perf: reduce container sizes and build times

- miku-stt: switch PyTorch CUDA -> CPU-only (~2.5 GB savings)
  - Silero VAD already runs on CPU via ONNX (onnx=True), CUDA PyTorch was waste
  - faster-whisper/CTranslate2 uses CUDA directly, no PyTorch GPU needed
  - torch+torchaudio layer: 3.3 GB -> 796 MB; total image 9+ GB -> 6.83 GB
  - Tested: Silero VAD loads (ONNX), Whisper loads on cuda, server ready

- llama-swap-rocm: add root .dockerignore to fix 31 GB build context
  - Dockerfile clones all sources from git, never COPYs from context
  - 19 GB of GGUF model files were being transferred on every build
  - Now excludes everything (*), near-zero context transfer

- anime-face-detector: add .dockerignore to exclude accumulated outputs
  - api/outputs/ (56 accumulated detection files) no longer baked into image
  - api/__pycache__/ and images/ also excluded

- .gitignore: remove .dockerignore exclusion so these files are tracked

stt-realtime/Dockerfile

@@ -1,12 +1,12 @@
 # RealtimeSTT Container
 # Uses Faster-Whisper with CUDA for GPU-accelerated inference
-# Includes dual VAD (WebRTC + Silero) for robust voice detection
+# Includes Silero VAD (ONNX, CPU-only) for robust voice detection
 #
 # Updated per RealtimeSTT PR #295:
 # - CUDA 12.8.1 (latest stable)
-# - PyTorch 2.7.1 with cu128 support
+# - PyTorch CPU-only (for Silero VAD tensor ops only - saves ~2.3 GB)
+# - Faster-Whisper/CTranslate2 uses CUDA directly, no PyTorch GPU needed
 # - Ubuntu 24.04 base
-# - Single Python 3.11 installation
 
 FROM nvidia/cuda:12.8.1-cudnn-runtime-ubuntu24.04
 
@@ -27,7 +27,7 @@ RUN apt-get update && apt-get install -y \
     curl \
     && rm -rf /var/lib/apt/lists/*
 
-# Install PyTorch with CUDA 12.8 support (installed first for layer caching)
+# Install PyTorch CPU-only (for Silero VAD tensor ops - GPU transcription uses CTranslate2 directly)
 COPY requirements-gpu-torch.txt .
 RUN python3 -m pip install --break-system-packages --no-cache-dir -r requirements-gpu-torch.txt