JuzeZhang
/

ViBES-Audio

speech-to-speech

knowledge-distillation

Model card Files Files and versions

1.33 GB

Ctrl+K

Ctrl+K

1 contributor

History: 6 commits

JuzeZhang's picture

README: version note — weights updated to stage-5 multi-task distill (2026-05-30)

a4c9ac6 verified 14 days ago

.gitattributes

1.52 kB
initial commit 28 days ago
README.md

4.89 kB
README: version note — weights updated to stage-5 multi-task distill (2026-05-30) 14 days ago
config.json

1.49 kB
fix config _name_or_path -> JuzeZhang/ViBES-Audio (drop internal step24000 path) 24 days ago
configuration_chatglm.py

2.27 kB
ViBES-Audio: distilled 0.5B GLM-4-Voice (speech backbone for ViBES) 28 days ago
model.safetensors

1.33 GB
xet

update ViBES-Audio to stage5_mt_model/final (latest GLM-4-Voice 0.5B distill, step24000) 24 days ago
modeling_chatglm.py

47.3 kB
ViBES-Audio: distilled 0.5B GLM-4-Voice (speech backbone for ViBES) 28 days ago
tokenization_chatglm.py

8.99 kB
ViBES-Audio: distilled 0.5B GLM-4-Voice (speech backbone for ViBES) 28 days ago
tokenizer.model

2.62 MB
xet

ViBES-Audio: distilled 0.5B GLM-4-Voice (speech backbone for ViBES) 28 days ago
tokenizer_config.json

3.18 MB
ViBES-Audio: distilled 0.5B GLM-4-Voice (speech backbone for ViBES) 28 days ago