styletts2/styletts2 · Getting errors in Voice cloning section

Nov 22, 2023

I submitted a voice sample but received an error. Can it be resolved?

  File "/home/user/app/app.py", line 25, in clsynthesize
    return (24000, styletts2importable.inference(text, styletts2importable.compute_style(voice), alpha=0.3, beta=0.7, diffusion_steps=20, embedding_scale=1))
  File "/home/user/app/styletts2importable.py", line 57, in compute_style
    wave, sr = librosa.load(path, sr=24000)
  File "/home/user/.pyenv/versions/3.10.13/lib/python3.10/site-packages/librosa/core/audio.py", line 175, in load
    y, sr_native = __soundfile_load(path, offset, duration, dtype)
  File "/home/user/.pyenv/versions/3.10.13/lib/python3.10/site-packages/librosa/core/audio.py", line 208, in __soundfile_load
    context = sf.SoundFile(path)
  File "/home/user/.pyenv/versions/3.10.13/lib/python3.10/site-packages/soundfile.py", line 658, in __init__
    self._file = self._open(file, mode_int, closefd)
  File "/home/user/.pyenv/versions/3.10.13/lib/python3.10/site-packages/soundfile.py", line 1212, in _open
    raise TypeError("Invalid file: {0!r}".format(self.name))
TypeError: Invalid file: None

mrfakename

StyleTTS 2 Online Demo (Not Affiliated with StyleTTS 2 Authors) org Nov 22, 2023

•

edited Nov 22, 2023

Hi @ysharma , would you mind providing me with several details:

What file type did you upload for the voice cloning (ie mp3/wav/ogg)
What text did you try to make it say?
Did you wait for the file to finish uploading before clicking "Synthesize"

I have tried it and it seems to work for me.

Thank you, and I will try to resolve this soon.

mrfakename

StyleTTS 2 Online Demo (Not Affiliated with StyleTTS 2 Authors) org Nov 30, 2023

Hi @ysharma , is this still an issue?

ysharma

Dec 2, 2023

Hi, thanks for looking into this. This is no longer an issue, sorry I couldn't respond any earlier @mrfakename .

ysharma changed discussion status to closed Dec 2, 2023