Document OmniVoice cloning gate

experiments/omnivoice-cloning/Dockerfile

@@ -0,0 +1,28 @@
+FROM nvidia/cuda:12.8.1-cudnn-runtime-ubuntu24.04
+
+ARG OMNIVOICE_VERSION=0.2.1
+ARG OMNIVOICE_TRITON_VERSION=0.1.0
+
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends \
+      ca-certificates curl ffmpeg libsndfile1 python3 python3-pip python3-venv \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN python3 -m venv /opt/venv
+ENV PATH="/opt/venv/bin:${PATH}"
+
+RUN python -m pip install --no-cache-dir --upgrade pip \
+    && python -m pip install --no-cache-dir \
+      --index-url https://download.pytorch.org/whl/cu128 \
+      "torch==2.8.0" "torchaudio==2.8.0" \
+    && python -m pip install --no-cache-dir \
+      "omnivoice==${OMNIVOICE_VERSION}" \
+      "omnivoice-triton==${OMNIVOICE_TRITON_VERSION}" \
+      "num2words>=0.5.14"
+
+EXPOSE 8008
+
+HEALTHCHECK --interval=5s --timeout=3s --start-period=600s --retries=3 \
+  CMD curl -fsS http://127.0.0.1:8008/ >/dev/null || exit 1
+
+CMD ["omnivoice-demo", "--ip", "0.0.0.0", "--port", "8008"]

experiments/omnivoice-cloning/README.md

@@ -0,0 +1,18 @@
+# OmniVoice cloning gate on Athena
+
+This is the isolated quality gate for `k2-fsa/OmniVoice` 0.2.1. It exposes
+the upstream Gradio demo through Athena's existing private Voice Studio route.
+The image also contains `omnivoice-triton` 0.1.0 for a later measured
+base-versus-optimized benchmark; the upstream UI deliberately starts in the
+unmodified reference mode so kernel changes cannot contaminate the first
+listening test.
+
+- Model weights: CC-BY-NC
+- Code: Apache-2.0
+- Private URL: `http://192.168.1.212:8008`
+- Persistent cache: `/data/voice/omnivoice/huggingface`
+- GPU allocator workaround: `expandable_segments:True`
+
+Use a clean 3–10 second reference and provide its exact transcript. German
+target text should be written out normally; avoid raw abbreviations and digits
+in the first quality test.

experiments/omnivoice-cloning/compose.yaml

@@ -0,0 +1,40 @@
+services:
+  voice-studio:
+    build: .
+    image: mike-ai/omnivoice-studio:0.2.1
+    container_name: mike-ai-voice-studio
+    restart: "no"
+    labels:
+      # Kept compatible with the current controller during the A/B gate.
+      com.mike-ai.voice-worker: vevo2
+    environment:
+      NVIDIA_VISIBLE_DEVICES: ${VOICE_GPU_UUID:?set VOICE_GPU_UUID to the RTX 5080 UUID}
+      NVIDIA_DRIVER_CAPABILITIES: compute,utility
+      HF_HOME: /models/huggingface
+      PYTORCH_CUDA_ALLOC_CONF: expandable_segments:True
+    ports:
+      - "127.0.0.1:8008:8008"
+    volumes:
+      - /data/voice/omnivoice/huggingface:/models/huggingface
+      - /data/voice/omnivoice/output:/output
+    healthcheck:
+      test: ["CMD-SHELL", "curl -fsS http://127.0.0.1:8008/ >/dev/null"]
+      interval: 5s
+      timeout: 3s
+      start_period: 600s
+      retries: 3
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              device_ids: ["${VOICE_GPU_UUID:?set VOICE_GPU_UUID to the RTX 5080 UUID}"]
+              capabilities: [gpu]
+    networks:
+      frontend:
+        aliases: [voice-studio]
+
+networks:
+  frontend:
+    name: mike-ai_frontend
+    external: true