[Bug] Failed running pretrained Models

[ghost]

Hi, i am on Arch Linux, with latest versions of Python and pip. I installed the TTS package with this command: pip install TTS. And by default it made a user installation in the .local folder. So i left it installing everything And everything was installed successfully.

So now, i ran this command just like in the demo video of the docs in order to test things out: tts —text “This is a Demo” —model_name tts_models/en/ljspeech/glow-tts —out_path test.wav

So as expected it downloaded both the model and the vocoder. However at the end of the install there was this error: zipfile.BadZipFile(“File is not a zip file”)

So i tried running it again and now it showed a different error: FileNotFoundError: no such file or directory: ‘/home/user/.local/share/tts/vocoder_models—en—ljspeech—multiband-melgan/config.json’

Now every time i try it gives the same error. It is also worth mentioning that if i list the models, the models shows as downloaded.

So any help ?

[erogol]

Can't replicate the error.

• Try the latest version of 🐸 TTS v0.1.2
• Try removing the downloaded models and re-run the commands.

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. You might also look our discussion channels.