Giters
auspicious3000
/
contentvec
speech self-supervised representations
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
436
Watchers:
11
Issues:
29
Forks:
33
auspicious3000/contentvec Issues
how to convert checkpoint_best_500.pt to checkpoint_best_legacy_500.pt model
Updated
11 days ago
Comments count
1
How to make preprocessed files?
Closed
20 days ago
Comments count
1
Base for ContentVec model
Updated
a month ago
Comments count
1
What are the pseudo labels?
Closed
3 months ago
Comments count
1
Speaker Identification Task Evaluation
Updated
3 months ago
Comments count
1
HuggingFace Version
Updated
3 months ago
Comments count
14
how to finetune contentvec coping hubert_asr.py
Closed
3 months ago
Regarding Multinode Training
Closed
6 months ago
Comments count
4
how to train a better contentvec model applied on svc task
Closed
3 months ago
question on torch version
Closed
4 months ago
How can I get kmeans clustered features?
Updated
4 months ago
Comments count
6
Inferencing a non-legacy model in the fairseq environment
Updated
6 months ago
Comments count
1
Larger hubert models.
Updated
7 months ago
请问是否有500分类的可用来训练的资源
Updated
9 months ago
Comments count
1
Question about speaker embedding
Closed
a year ago
Comments count
4
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。
Updated
a year ago
How to get a new spk2info.dict?
Updated
a year ago
Comments count
4
Question about released model and speaker information
Closed
a year ago
Comments count
2
Can this model be called using C++?
Closed
a year ago
Comments count
1
How to generate {train, valid}.km files?
Closed
a year ago
Comments count
5
issue about forward_padding_mask
Closed
a year ago
Comments count
2
Loading the model for inference
Closed
a year ago
Comments count
6
Uploaded 500-classes pretrained models are maybe incorrect (no trained)
Closed
a year ago
Comments count
4
Contrastive loss weights
Updated
a year ago
Comments count
1
How to get lo, hi of spk2info in onwn dataset
Closed
a year ago
Comments count
1
Question about contrastive loss
Closed
a year ago
Comments count
3
GE2E Pre-trained Model for Speaker Embedding Extraction
Closed
a year ago
Comments count
2
Which class setting did you use in the vc experiments?
Closed
a year ago
What's the open source license of this work?
Closed
2 years ago
Comments count
1