ZhangXInFD SpeechTokenizer issues

ZhangXInFD / SpeechTokenizer

This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models. Samples are presented on

https://0nutation.github.io/SpeechTokenizer.github.io/

Apache License 2.0

405 stars 37 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Can we generate audio from just semantic tokens?

#16 macabdul9 opened 1 week ago
0
Ask for number range of training loss.

#15 liangpenglong opened 1 week ago
0
changing hubert model to another model

#14 acul3 opened 1 month ago
0
10 batchsize = 63.72G???(All File are 3s wav)

#13 coding-sharks opened 1 month ago
0
ImportError: cannot import name 'split_torch_state_dict_into_shards' from 'huggingface_hub'

#12 ehosseiniasl opened 2 months ago
2
Cross-lingual

#11 coding-sharks opened 2 months ago
0
zero grad issus in encodec?

#10 yuzuda283 opened 2 months ago
0
Add example.py

#9 karthik19967829 closed 3 months ago
0
distill loss weight?

#8 yuzuda283 closed 2 months ago
1
what is the input when inference for encoding?

#7 Edwardmark closed 3 months ago
2
Could you kindly share the training code?

#6 zhenye234 closed 2 months ago
2
How to deal with the integer values of RVQ

#5 phdshliang opened 5 months ago
0
About HuBERT unit

#4 0417keito closed 2 months ago
5
Fix typo in README.md

#3 eltociear closed 1 year ago
1
Training process?

#2 fmac2000 closed 10 months ago
8
Update README.md

#1 KeiKinn closed 1 year ago
1