transformers!=5.0.*,!=5.1.*,!=5.2.*,!=5.3.*,!=5.4.*,!=5.5.0,<5.9.0,>=4.56.0 av>=14.0.0 omegaconf>=2.3.0 diffusers==0.38.0 safetensors>=0.8.0rc0 accelerate==1.12.0 soundfile>=0.13.1 cache-dit==1.3.0 tqdm>=4.66.0 torchsde>=0.2.6 openai-whisper>=20250625 imageio[ffmpeg]>=2.37.2 x-transformers>=2.12.2 einops>=0.8.1 prettytable>=3.8.0 aenum==3.1.16 pyzmq>=25.0.0 janus>=1.0.0 pydub onnxruntime>=1.23.2 fa3-fwd==0.0.3 [demo] gradio>=6.7.0 [dev] pytest>=7.0.0 pytest-asyncio>=0.21.0 pytest-cov>=4.0.0 pytest-mock>=3.10.0 datasets>=2.14.0 mypy==1.11.1 pre-commit==4.0.1 openai-whisper>=20250625 psutil>=7.2.0 soundfile>=0.13.1 imageio[ffmpeg]>=0.6.0 opencv-python>=4.12.0.88 mooncake-transfer-engine-cuda13>=0.3.9 av openpyxl>=3.0.0 pyttsx3>=2.99 opencc>=1.2.0 mistune>=3.2.0 torchmetrics>=1.4.0 ray[default] jiwer>=3.0.0 zhon>=2.0.0 zhconv>=1.4.2 scipy>=1.10.0 funasr>=1.0.0 lpips>=0.1.4 orjson>=3.11.7 voxcpm>=2.0.2 torchdiffeq>=0.2.5 FlagEmbedding kernels<0.15.0 [docs] mkdocs>=1.5.0 mkdocs-api-autonav mkdocs-material mkdocstrings-python mkdocs-gen-files mkdocs-awesome-nav mkdocs-glightbox mkdocs-git-revision-date-localized-plugin mkdocs-minify-plugin regex ruff pydantic [local] FlagEmbedding [minicpmo] stepaudio2-minicpmo