HereLiesAz
/

liperty-avhubert-encoder

visual-speech-recognition

Model card Files Files and versions

liperty-avhubert-encoder

4.97 GB

Ctrl+K

Ctrl+K

1 contributor

History: 8 commits

HereLiesAz's picture

V3 seq2seq decoder export (TransformerDecoder, 6 layers, vocab=1000)

77e5fd3 verified 1 day ago

.gitattributes

1.52 kB
initial commit 3 days ago
LICENSE.txt

8.81 kB
Add AV-HuBERT license (per redistribution requirement) 3 days ago
README.md

1.52 kB
Add README with attribution and provenance 3 days ago
avhubert_base_vox_433h_decoder.onnx

239 MB
xet

V3 seq2seq decoder export (TransformerDecoder, 6 layers, vocab=1000) 1 day ago
avhubert_base_vox_433h_dict.txt

7.8 kB
V3 seq2seq decoder export (TransformerDecoder, 6 layers, vocab=1000) 1 day ago
avhubert_base_vox_433h_visual_encoder.onnx

411 MB
xet

ONNX-exported AV-HuBERT base+vox+433h fine-tuned visual encoder (Docker, parity-passed) 2 days ago
avhubert_visual_encoder.onnx

411 MB
xet

ONNX-exported AV-HuBERT base visual encoder (Docker route, parity-fixed) 2 days ago
large_vox_iter5.pt

3.91 GB
xet

Mirror of facebookresearch AV-HuBERT large_vox_iter5 (LRS3+VoxCeleb2 pretrained) 3 days ago