Issues
- 0
Use ContentVec as pre-trained model.
#31 opened by Abedalhkeem-z - 2
- 1
How to make preprocessed files?
#29 opened by shirounanashi - 1
Base for ContentVec model
#28 opened by Lukysoon - 1
What are the pseudo labels?
#23 opened by Lukysoon - 1
Speaker Identification Task Evaluation
#27 opened by GovindK58 - 14
HuggingFace Version
#6 opened by leng-yue - 0
how to finetune contentvec coping hubert_asr.py
#26 opened by li-henan - 4
Regarding Multinode Training
#20 opened by nonmetal - 0
- 0
question on torch version
#24 opened by li-henan - 6
How can I get kmeans clustered features?
#22 opened by Remaxic - 1
- 0
Larger hubert models.
#19 opened by thepowerfuldeez - 1
请问是否有500分类的可用来训练的资源
#18 opened by hihei - 4
Question about speaker embedding
#17 opened by TechInterMezzo - 0
您好,看了您对ContentVec的解释,有其他问题想请教一下,可以留个邮箱沟通下嘛,谢谢了。
#16 opened by xypiaofei - 4
How to get a new spk2info.dict?
#14 opened by zyfily - 2
- 1
Can this model be called using C++?
#11 opened by sunTFly - 5
How to generate {train, valid}.km files?
#13 opened by freds0 - 2
issue about forward_padding_mask
#12 opened by zhenye234 - 6
Loading the model for inference
#1 opened by lesterphillip - 4
- 1
Contrastive loss weights
#8 opened by jingru-lin - 1
How to get lo, hi of spk2info in onwn dataset
#7 opened by k-washi - 3
Question about contrastive loss
#5 opened by Mu-Y - 2
- 0
- 1