# speaches — OpenAI-compatible ASR (faster-whisper / CTranslate2) on irv-ml1.
#
# Consumer: Eyra (meeting recorder). Its hallucination gate keys on the
# per-segment `no_speech_prob` field returned by `response_format=verbose_json`,
# so that field surviving the API boundary is LOAD-BEARING, not cosmetic.
#
# API:
#   POST /v1/audio/transcriptions   — multipart; response_format=verbose_json
#   GET  /v1/models                 — registry of available STT models
#   GET  /health
#
# Coexists with the `parakeet` stack (:8765). Parakeet is a TDT/transducer model
# returning a bare {"text": ...} — it has no `no_speech_prob` concept at all, so
# it cannot serve this consumer. Two ASR services on one box is deliberate.
#
# All tunables live in .env — edit that, not this file.

services:
  speaches:
    image: ${SPEACHES_IMAGE}
    container_name: speaches
    restart: unless-stopped
    ports:
      - "${SPEACHES_BIND:-0.0.0.0}:${SPEACHES_PORT}:8000"
    environment:
      - UVICORN_HOST=0.0.0.0
      - UVICORN_PORT=8000
      - LOG_LEVEL=${SPEACHES_LOG_LEVEL:-info}
      # ── VAD: PINNED OFF at the consumer's explicit request ──────────────
      # Eyra VAD-gates upstream on the capture edge and sends only speech
      # segments. A second VAD here would re-chunk the audio and therefore
      # shift what `no_speech_prob` MEANS per segment, underneath a gate
      # calibrated against this stack.
      # ⚠ The upstream default is True, and the variable name is explicitly
      # marked unstable (leading underscore). That is exactly why
      # SPEACHES_IMAGE is pinned to a digest below — an unpinned bump could
      # silently rename this var, restoring VAD and moving the gate.
      - _UNSTABLE_VAD_FILTER=${SPEACHES_VAD_FILTER:-False}
      # ── Whisper / CTranslate2 ───────────────────────────────────────────
      # float16: irv-ml1 is Ampere (sm_86) — no native FP8/NVFP4, fp16 is the
      # correct compute type here. device_index 0 is the index INSIDE the
      # container, which the device_ids pin below maps to the A6000.
      - WHISPER__INFERENCE_DEVICE=cuda
      - WHISPER__DEVICE_INDEX=0
      - WHISPER__COMPUTE_TYPE=${SPEACHES_COMPUTE_TYPE:-float16}
      - WHISPER__NUM_WORKERS=${SPEACHES_NUM_WORKERS:-1}
      # ── Residency ───────────────────────────────────────────────────────
      # -1 = never unload. Deliberate: a mid-meeting model reload would be a
      # multi-second stall on a latency-sensitive draft-caption tier. Both
      # tiers resident is ~4.6 GB against 26 GB free on the A6000. Set to 300
      # (the upstream default) to trade that latency back for VRAM if the card
      # gets tight — e.g. when Eyra's diarization workload lands here.
      - STT_MODEL_TTL=${SPEACHES_STT_MODEL_TTL:--1}
      - ENABLE_UI=${SPEACHES_ENABLE_UI:-true}
      - PRELOAD_MODELS=${SPEACHES_PRELOAD_MODELS}
      - HF_HOME=/home/ubuntu/.cache/huggingface
    volumes:
      # Model cache persists across recreates so a bounce is not a re-download.
      - ${SPEACHES_CACHE_DIR}:/home/ubuntu/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              # "1" = RTX A6000 (verified empirically — nvidia-smi index 1;
              # note native CUDA on this host enumerates the A6000 as 0, the
              # docker view is what matters here). "0" would be the 3090,
              # which already hosts parakeet + the TTS stacks.
              device_ids: ["${SPEACHES_GPU_ID:-1}"]
              capabilities: [gpu]
    healthcheck:
      test: ["CMD-SHELL", "curl -fsS http://localhost:8000/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      # First boot downloads ~4.6 GB of CT2 weights for the two preloaded tiers.
      start_period: 600s
    labels:
      - homepage.group=AI - Audio Tools
      - homepage.name=Speaches ASR
      - homepage.icon=mdi-text-to-speech
      - homepage.description=OpenAI-compatible faster-whisper STT, verbose_json (irv-ml1)
      - homepage.href=http://10.100.79.3:${SPEACHES_PORT}