mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-15 04:40:40 -07:00
Jamie Pine
94487f32a5
- Added support for MLX backend on Apple Silicon, enabling optimized performance for TTS and STT tasks. - Implemented platform detection to dynamically select between MLX and PyTorch based on the runtime environment. - Updated build process to include MLX-specific dependencies and configurations for macOS. - Refactored backend code to improve model loading and inference logic, accommodating backend-specific requirements. - Enhanced documentation to clarify backend selection and performance benefits for different platforms. - Streamlined installation instructions and troubleshooting guidance for MLX-related issues.
109 lines
3.7 KiB
Python
109 lines
3.7 KiB
Python
"""
|
|
PyInstaller build script for creating standalone Python server binary.
|
|
"""
|
|
|
|
import PyInstaller.__main__
|
|
import os
|
|
import platform
|
|
from pathlib import Path
|
|
|
|
|
|
def is_apple_silicon():
|
|
"""Check if running on Apple Silicon."""
|
|
return platform.system() == "Darwin" and platform.machine() == "arm64"
|
|
|
|
|
|
def build_server():
|
|
"""Build Python server as standalone binary."""
|
|
backend_dir = Path(__file__).parent
|
|
|
|
# PyInstaller arguments
|
|
args = [
|
|
'server.py', # Use server.py as entry point instead of main.py
|
|
'--onefile',
|
|
'--name', 'voicebox-server',
|
|
]
|
|
|
|
# Add local qwen_tts path if specified (for editable installs)
|
|
qwen_tts_path = os.getenv('QWEN_TTS_PATH')
|
|
if qwen_tts_path and Path(qwen_tts_path).exists():
|
|
args.extend(['--paths', str(qwen_tts_path)])
|
|
print(f"Using local qwen_tts source from: {qwen_tts_path}")
|
|
|
|
# Add common hidden imports
|
|
args.extend([
|
|
'--hidden-import', 'backend',
|
|
'--hidden-import', 'backend.main',
|
|
'--hidden-import', 'backend.config',
|
|
'--hidden-import', 'backend.database',
|
|
'--hidden-import', 'backend.models',
|
|
'--hidden-import', 'backend.profiles',
|
|
'--hidden-import', 'backend.history',
|
|
'--hidden-import', 'backend.tts',
|
|
'--hidden-import', 'backend.transcribe',
|
|
'--hidden-import', 'backend.platform_detect',
|
|
'--hidden-import', 'backend.backends',
|
|
'--hidden-import', 'backend.backends.pytorch_backend',
|
|
'--hidden-import', 'backend.utils.audio',
|
|
'--hidden-import', 'backend.utils.cache',
|
|
'--hidden-import', 'backend.utils.progress',
|
|
'--hidden-import', 'backend.utils.hf_progress',
|
|
'--hidden-import', 'backend.utils.validation',
|
|
'--hidden-import', 'torch',
|
|
'--hidden-import', 'transformers',
|
|
'--hidden-import', 'fastapi',
|
|
'--hidden-import', 'uvicorn',
|
|
'--hidden-import', 'sqlalchemy',
|
|
'--hidden-import', 'librosa',
|
|
'--hidden-import', 'soundfile',
|
|
'--hidden-import', 'qwen_tts',
|
|
'--hidden-import', 'qwen_tts.inference',
|
|
'--hidden-import', 'qwen_tts.inference.qwen3_tts_model',
|
|
'--hidden-import', 'qwen_tts.inference.qwen3_tts_tokenizer',
|
|
'--hidden-import', 'qwen_tts.core',
|
|
'--hidden-import', 'qwen_tts.cli',
|
|
'--copy-metadata', 'qwen-tts',
|
|
'--collect-submodules', 'qwen_tts',
|
|
'--collect-data', 'qwen_tts',
|
|
# Fix for pkg_resources and jaraco namespace packages
|
|
'--hidden-import', 'pkg_resources.extern',
|
|
'--collect-submodules', 'jaraco',
|
|
])
|
|
|
|
# Add MLX-specific imports if building on Apple Silicon
|
|
if is_apple_silicon():
|
|
print("Building for Apple Silicon - including MLX dependencies")
|
|
args.extend([
|
|
'--hidden-import', 'backend.backends.mlx_backend',
|
|
'--hidden-import', 'mlx',
|
|
'--hidden-import', 'mlx.core',
|
|
'--hidden-import', 'mlx.nn',
|
|
'--hidden-import', 'mlx_audio',
|
|
'--hidden-import', 'mlx_audio.tts',
|
|
'--hidden-import', 'mlx_audio.asr',
|
|
'--collect-submodules', 'mlx',
|
|
'--collect-submodules', 'mlx_audio',
|
|
# Collect MLX data files including Metal shader libraries (.metallib)
|
|
'--collect-data', 'mlx',
|
|
'--collect-data', 'mlx_audio',
|
|
])
|
|
else:
|
|
print("Building for non-Apple Silicon platform - PyTorch only")
|
|
|
|
args.extend([
|
|
'--noconfirm',
|
|
'--clean',
|
|
])
|
|
|
|
# Change to backend directory
|
|
os.chdir(backend_dir)
|
|
|
|
# Run PyInstaller
|
|
PyInstaller.__main__.run(args)
|
|
|
|
print(f"Binary built in {backend_dir / 'dist' / 'voicebox-server'}")
|
|
|
|
|
|
if __name__ == '__main__':
|
|
build_server()
|