Issues
- 2
- 11
- 0
Ask for help about GAN use conv
#45 opened by Liujingxiu23 - 3
Pyworld in requirements
#43 opened by karkirowle - 0
How can I synthesize my own text to speech?
#42 opened by zxq2233 - 1
./train_gan.sh: line 53: 5671 Segmentation fault
#41 opened by yuuSiVo - 2
Segmentation fault (core dumped)
#16 opened by yutaozuo - 1
- 4
- 1
GAN conditioned on speaker id
#34 opened by mrgloom - 2
Issue when using my own data
#38 opened by khorshidisamira - 1
CPU load 100% on all cores using vc_demo.sh
#35 opened by mrgloom - 2
Quality of voice conversion from female to male
#26 opened by fxw915 - 3
Publish how much audio needed?
#21 opened by mathematiguy - 1
mismatch
#20 opened by MrRenQIANG - 1
AssertionError
#19 opened by yuuSiVo - 1
- 1
Feature extraction for TTS details
#32 opened by mrgloom - 1
Can you please share pre-trained model
#27 opened by aishweta - 1
Add download_dataset.sh
#30 opened by mrgloom - 1
No such file or directory: '../checkpoints/vc/baseline/checkpoint_epoch200_Generator.pth
#37 opened by khorshidisamira - 1
Amazing implementation. Did you think of extending it with GAN-TTS with Stylisation ?
#36 opened by shamanez - 5
What's the inputs of GAN-TTS?
#12 opened by Alexander-flyer - 1
ImportError: No module named nnmnkwii.datasets
#33 opened by mrgloom - 0
- 1
Add requirements.txt
#31 opened by mrgloom - 1
- 2
- 1
- 0
- 1
Support for pytorch v0.4
#18 opened by r9y9 - 1
FileExistsError: [Errno 17] File exists: './checkpoints/jp_tts_order59/tts_duration/gan'
#17 opened by yuuSiVo - 5
- 5
No audio files generated
#11 opened by joshuatw - 5
gantts.version
#10 opened by Sangramsingkayte - 1
Remind: the function 'adjast_frame_lengths' in nnmnkwii have been replaced to 'adjust_frame_lengths'
#13 opened by Alexander-flyer - 3
- 4
- 6
Problem with dataset_loaders
#8 opened by raghadeepa - 1
- 3
- 10
- 2