File size: 1,138 Bytes
c6a64b8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 | [build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"
[project]
name = "vibevoice"
version = "0.1.0"
authors = [
{ name="vibevoice team", email="vibepod@microsoft.com" },
]
description = "A model for speech generation with an AR + diffusion architecture."
readme = "README.md"
requires-python = ">=3.9"
classifiers = [
"Programming Language :: Python :: 3",
# "License :: OSI Approved :: MIT License",
"Operating System :: OS Independent",
]
dependencies = [
"torch",
"accelerate==1.6.0",
"transformers==4.51.3", # we develop this project on transformers==4.51.3, later version may not be compatible
"datasets==3.5.0", # avoid issues with torchcodec
"peft", # for finetuning
"llvmlite>=0.40.0",
"numba>=0.57.0",
"diffusers",
"tqdm",
"numpy",
"scipy",
"librosa",
"ml-collections",
"absl-py",
"gradio==5.50.0",
"av",
"aiortc"
]
[project.optional-dependencies]
# Optional dependencies for streaming model web service
streaming-web = [
"fastapi",
"uvicorn[standard]",
]
[tool.setuptools.packages.find]
where = ["."]
|