CorentinJ / Real-Time-Voice-Cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time
Other
52.53k stars 8.78k forks source link

Link to the `synthesizer.pt` from default_model.py is broken #972

Closed daniil-lyakhov closed 2 years ago

daniil-lyakhov commented 2 years ago

Greetings! Can't launch demo_cli.py due to broken link to the default synthetizer checkpoint:

https://github.com/CorentinJ/Real-Time-Voice-Cloning/blob/master/utils/default_models.py#L11

https://www.dropbox.com/s/r37koa6ho5prz7w/synthesizer.pt?dl=1

image

Workaround: have downloaded checkpoint from here

CorentinJ commented 2 years ago

Thanks for reporting. Yeah dropbox won't let me keep this public link this size with this much traffic. Google drive doesn't allow for direct download for files larger than 100mb. I tried to split the file in parts at some point but eventually gave up on that idea.

Rishi0812 commented 2 years ago

Solved the issue! Check out https://github.com/CorentinJ/Real-Time-Voice-Cloning/pull/1030