# Parakeet ASR via sherpa-onnx + our own thin FastAPI wrapper.
#
# We previously wrapped Shadowfita/parakeet-tdt-0.6b-v2-fastapi but hit two
# unfixed upstream bugs (open issues #16 + #10) the first time we actually sent
# a transcription request. Switched to sherpa-onnx — ONNX Runtime + CUDA, a
# prebuilt int8 quantized Parakeet-TDT from k2-fsa — and wrote our own ~50-line
# wrapper we own end-to-end.
#
# HOST: fv-ml1, GPU 0 (relocated from irv-ml1 2026-09-15).
#
# ⚠ GPU 0, NOT the empty GPU 3. This seat holds ~800 MiB — under 1% of a 96 GB
# card — so it rides on the card with the most uncommitted headroom rather than
# putting the first fingerprint on a pristine one. GPU 0's seats commit
# util 0.40 + 0.48 = 0.88, leaving ~13 GB; GPU 1 is at 0.975 and GPU 2 at 0.96,
# both too tight. Keeping GPU 3 at 2 MiB means it can still take a full-card seat
# (flash-next needs 93 GiB) without a neighbour eating its profiling margin —
# vLLM sizes KV cache as a fraction of TOTAL VRAM, not free VRAM, so a resident
# tenant on an otherwise-empty card is worth more than its megabytes suggest.
#
# ⚠ The pin is `deploy.resources.reservations.devices[].device_ids`, the fleet
# convention — NOT `runtime: nvidia` + NVIDIA_VISIBLE_DEVICES, and NOT
# `count: all` (which is what the dead on-host stub did, and would have let this
# tiny ASR seat see all four cards). device_ids presents the pinned card as
# cuda:0 INSIDE the container, which is what sherpa-onnx's
# CUDAExecutionProvider takes by default.
#
# Model weights (~460 MB int8) download on first run via the entrypoint to
# ${PARAKEET_MODELS_DIR}/ (persistent host bind mount). Subsequent starts skip
# the download.
#
# API:
#   POST /transcribe                  — multipart file upload, returns {"text": "..."}
#   POST /v1/audio/transcriptions     — same body, OpenAI-compatible path alias
#   GET  /healthz
#
# All tunables live in .env — edit that, not this file.

services:
  parakeet:
    image: local/parakeet:${PARAKEET_TAG}
    build:
      context: .
      dockerfile: Dockerfile
    container_name: parakeet
    restart: unless-stopped
    ports:
      - "${PARAKEET_BIND:-0.0.0.0}:${PARAKEET_PORT}:8000"
    environment:
      - MODEL_DIR=/models
      - MODEL_URL=${PARAKEET_MODEL_URL}
      - PROVIDER=${PARAKEET_PROVIDER:-cuda}
      - NUM_THREADS=${PARAKEET_NUM_THREADS:-1}
      - LOG_LEVEL=${PARAKEET_LOG_LEVEL:-INFO}
    volumes:
      - ${PARAKEET_MODELS_DIR}:/models
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ["${PARAKEET_GPU:-0}"]
              capabilities: [gpu]
    networks:
      - tnet
    healthcheck:
      # Image ships wget (apt) but not curl — use wget so the check actually runs.
      test: ["CMD-SHELL", "wget -q -O /dev/null http://localhost:8000/healthz || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      # First boot may include a ~460 MB model download.
      start_period: 300s
    labels:
      - homepage.group=AI - Audio Tools
      - homepage.name=Parakeet ASR
      - homepage.icon=mdi-microphone
      - homepage.description=Parakeet-TDT speech-to-text via sherpa-onnx (fv-ml1 GPU 0)
      - homepage.href=http://10.251.50.54:${PARAKEET_PORT}

networks:
  tnet:
    name: traefik-net
    external: true