Issues
- 3
- 1
- 1
Feature Request
#44 opened by ChrisDelClea - 4
Include pre-trained models
#1 opened by JRMeyer - 1
Transition agent in forward attention
#47 opened by narendranp - 4
Keeping prosodic features of reference Speaker
#41 opened by jucasansao - 2
> They are my prepared training list.
#43 opened by JeffC0628 - 1
Fine-tuning help
#38 opened by leonardw86 - 26
- 2
assignment statement of y_tts_pred & y_vc_pred
#34 opened by inconnu11 - 3
Multi-GPU training
#39 opened by ivancarapinha - 2
list file format
#33 opened by leonardw86 - 1
The mechanism of alignment between text encoder output and audio_seq2seq output
#37 opened by inconnu11 - 10
Speaker and linguistic embedding visualizations do not look good as in the paper
#29 opened by huukim136 - 1
Training the model for a different language
#36 opened by ivancarapinha - 3
Pre-train model results
#35 opened by ivancarapinha - 2
GPU memory requirements
#32 opened by ivancarapinha - 15
Interpreting results
#26 opened by JRMeyer - 1
Did you use a silence symbol?
#31 opened by youngsuenXMLY - 2
Alignment problem
#23 opened by Approximetal - 4
How much time is the training dataset?
#30 opened by youngsuenXMLY - 1
deduce num_speakers from *list files
#18 opened by JRMeyer - 1
- 5
Normalizing features
#28 opened by huukim136 - 3
Remove all Legacy Code
#24 opened by JRMeyer - 6
Why consistent_loss_w=0.0 ?
#22 opened by Approximetal - 0
- 3
Documentation: Training Time
#20 opened by JRMeyer - 5
gate outputs?
#17 opened by JRMeyer - 2
Upgrade to Python3
#4 opened by JRMeyer - 1
- 1
text_inputs vs text_targets?
#16 opened by JRMeyer - 1
Why skip long utterances?
#3 opened by JRMeyer - 1
Upgrade to TensorFlow 2.0 (or not?)
#6 opened by JRMeyer