Issues
- 0
Audio playback speed is too fast
#36 opened by GitVHV - 0
How to keep voice with same person.
#38 opened by binhmuc - 0
how to run with gpu and tpu
#37 opened by nam157 - 2
Một vài thư viện không support Windows
#30 opened by ThinhNgVhust - 0
- 2
the number in the text
#27 opened by hiennguyen92 - 0
- 2
Prediction time is too slow
#32 opened by GitVHV - 2
Training infinity ;))
#26 opened by thuandq - 0
Chuyển giao công nghệ
#31 opened by infinitysoftwarecorp - 1
need to tranning read number
#29 opened by tomnyson - 0
EOFError: Ran out of input
#28 opened by dugduy - 1
FileNotFoundError: [Errno 2] No such file or directory: 'assets/infore/hifigan/hk_hifi.pickle'
#25 opened by anhntk54 - 3
How to convert hifigan V3 to haiku correctly?
#24 opened by nampdn - 2
mfa version
#17 opened by MostafaAlaviyan - 2
- 0
acoustic training generate strange melspectrogram
#23 opened by nampdn - 7
Hifi GAN with 24kHz
#20 opened by ngoquanghuy99 - 6
- 1
could not synchronize on CUDA context
#16 opened by lethanhson9901 - 17
improve tts
#9 opened by lethanhson9901 - 5
How to handle english words in vietnamese text
#13 opened by phanan9225 - 2
Feature: UnivNet implementation
#15 opened by lethanhson9901 - 3
High RAM usage acoustic model
#14 opened by lethanhson9901 - 2
Problems with Special Phonemes
#12 opened by phanan9225 - 2
How to create lexicon.txt file
#11 opened by phanan9225 - 1
number, date, ... to speech
#8 opened by luuvanduc1999 - 1
Graphemes to phonemes
#6 opened by huypl53 - 2
Error when fine tune new dataset
#5 opened by lethanhson9901 - 1
[Gen Loss and Mel-Spec Error]
#3 opened by TruongThuyLiem - 0
load Pretrained hifi-gan error
#7 opened by thanhdo99 - 10
[Textgrid for dataset]
#1 opened by frank269 - 2
- 2
Training with other dataset
#2 opened by TruongThuyLiem