Not too bad even just using the base model
https://huggingface.co/metavoiceio/metavoice-1B-v0.1
demo here https://ttsdemo.themetavoice.xyz/
Settings: stability 4 similarity 3
sample used: https://voca.ro/1ivZKXmuIYJ7
result: https://voca.ro/1o7XshzTQTCV
Interesting! I still have way better results with MRQ and my trained models (I have a challenging speaker though, with lots of nuances in his voice), but it's still better than all the open source other tools I've tested until now. Thanks for sharing!
Can't wait to tweak into finetuning because the base model is quite good already as you say.
Interesting! I still have way better results with MRQ and my trained models (I have a challenging speaker though, with lots of nuances in his voice), but it's still better than all the open source other tools I've tested until now. Thanks for sharing!
Can't wait to tweak into finetuning because the base model is quite good already as you say.
Not too bad even just using the base model
https://huggingface.co/metavoiceio/metavoice-1B-v0.1
demo here https://ttsdemo.themetavoice.xyz/
Settings: stability 4 similarity 3
sample used: https://voca.ro/1ivZKXmuIYJ7
result: https://voca.ro/1o7XshzTQTCV
Interesting! I still have way better results with MRQ and my trained models (I have a challenging speaker though, with lots of nuances in his voice), but it's still better than all the open source other tools I've tested until now. Thanks for sharing!
Can't wait to tweak into finetuning because the base model is quite good already as you say.