docker: containerizzazione tts-server con GPU Vulkan (Dockerfile multi-stage + compose + entrypoint voci .spk/.rvq)

docker/tts-server/docker-compose.yml

@@ -0,0 +1,41 @@
+# ============================================================================
+# tts-server (Qwen3-TTS, Vulkan) — docker compose
+# ----------------------------------------------------------------------------
+# Uso:
+#   export RENDER_GID=$(getent group render | cut -d: -f3)   # GID gruppo render
+#   docker compose up -d --build
+#
+# GPU: AMD/Intel via Mesa RADV (/dev/dri/renderD128). Su host dove il node
+# è world-writable (es. Fedora) group_add non è necessario ma innocuo.
+# NVIDIA: aggiungere il runtime nvidia (vedi README.md).
+#
+# Variabili utili:
+#   MODELS_DIR / VOICES_DIR : percorsi di modelli e voci (default: ../ dal compose)
+#   PORT                    : porta host (default 8881)
+# ============================================================================
+services:
+  tts-server:
+    build:
+      context: ../..
+      dockerfile: docker/tts-server/Dockerfile
+    image: qwentts-tts:vulkan
+    container_name: tts-server
+    devices:
+      - /dev/dri/renderD128:/dev/dri/renderD128
+    group_add:
+      - "${RENDER_GID:-44}"
+    environment:
+      GGML_BACKEND: Vulkan0
+      MODEL_PATH: /models/qwen-talker-1.7b-base-Q8_0.gguf
+      CODEC_PATH: /models/qwen-tokenizer-12hz-Q8_0.gguf
+      TTS_LANG: Italian
+      MODEL_ALIAS: qwen3-tts
+      HOST: 0.0.0.0
+      PORT: "8881"
+      VOICE_DIR: /voices
+    volumes:
+      - "${MODELS_DIR:-../models}:/models:ro"
+      - "${VOICES_DIR:-../voices}:/voices:ro"
+    ports:
+      - "${PORT:-8881}:8881"
+    restart: unless-stopped