42 lines
1,003 B
TOML
42 lines
1,003 B
TOML
[build-system]
|
|
requires = ["setuptools>=61.0"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "vibevoice"
|
|
version = "0.0.1"
|
|
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
|
|
"diffusers",
|
|
"tqdm",
|
|
"numpy",
|
|
"scipy",
|
|
"librosa",
|
|
"ml-collections",
|
|
"absl-py",
|
|
"gradio",
|
|
"av",
|
|
"aiortc",
|
|
"librosa"
|
|
]
|
|
|
|
|
|
[project.urls]
|
|
"Homepage" = "https://github.com/microsoft/VibeVoice"
|
|
"Bug Tracker" = "https://github.com/microsoft/VibeVoice/issues"
|
|
|
|
[tool.setuptools.packages.find]
|
|
where = ["."]
|