chenbhao
/

omni

training-framework

Model card Files Files and versions

35.3 GB

Ctrl+K

Ctrl+K

3 contributors

History: 83 commits

chenbhao's picture

Add video call screenshot to README

6918b42 2 months ago

assets
Add assets directory 2 months ago
checkpoint
Add training checkpoints and dataset via LFS 2 months ago
configs
fix VAM: funasr+pyarrow deadlock, librosa+numpy compat, reduce iter_batches batch_size 2 months ago
dataset
Add training checkpoints and dataset via LFS 2 months ago
docs
Update docs: challenges.md (training bias + scene text approach), vam/multimodal/trainers docs sync 2 months ago
scripts
Simplify voice_args: remove redundant fallback chain, require explicit name 2 months ago
src
Add NaN guard to audio code generation path 2 months ago
.gitattributes

401 Bytes
Add assets directory 2 months ago
.gitignore

279 Bytes
cleanup: remove deprecated doc files, update src training utils 2 months ago
.python-version

5 Bytes
Initial commit: omni package with src layout and pyproject config 2 months ago
README.md

10 kB
Add video call screenshot to README 2 months ago
pyproject.toml

1.18 kB
Fix voice clone, path defaults, README rewrite; add pydub dep 2 months ago
uv.lock

633 kB
Fix voice clone, path defaults, README rewrite; add pydub dep 2 months ago