Hugging Face's logo

jh-y
/
dllm-vsr

PyTorch
Safetensors
visual-speech-recognition
lip-reading
discrete-diffusion
diffusion-language-model
lrs3
Model card Files
xet
 Community
dllm-vsr / usr2 /len_pred /len_pred_wildvsr.jsonl
jh-y's picture
jh-y
Update model card (EMNLP 2026 camera-ready) and add length-predictor outputs (K_pred±5 pools for LRS3 test / WildVSR)
7a9cd42 verified
Raw History Contribute Delete
861 kB
File too large to display, you can check the raw version instead.