mirror of
https://github.com/zenlm/zen-translator.git
synced 2026-10-30 14:57:35 +00:00
130 lines
2.9 KiB
TOML
130 lines
2.9 KiB
TOML
[project]
|
|
name = "zen-translator"
|
|
version = "0.1.0"
|
|
description = "Real-time multimodal translation with lip sync and voice cloning"
|
|
readme = "README.md"
|
|
license = {text = "Apache-2.0"}
|
|
authors = [
|
|
{name = "Hanzo AI", email = "[email protected]"},
|
|
{name = "Zen LM", email = "[email protected]"}
|
|
]
|
|
requires-python = ">=3.14"
|
|
keywords = ["translation", "lip-sync", "voice-cloning", "multimodal", "real-time", "streaming"]
|
|
classifiers = [
|
|
"Development Status :: 3 - Alpha",
|
|
"Intended Audience :: Developers",
|
|
"License :: OSI Approved :: Apache Software License",
|
|
"Programming Language :: Python :: 3.10",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
|
"Topic :: Multimedia :: Sound/Audio :: Speech",
|
|
"Topic :: Multimedia :: Video",
|
|
]
|
|
|
|
dependencies = [
|
|
# Core ML
|
|
"torch>=2.1.0",
|
|
"transformers>=4.45.0",
|
|
"accelerate>=0.25.0",
|
|
"safetensors>=0.4.0",
|
|
|
|
# Audio processing
|
|
"librosa>=0.10.0",
|
|
"soundfile>=0.12.0",
|
|
"sounddevice>=0.4.6",
|
|
"pyaudio>=0.2.14",
|
|
"webrtcvad>=2.0.10",
|
|
|
|
# Video processing
|
|
"opencv-python>=4.8.0",
|
|
"ffmpeg-python>=0.2.0",
|
|
"av>=11.0.0",
|
|
|
|
# Streaming
|
|
"fastapi>=0.109.0",
|
|
"uvicorn[standard]>=0.27.0",
|
|
"websockets>=12.0",
|
|
"python-multipart>=0.0.6",
|
|
"httpx>=0.26.0",
|
|
|
|
# Data processing
|
|
"numpy>=1.24.0",
|
|
"scipy>=1.11.0",
|
|
"pandas>=2.0.0",
|
|
"datasets>=2.16.0",
|
|
"huggingface-hub>=0.20.0",
|
|
|
|
# Utils
|
|
"pydantic>=2.5.0",
|
|
"pydantic-settings>=2.1.0",
|
|
"rich>=13.7.0",
|
|
"typer>=0.9.0",
|
|
"tqdm>=4.66.0",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
ui = [
|
|
"gradio>=4.44.0",
|
|
"fastrtc>=0.0.20",
|
|
"python-dotenv>=1.0.0",
|
|
"certifi>=2024.0.0",
|
|
]
|
|
training = [
|
|
"ms-swift>=2.4.0",
|
|
"peft>=0.7.0",
|
|
"bitsandbytes>=0.42.0",
|
|
"wandb>=0.16.0",
|
|
"deepspeed>=0.13.0",
|
|
]
|
|
cosyvoice = [
|
|
"onnxruntime-gpu>=1.16.0",
|
|
"WeTextProcessing>=1.0.0",
|
|
"modelscope>=1.12.0",
|
|
]
|
|
dev = [
|
|
"pytest>=7.4.0",
|
|
"pytest-asyncio>=0.23.0",
|
|
"pytest-cov>=4.1.0",
|
|
"ruff>=0.1.0",
|
|
"mypy>=1.8.0",
|
|
"pre-commit>=3.6.0",
|
|
]
|
|
all = [
|
|
"zen-translator[ui,training,cosyvoice,dev]",
|
|
]
|
|
|
|
[project.scripts]
|
|
zen-translate = "zen_translator.cli:app"
|
|
zen-serve = "zen_translator.server:main"
|
|
|
|
[project.urls]
|
|
Homepage = "https://zenlm.org"
|
|
Repository = "https://github.com/zenlm/zen-translator"
|
|
Documentation = "https://docs.zenlm.org/translator"
|
|
Issues = "https://github.com/zenlm/zen-translator/issues"
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["src/zen_translator"]
|
|
|
|
[tool.ruff]
|
|
line-length = 100
|
|
target-version = "py310"
|
|
|
|
[tool.ruff.lint]
|
|
select = ["E", "F", "I", "N", "W", "UP"]
|
|
ignore = ["E501"]
|
|
|
|
[tool.mypy]
|
|
python_version = "3.10"
|
|
strict = true
|
|
ignore_missing_imports = true
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests"]
|
|
asyncio_mode = "auto"
|