fix(mlx): bundle native libs and broaden error handling for Apple Silicon

The distributed macOS aarch64 binary shipped without MLX acceleration despite
the model and backend code supporting it. Two root causes:

1. **OSError not caught in platform_detect.py**
   PyInstaller bundles isolate the filesystem, so when MLX tries to load its
   Metal shader libraries (.metallib) it raises OSError, not ImportError.
   platform_detect.get_backend_type() only caught ImportError, causing a
   silent fallback to PyTorch even on Apple Silicon hardware.
   Fix: broaden the except clause to (ImportError, OSError, RuntimeError)
   and import mlx.core instead of mlx (forces native lib loading eagerly).

2. **collect_data_files used instead of collect_all for MLX**
   build_binary.py and voicebox-server.spec used --collect-data /
   collect_data_files for mlx and mlx_audio. This copies Python source and
   pure-Python data, but NOT native shared libraries (.dylib, .metallib).
   Fix: switch to --collect-all / collect_all which captures binaries too,
   then pass them to Analysis(binaries=...) in the spec.

Result: macOS Apple Silicon users now get MLX inference (~4-5x faster than
PyTorch CPU), matching the performance documented in the README.

backend/platform_detect.py

@@ -19,15 +19,17 @@ def is_apple_silicon() -> bool:
 def get_backend_type() -> Literal["mlx", "pytorch"]:
     """
     Detect the best backend for the current platform.
-    
+
     Returns:
-        "mlx" on Apple Silicon (if MLX is available), "pytorch" otherwise
+        "mlx" on Apple Silicon (if MLX is available and functional), "pytorch" otherwise
     """
     if is_apple_silicon():
         try:
-            import mlx
+            import mlx.core  # noqa: F401 — triggers native lib loading
             return "mlx"
-        except ImportError:
-            # MLX not installed, fallback to PyTorch
+        except (ImportError, OSError, RuntimeError):
+            # MLX not installed, or native libraries failed to load inside a
+            # PyInstaller bundle (OSError on missing .dylib / .metallib).
+            # Fall through to PyTorch.
             return "pytorch"
     return "pytorch"