Rongjiehuang/GenerSpeech
PyTorch Implementation of GenerSpeech (NeurIPS'22): a text-to-speech model towards zero-shot style transfer of OOD custom voice.
PythonMIT
Issues
- 1
Expired Download Link
#23 opened by hz01 - 1
where is the dataset
#28 opened by YueMing-github - 0
How to solve this error?
#27 opened by fish0131 - 1
pre-training model
#25 opened by jcl-gx - 0
When we use the style adaptor, how can we get the word/Phoneme boundary?
#24 opened by Superman-Valencia - 0
Pretrained model links are down!
#22 opened by ArEnSc - 0
- 1
Some questions after reading the paper
#4 opened by enhuiz - 1
Could not reproduce the result
#10 opened by sinhprous1 - 2
the link for the pre-trained weights has expired
#20 opened by meriamOu - 0
MFA dictionary
#19 opened by zuihaodeyujian - 0
How to use the adaption part of your model ?
#18 opened by yiwei0730 - 0
Versions of libraries/tools used
#17 opened by prasannasagar - 1
Proper installation steps
#14 opened by iamanigeeit - 0
Alternative to MFA installation
#16 opened by prasannasagar - 5
Pretrained models URL not working
#15 opened by prasannasagar - 2
- 2
Conda installation issue
#11 opened by snufas - 0
Mistmatch between paper and the implementation
#12 opened by betklab - 3
emotion_encoder_path
#9 opened by ZahraGhasemi-AI - 1
None achademical but a general question here
#7 opened by lucasjinreal - 1
What exactly wrong with the key here?
#6 opened by reubzdubz - 1
Handling of OOVs
#8 opened by enhuiz - 1
MFA inference problem
#5 opened by edwin-19 - 2
- 1
bug of inference
#2 opened by JJun-Guo - 1