KevinMIN95 / StyleSpeech

Official implementation of Meta-StyleSpeech and StyleSpeech
MIT License
241 stars 39 forks source link

the audio quality is not good by using HiFi-GAN #14

Open 443127316 opened 2 years ago

443127316 commented 2 years ago

Same as the title, I use the HiFi-GAN vocoder to generate the audio. But there is full of noice in the audio. How could you make the qualified audio as the demo page. Could you pls share some experinece.

Thanks a lot.

hcy71o commented 2 years ago

Following the official code of HiFi-GAN, they inference audio by audio = audio * MAX_WAV_VALUE audio = audio.cpu().numpy().astype('int16') write(output_file, h.sampling_rate, audio)

In my case, it works when I changed the code a little as follow: audio = audio.cpu().float().numpy() write(output_file, h.sampling_rate, audio)