feat(deploy): add whisper.cpp Kubernetes deployment

Add Dockerfile and K8s manifests for whisper.cpp transcription service.
Deploys to ai-stack namespace with worker node affinity for GPU access.

deploy/whisper/Dockerfile

@@ -0,0 +1,40 @@
+FROM ubuntu:22.04 AS build
+WORKDIR /app
+
+RUN apt-get update && \
+    apt-get install -y build-essential wget cmake git \
+    && rm -rf /var/lib/apt/lists/*
+
+ARG WHISPER_CPP_VERSION=v1.8.3
+RUN git clone --depth 1 --branch ${WHISPER_CPP_VERSION} \
+    https://github.com/ggml-org/whisper.cpp.git .
+
+ARG WHISPER_MODEL=base.en
+RUN bash ./models/download-ggml-model.sh ${WHISPER_MODEL}
+RUN cmake -B build && cmake --build build --config Release -j$(nproc)
+
+FROM ubuntu:22.04
+WORKDIR /app
+
+RUN apt-get update && \
+    apt-get install -y curl ffmpeg \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY --from=build /app/build/bin/whisper-server /usr/local/bin/whisper-server
+COPY --from=build /app/build/src/libwhisper.so* /usr/local/lib/
+COPY --from=build /app/build/ggml/src/libggml*.so* /usr/local/lib/
+COPY --from=build /app/models /app/models
+RUN ldconfig
+
+ARG WHISPER_MODEL=base.en
+ENV WHISPER_MODEL_PATH=/app/models/ggml-${WHISPER_MODEL}.bin
+
+EXPOSE 8080
+
+ENTRYPOINT ["whisper-server"]
+CMD ["--model", "/app/models/ggml-base.en.bin", \
+     "--host", "0.0.0.0", \
+     "--port", "8080", \
+     "--convert", \
+     "--language", "en", \
+     "--inference-path", "/v1/audio/transcriptions"]