Hugging Face's logo

espnet
/
voxcelebs12_ska_wavlm_joint

ESPnet
multilingual
audio
speaker-recognition
Model card Files Community
jungjee commited on
Commit
da3d5bc
·
verified ·
1 Parent(s): 09d197d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -32,7 +32,7 @@ import numpy as np
32
  from espnet2.bin.spk_inference import Speech2Embedding
33
 
34
  # from uploaded models
35
- speech2spk_embed = Speech2Embedding.from_pretrained(model_tag="espnet/voxcelebs12_rawnet3")
36
  embedding = speech2spk_embed(np.zeros(16500))
37
 
38
  # from checkpoints trained by oneself
 
32
  from espnet2.bin.spk_inference import Speech2Embedding
33
 
34
  # from uploaded models
35
+ speech2spk_embed = Speech2Embedding.from_pretrained(model_tag="espnet/voxcelebs12_ska_wavlm_joint")
36
  embedding = speech2spk_embed(np.zeros(16500))
37
 
38
  # from checkpoints trained by oneself