# Parakeet ASR stack tunables. Copy to `.env` on fv-ml1 before deploying.
#
#   cp .env.example .env
#   # edit as needed
#   docker compose build
#   docker compose up -d

# Image tag. Bump when you change the Dockerfile / app.py so docker caches
# cleanly.
PARAKEET_TAG=sherpa-onnx-v4

# Which GPU to pin. The container sees whichever card this names as cuda:0.
#
# ⚠ GPU 0, deliberately, NOT the empty GPU 3. This seat is ~800 MiB and GPU 0 has
# the most uncommitted headroom of the three working cards (its seats commit
# util 0.88, ~13 GB spare; GPU 1 is at 0.975, GPU 2 at 0.96). Leaving GPU 3
# untouched keeps a full 96 GB card available for a real seat — vLLM sizes KV
# cache against TOTAL VRAM, so even a 1 GB tenant eats into a big seat's margin.
PARAKEET_GPU=0

# Host port for the FastAPI server (container listens on 8000). 8300 is
# fv-ml1's established parakeet port; the 80xx range belongs to the vLLM seats.
PARAKEET_PORT=8300

# Bind address. 0.0.0.0 exposes on all interfaces. Use 127.0.0.1 to restrict
# to local-only — but LiteLLM on ana-docker reaches this over the LAN, so it
# has to be 0.0.0.0 for the gateway alias to work.
PARAKEET_BIND=0.0.0.0

# Host path for the ONNX model files — encoder/decoder/joiner/tokens.txt.
# Downloaded by the entrypoint on first run if absent. Must exist before
# first `up` (directory, not files). Regenerable — exclude from restic.
PARAKEET_MODELS_DIR=/tank/parakeet/models

# Which sherpa-onnx release tarball to fetch on first boot.
#   v3 (default, 464 MiB) — 25 European languages
#   v2                    — English only, swap the URL below
# https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-nemo-parakeet-tdt-0.6b-v2-int8.tar.bz2
PARAKEET_MODEL_URL=https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-nemo-parakeet-tdt-0.6b-v3-int8.tar.bz2

# ONNX Runtime execution provider. `cuda` uses the GPU (requires the nvidia
# container runtime + matching CUDA/cuDNN in the image). `cpu` falls back to
# CPU.
#
# ⚠ ORT's CUDA EP FALLS BACK TO CPU SILENTLY when it cannot initialise — the
# server still answers 200 and still returns correct text, just slowly. So
# `PROVIDER=cuda` is a REQUEST, not a guarantee, and the only honest check is
# to watch `nvidia-smi` during a transcription and confirm a process appears on
# the pinned card. See README § Verifying the GPU is actually in use.
PARAKEET_PROVIDER=cuda

# CPU threads per recognizer session. Irrelevant when provider=cuda;
# only matters for provider=cpu.
PARAKEET_NUM_THREADS=1

# Log level: DEBUG | INFO | WARNING | ERROR
PARAKEET_LOG_LEVEL=INFO