VinAIResearch/XPhoneBERT
XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech (INTERSPEECH 2023)
PythonMIT
Issues
- 0
The quality of the voice gradually decreases towards the end of the paragraph
#25 opened by manhcuong17072002 - 2
- 1
- 1
Checkpoint request
#22 opened by ndhuynh02 - 5
punctuation missing
#6 opened by thanhlong1997 - 0
the problem of inference
#23 opened by zhaozhuoyang-six - 0
- 1
- 1
Can you share any audio samples?
#16 opened by jun-danieloh - 3
any audio samples?
#3 opened by innnky - 1
Chinese data about tones
#18 opened by russell-shu - 1
- 2
Multispeaker
#15 opened by qwertyflagstop - 1
Finetune this model on a new language
#17 opened by gongchenghhu - 1
Text Normalization Process
#14 opened by qwertyflagstop - 2
- 1
Any comments on the size required for the dataset? (Also, can you share the pretrained models)
#9 opened - 1
- 28
Gibberish output after 70k steps
#4 opened by godspirit00 - 8
- 3
[Bug] RuntimeError: stft requires the return_complex parameter be given for real inputs #2449
#8 opened by K2O7I - 2
- 1
About Bert
#2 opened by YuruW - 1
Multi speaker trainingļ¼
#1 opened by Stardust-minus