Lucas Hideki Ueda

icon indicating an email [email protected]

icon company Unicamp | RECOD.ai | CPQD icon location Campinas - SP , Brazil icon location Ph.D student in Expressive TTS, focusing on inductive bias in acoustic model architecture. I like random projects and challenges, this is what u will see here.

Results 4 comments of Lucas Hideki Ueda

🐸 TTS roadmap

Are you guys planning to develop some expressive TTS architectures? I'm currently studying this topic and planning to implement some of them based on Coqui, part of them just controlling...

🐸 TTS roadmap

> @lucashueda Capacitron VAE: #510 Oh nice, hope to see Capacitron integrated soon. So maybe, in the future I'll be able to contribute with some others expressive architectures

can the pre-trained hubert-soft or discrete model be used for encoding mandarin Chinese language data ?

I have experimented transfering to portuguese data and it worked

Can you share the training scripts?

Try to follow the acoustic-model repository (the lik is in the readme), I was able to train in a very straight forward way