search

microsoft / SpeechT5

Unified-Modal Speech-Text Pre-Training for Spoken Language Processing
MIT License
1.16k stars 113 forks source link

Can you provide a voice conversion finetune recipe? #12

Closed hpjang closed 2 years ago

hpjang commented 2 years ago

First, Thank you, for your amazing achievements.

I tried asr finetune. It's work well! So, I'd like to do other things too!

Such like voice conversion task!! Can you provide voice conversion finetune and convert recipe??

Ajyy commented 2 years ago

Sure! we plan to release the recipe of voice conversion task recently (about 2~3 weeks). Thanks for your attention.

mechanicalsea commented 2 years ago

Hi, @hpjang VC finetune and convert recipe are available after this commit. The scripts can be helpful to implement VC fine-tuning.

We also provide re-implementation of VC fine-tuned model speecht5_vc.pt and some samples, but with a smaller batch size or max updates, which can be helpful.

Thanks for you attention to our work.