profile
viewpoint

Ask questionsAfter steps from README.md for getting audio: ModuleNotFoundError: No module named 'librosa'

$ python3 inference.py -f <(ls mel_spectrograms/*.pt) -w waveglow_old.pt -o . --is_fp16 -s 0.6
Traceback (most recent call last):
  File "inference.py", line 30, in <module>
    from mel2samp import files_to_list, MAX_WAV_VALUE
  File "/home/vitaly_zdanevich/waveglow/mel2samp.py", line 38, in <module>
    from tacotron2.layers import TacotronSTFT
  File "/home/vitaly_zdanevich/waveglow/tacotron2/layers.py", line 2, in <module>
    from librosa.filters import mel as librosa_mel_fn
ModuleNotFoundError: No module named 'librosa'
NVIDIA/waveglow

Answer questions rafaelvalle

This is probably related to your setup, not the repo.

useful!

Related questions

No questions were found.
source:https://uonfu.com/
answerer
Rafael Valle rafaelvalle http://rafaelvalle.github.io/ My research focuses on machine listening and improvisation. During my PhD at Berkeley I was advised mainly by Sanjit Seshia and Edmund Campion.
Github User Rank List