auspicious3000/contentvec

Issues

• Use ContentVec as pre-trained model.

  #31 opened 3 months ago by Abedalhkeem-z
  0

• how to convert checkpoint_best_500.pt to checkpoint_best_legacy_500.pt model

  #30 opened 5 months ago by kwaihua
  2

• How to make preprocessed files?

  #29 opened 5 months ago by shirounanashi
  1

• Base for ContentVec model

  #28 opened 5 months ago by Lukysoon
  1

• What are the pseudo labels?

  #23 opened 7 months ago by Lukysoon
  1

• Speaker Identification Task Evaluation

  #27 opened 7 months ago by GovindK58
  1

• HuggingFace Version

  #6 opened 2 years ago by leng-yue
  14

• how to finetune contentvec coping hubert_asr.py

  #26 opened 7 months ago by li-henan
  0

• Regarding Multinode Training

  #20 opened 10 months ago by nonmetal
  4

• how to train a better contentvec model applied on svc task

  #25 opened 8 months ago by li-henan
  0

• question on torch version

  #24 opened 8 months ago by li-henan
  0

• How can I get kmeans clustered features?

  #22 opened 9 months ago by Remaxic
  6

• Inferencing a non-legacy model in the fairseq environment

  #21 opened 10 months ago by misakiudon
  1

• Larger hubert models.

  #19 opened a year ago by thepowerfuldeez
  0

• 请问是否有500分类的可用来训练的资源

  #18 opened a year ago by hihei
  1

• Question about speaker embedding

  #17 opened a year ago by TechInterMezzo
  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。

  #16 opened a year ago by xypiaofei
  0

• How to get a new spk2info.dict?

  #14 opened a year ago by gu76h
  4

• Question about released model and speaker information

  #15 opened a year ago by asr-pub
  2

• Can this model be called using C++?

  #11 opened a year ago by sunTFly
  1

• How to generate {train, valid}.km files?

  #13 opened a year ago by freds0
  5

• issue about forward_padding_mask

  #12 opened a year ago by zhenye234
  2

• Loading the model for inference

  #1 opened a year ago by lesterphillip
  6

• Uploaded 500-classes pretrained models are maybe incorrect (no trained)

  #10 opened 2 years ago by TylorShine
  4

• Contrastive loss weights

  #8 opened 2 years ago by jingru-lin
  1

• How to get lo, hi of spk2info in onwn dataset

  #7 opened 2 years ago by k-washi
  1

• Question about contrastive loss

  #5 opened 2 years ago by Mu-Y
  3

• GE2E Pre-trained Model for Speaker Embedding Extraction

  #3 opened 2 years ago by kingformatty
  2

• Which class setting did you use in the vc experiments?

  #4 opened 2 years ago by splinter21
  0

• What's the open source license of this work?

  #2 opened 2 years ago by splinter21
  1