search

fatchord / WaveRNN

WaveRNN Vocoder + TTS
https://fatchord.github.io/model_outputs/
MIT License
2.14k stars 698 forks source link

The version of librosa #155

Open sih4sing5hong5 opened 5 years ago

sih4sing5hong5 commented 5 years ago

I installed with pip install -r requirements.txt and ran gen_tacotron.py got

Traceback (most recent call last):
  File "gen_tacotron.py", line 165, in <module>
    wav = reconstruct_waveform(m, n_iter=args.iters)
  File "/WaveRNN/utils/dsp.py", line 110, in reconstruct_waveform
    S = librosa.feature.inverse.mel_to_stft(
AttributeError: module 'librosa.feature' has no attribute 'inverse'

The librosa version of requirements.txt is 0.6.3. I found some comments about this

The module librosa.feature.inverse was introduced in version 0.7

Is there any side effect if upgdating the version of librosa?

fatchord commented 5 years ago

Thanks for the heads up. I'll have a look at this when I get the time. Cheers!