Issues
- 1
Repo release for "SPIRIT-LM: Interleaved Spoken and Written Language Model" ?
#34 opened by Baiiiiiiiiii - 0
- 4
- 2
Voice change
#23 opened by sankar-mukherjee - 0
5% accuracy on expresso test set
#36 opened by ramonsanabria - 0
Load mhubert_base_25hz error
#33 opened by 0nutation - 0
installation bugs
#32 opened by 0nutation - 0
About the license of "EXPRESSO" dataset
#31 opened by sh-lee-prml - 1
chinese supprt or train it from scratch
#24 opened by zdj97 - 0
- 0
- 0
calling tacotron2 stales with numpy=1.22
#21 opened by RobinAlgayres - 0
Need Help
#20 opened by princess200816 - 0
- 2
- 5
- 4
Code release
#13 opened by Rongjiehuang - 1
Textless Speech Emotion Conversion
#12 opened by harisbinzia - 1
Tacotron2 training codes
#16 opened by WillQuCD - 1
About the vocabulary size
#15 opened by yyz845935161 - 4
There was an error when I installed Fairseq
#10 opened by yyz845935161 - 1
Example "Speaker_Probing" not working
#17 opened by fra1993 - 0
Aboutthe vocabulary size
#14 opened by yyz845935161 - 0
Fairseq installation
#6 opened by eonglints