# Parakeet ASR via NeMo torch (unified-en-0.6b, bf16 weights) + our own thin FastAPI wrapper.
#
# Replacement seat for stacks/parakeet (sherpa-onnx int8). Same port (:8300), same endpoints,
# same body — LiteLLM and `talk` need no change. Rollback: stop this container, start the old
# `parakeet` one (kept; container and image both intact).
#
# HOST: fv-ml1, GPU 0.
#
# ⚠ GPU 0 room came from gen-small's util SLACK, not its KV: util went 0.48 -> 0.36 (now 0.33 in its .env),
# and the KV is byte-pinned (unchanged at 670,142 tokens). Plan GPU 0 against this seat's STEADY STATE of
# 3,582 MiB (the torch cache after a long, windowed request), not its at-rest figure; that leaves Free ~385 MiB
# (the old seat held 1,690 MiB). Do not raise that util back without re-measuring nvidia-smi Free
# on GPU 0 — util does not predict resident VRAM (see the 09-15 note in gen-small-seat/.env).
#
# ⚠ Weights: /tank/aimodels/huggingface mounted READ-ONLY. nvidia/parakeet-unified-en-0.6b @
# fe53cd885760c96b6a5f51a0bfd362cb4584a98b. HF_HUB_OFFLINE=1 in the image: the seat never phones home.
#
# API (identical to the replaced seat):
#   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-nemo:
    image: local/parakeet-nemo:${PARAKEET_NEMO_TAG}
    container_name: parakeet-nemo
    restart: unless-stopped
    ports:
      - "${PARAKEET_NEMO_BIND:-0.0.0.0}:${PARAKEET_NEMO_PORT}:8000"
    environment:
      - MODEL_PATH=/hf/hub/models--nvidia--parakeet-unified-en-0.6b/snapshots/${PARAKEET_NEMO_REV}/parakeet-unified-en-0.6b.nemo
      - WARMUP_SECONDS=${PARAKEET_NEMO_WARMUP:-1,8,60}
      # CUDA graphs pin memory in torch's cache, which fights the empty_cache the windowed path
      # needs to return memory to GPU 0's neighbours (illegal-memory-access wedge, 2026-10-01).
      - CUDA_GRAPHS=${PARAKEET_NEMO_CUDA_GRAPHS:-0}
      - MEM_CAP_MIB=${PARAKEET_NEMO_MEM_CAP_MIB:-3840}
      - WINDOW_S=${PARAKEET_NEMO_WINDOW_S:-360}
      - LOG_LEVEL=${PARAKEET_NEMO_LOG_LEVEL:-INFO}
    volumes:
      - /tank/aimodels/huggingface:/hf:ro
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ["${PARAKEET_NEMO_GPU:-0}"]
              capabilities: [gpu]
    networks:
      - tnet
    healthcheck:
      test: ["CMD-SHELL", "wget -q -O /dev/null http://localhost:8000/healthz || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      # Import-time model load + three warm-up decodes; no download (weights are mounted).
      start_period: 240s
    labels:
      - homepage.group=AI - Audio Tools
      - homepage.name=Parakeet ASR (NeMo)
      - homepage.icon=mdi-microphone
      - homepage.description=Parakeet-unified-en speech-to-text via NeMo bf16 (fv-ml1 GPU 0)
      - homepage.href=http://10.251.50.54:${PARAKEET_NEMO_PORT}

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