search

fatchord / WaveRNN

WaveRNN Vocoder + TTS
https://fatchord.github.io/model_outputs/
MIT License
2.13k stars 698 forks source link

Question about function melspectrogram() #29

Closed stevepear closed 5 years ago

stevepear commented 5 years ago

Hi - I tried your alternate model, and it worked good easily, so I am thankful for your work. But I noticed the output of your melspectrogram() function clips to 1.0 often on LJSpeech data. (Of course, it might be my bad implementation). But also it seems the code is similar to keithito/tacotron. In Keith's version he later changed one line to S = _amp_to_db(_linear_to_mel(np.abs(D))) - hparams.ref_level_db in response to an "issue" sent in by Rafael Valle. I wonder whether this difference was intentional or not, (or maybe not relevant). Thanks.

fatchord commented 5 years ago

@stevepear Nice catch, thanks. I think that's what was messing up my attempts at using mu-law.