Hugging Face's logo

Emova-ollm
/
emova_speech_tokenizer_hf

Feature Extraction
Transformers
Safetensors
English
Chinese
EMOVASpeechTokenizer
speech
tokenization
custom_code
Model card Files Community
KaiChen1998 commited on
Commit
c46162e
·
verified ·
1 Parent(s): d15d5d3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -43,8 +43,7 @@ import torch
43
  from transformers import AutoModel
44
 
45
  # load pretrained model
46
- model = AutoModel.from_pretrained("Emova-ollm/emova_speech_tokenizer_hf", torch_dtype=torch.float32, trust_remote_code=True).eval()
47
- model = model.cuda()
48
 
49
  # S2U
50
  wav_file = "./examples/s2u/example.wav"
 
43
  from transformers import AutoModel
44
 
45
  # load pretrained model
46
+ model = AutoModel.from_pretrained("Emova-ollm/emova_speech_tokenizer_hf", torch_dtype=torch.float32, trust_remote_code=True).eval().cuda()
 
47
 
48
  # S2U
49
  wav_file = "./examples/s2u/example.wav"