Hi everyone, I'm a new member of the group. Glad to have read the detailed instructions in the README and the previous discussions. I completed the voice training after 3 steps:
Step 1: train with tacotron2
Step 2: train flowtron with n_flows=1 and warmstart with tacotron2 model
Step 3: continue with n_flows=2
The results are quite good, the sound is easy to understand (with me and some my friends).
I'm doing the emotional transfer(style_transfer) but the quality is very poor (The sound doesn't sound natural, doesn't feel right).
I have tried with both the flowtron_ljs model for English and my model for Vietnamese.
Can someone who has completed this process give me some suggestions?
Thanks a lot.
@rafaelvalle Please help me and give me some advice.
Hi everyone, I'm a new member of the group. Glad to have read the detailed instructions in the README and the previous discussions. I completed the voice training after 3 steps:
The results are quite good, the sound is easy to understand (with me and some my friends). I'm doing the emotional transfer(style_transfer) but the quality is very poor (The sound doesn't sound natural, doesn't feel right). I have tried with both the flowtron_ljs model for English and my model for Vietnamese.
Can someone who has completed this process give me some suggestions? Thanks a lot.
@rafaelvalle Please help me and give me some advice.