jinhan / tacotron2-vae Goto Github PK

This project looks very interesting, could we have a pretrained model, please?
I couldn't download the dataset from the link you provided because I never receive the confirmation number when I register to the website with my student email.
Thanks for your kind attention.

Thank you for this amazing implementation. Everything is working perfectly except I wasn't able to figure out how to select speakers during inference (I have trained with 5 speakers).

Any hints would be really appreciated!

Hi.
I am exploring about speed of training and inference different multi speaker TTS models on single CPU and on singe GPU.
Thanks for any explanation in this case for current model or any other models of multi speaker TTS.

Can I ask that in your language you are using, Korean, the input you are using is phoneme or Korean words?
Because I am trying to use phoneme in my language, Do you have any suggestions for me!

Excuse me，in u code, i found you also used the english dataset — IEMOCAP，the format like this:
/home/jinhan/Storage/IEMOCAP/IEMOCAP_processed/session4_M/neu/psn4M_neu_s212_orgn.wav|whose is it|7|0
/home/jinhan/Storage/IEMOCAP/IEMOCAP_processed/session3_F/neu/psn3F_neu_s497_orgn.wav|eight pieces of luggage okay|4|0

Cloud you share the wav file and the transcript of them,i have some problem about processing the orignal dataset, my email is :[email protected], hope the answer！ Thanks very much！