I think i am doing something wrong

[dillfrescott]

I tried inferencing with the pretrained checkpoint and the results are just a distorted and low resolution version of the input file :(

I also tried training my own model with the same results so it must be something I'm doing wrong

[ksadov]

Can you share the file that you used as input to the network?

[dillfrescott]

https://transfer.sh/6fXxiObBEV/wishvocals.wav

[pauortegariera]

Hi, sorry for the inconvenience, i need desesperatly the checkpoints of a pretrained model this implementation because i want to do a finetuning. I need help on this please!

[okleochat]

https://transfer.sh/6fXxiObBEV/wishvocals.wav

Did you ever get it right? I am experiencing the same thing.

[dillfrescott]

https://transfer.sh/6fXxiObBEV/wishvocals.wav

Did you ever get it right? I am experiencing the same thing.

no sorry I don't believe I ever did

[dillfrescott]

Also last commit on this repo was 2 years ago. I'm fairly certain its dead. You may want to look for alternative implementations.

[okleochat]

Also last commit on this repo was 2 years ago. I'm fairly certain its dead. You may want to look for alternative implementations.

Oh, Christ. Do you have any suggestions?

[dillfrescott]

I dont sadly. I havent really done much with voice conversion lately