Is need text in training corpus or only wav files?

maum-ai / cotatron

Official code for Cotatron @ INTERSPEECH 2020

https://mindslab-ai.github.io/cotatron

BSD 3-Clause "New" or "Revised" License

212 stars 32 forks source link

Is need text in training corpus or only wav files? #7

Open ghost opened 3 years ago

ghost commented 3 years ago

Thanks you!

seungwonpark commented 3 years ago

Both text and audio are required.

ghost commented 3 years ago

Is can mix languages? or English only is supported?

seungwonpark commented 3 years ago

Cross-lingual conversion will be possible if it's trained with a dataset of multiple languages. This repo does not directly support such training strategy, but you'll be able to try that by changing some parts of the code!

ghost commented 3 years ago

I have five chinese speakers, make training is OK. How long each voice should have? How many speaker should have?