代码里也有。原作者的preprocessor.py 172行要改成wav, _ = librosa.load(wav_path, self.sampling_rate)，因为没参数的话还是默认22050 read的 > > 天哪，非常感谢。这个地方还真没注意到。我立马调整一下。 还有一个问题，想要问一下大神。我用标贝数据训练了模型，训练epoch约150。模型合成出来的语音，前半段还可以听。后半段完全没法听。不知道大神能不能指点一下。下面是我的语音： [哈尔滨今天晴，十度到二十二度，南风三级，空气质量良。.zip](https://github.com/ming024/FastSpeech2/files/7646156/default.zip) > > 语谱图在这：  非常期望大神指点一二 @Tian14267 Hi, I faced the same problem with yours. My audio...

Do you have plan to implement Text to speech models?