search

tiberiu44 / TTS-Cube

End-2-end speech synthesis with recurrent neural networks
https://tiberiu44.github.io/TTS-Cube/
Apache License 2.0
225 stars 45 forks source link

how to synthesize from melspectogram directly without using encoder #32

Closed saibharani closed 5 years ago

saibharani commented 5 years ago

can we synthesize directly from melspectrogram without using encoder

tiberiu44 commented 5 years ago

Hi,

You can use the vocoder here: https://github.com/ksw0306/ClariNet

It has the same format, so you can use my pretained 16khz model.

Best, Tibi

saibharani commented 5 years ago

while synthesizing using clarinet repo mentioned above using your pretrained model which file should we use synthesize.py or synthesize_student.py and if it is synthesize_student.py what should we give for the argument --teacher-name thank you

tiberiu44 commented 5 years ago

synthesize_student