feat: 大屏后端（FastAPI+MQTT+sim_engine）

- REST :10085 / MQTT 控制 / SSE 回退 / AI+语音 - 数据源规划：接核心服务端 + 算力引擎真实数据
2026-08-23 22:35:05 +08:00
parent 9700eb652b
commit b681eac2df
236 changed files with 54727 additions and 0 deletions
@@ -0,0 +1,143 @@
+[build-system]
+requires = ["setuptools>=77.0.3", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "speech-to-speech"
+version = "0.2.11"
+description = "Low-latency speech-to-speech pipeline"
+readme = "README.md"
+requires-python = ">=3.10"
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+authors = [
+    { name = "Hugging Face" },
+]
+keywords = ["speech-to-speech", "voice-agents", "speech-recognition", "text-to-speech", "openai"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Multimedia :: Sound/Audio :: Speech",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = [
+    "fastapi>=0.115.0",
+    "httpx>=0.28.0",
+    "nltk==3.9.4",
+    "numpy>=1.26.0,<2.4.4; platform_system == 'Darwin'",
+    "numpy>=1.26.0; platform_system != 'Darwin'",
+    "openai==2.28.0",
+    "pillow>=10.0.0",
+    "pydantic>=2.0",
+    "rich>=13.0",
+    "scipy>=1.10.0",
+    "sounddevice==0.5.3; platform_system == 'Darwin'",
+    "sounddevice>=0.5.0; platform_system != 'Darwin'",
+    "soundfile>=0.13.0; platform_system == 'Darwin'",
+    "torch==2.11.0; platform_system == 'Darwin'",
+    "torch>=2.4.0; platform_system != 'Darwin'",
+    "torchaudio==2.11.0; platform_system == 'Darwin'",
+    "torchaudio>=2.4.0; platform_system != 'Darwin'",
+    "transformers==5.6.2; platform_system == 'Darwin'",
+    "transformers>=4.57.0; platform_system != 'Darwin'",
+    "uvicorn>=0.30.0",
+    "websockets>=12.0",
+    "nano-parakeet>=0.2.0; platform_system != 'Darwin'",
+    "faster-qwen3-tts[ggml]>=0.3.2; platform_system != 'Darwin' and platform_system != 'Windows'",
+    "faster-qwen3-tts>=0.3.2; platform_system == 'Windows'",
+    "lingua-language-detector>=2.0.2",
+    "miniaudio==1.61; platform_system == 'Darwin'",
+    "mlx==0.31.1; platform_system == 'Darwin'",
+    "mlx-audio==0.4.2; platform_system == 'Darwin'",
+    "mlx-lm==0.31.1; platform_system == 'Darwin'",
+    "mlx-metal==0.31.1; platform_system == 'Darwin'",
+    "misaki>=0.9.4; platform_system == 'Darwin'",
+    "espeakng-loader>=0.2.4; platform_system == 'Darwin'",
+    "spacy>=3.8.4; platform_system == 'Darwin'",
+    "phonemizer-fork>=3.3.2; platform_system == 'Darwin'",
+]
+
+[project.optional-dependencies]
+chattts = [
+    "ChatTTS>=0.1.1",
+]
+facebook-mms = [
+    "transformers>=4.57.0",
+]
+faster-whisper = [
+    "faster-whisper>=1.0.3",
+]
+kokoro = [
+    "kokoro>=0.9.2; platform_system != 'Darwin'",
+]
+language-detection = [
+    "lingua-language-detector>=2.0.2",
+]
+mlx-lm = [
+    "mlx-lm==0.31.1; platform_system == 'Darwin'",
+    "mlx-vlm==0.4.1; platform_system == 'Darwin'",
+]
+paraformer = [
+    "funasr>=1.1.6",
+    "modelscope>=1.17.1",
+    "onnxruntime<1.24; python_version < '3.11'",
+]
+pocket = [
+    "pocket-tts>=0.1.0",
+]
+websocket = [
+    "websockets>=12.0",
+]
+whisper-mlx = [
+    "lightning-whisper-mlx>=0.0.10; platform_system == 'Darwin'",
+]
+
+[project.urls]
+Homepage = "https://github.com/huggingface/speech-to-speech"
+Repository = "https://github.com/huggingface/speech-to-speech"
+Issues = "https://github.com/huggingface/speech-to-speech/issues"
+
+[project.scripts]
+speech-to-speech = "speech_to_speech.s2s_pipeline:main"
+
+[dependency-groups]
+dev = [
+    "ruff",
+    "mypy",
+    "pytest",
+    "pytest-asyncio",
+    "websockets>=12.0",
+]
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+
+[tool.uv]
+package = true
+prerelease = "allow"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+include = ["speech_to_speech*"]
+exclude = ["tests*"]
+
+[tool.setuptools.package-data]
+speech_to_speech = ["TTS/*.wav"]
+
+[tool.ruff]
+src = ["src"]
+line-length = 120
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "W"]
+ignore = ["E501"]
+
+[tool.mypy]
+python_version = "3.10"
+ignore_missing_imports = true
+warn_unused_configs = true
+check_untyped_defs = false