# Parakeet ASR stack tunables. Copy to `.env` on irv-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-v2

# Host port for the FastAPI server (container listens on 8000)
PARAKEET_PORT=8765

# Bind address. 0.0.0.0 exposes on all interfaces including the WG tunnel IP
# (10.100.79.3). Use 127.0.0.1 to restrict to local-only.
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).
PARAKEET_MODELS_DIR=/worktank/parakeet/models

# Which sherpa-onnx release tarball to fetch on first boot. Default is the
# int8-quantized English-only v2 (~400 MB). Switch to the v3 tarball below
# to cover 25 European languages at a similar size:
#   https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-nemo-parakeet-tdt-0.6b-v3-int8.tar.bz2
PARAKEET_MODEL_URL=https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-nemo-parakeet-tdt-0.6b-v2-int8.tar.bz2

# ONNX Runtime execution provider. `cuda` uses the GPU (requires nvidia
# runtime + matching CUDA/cuDNN in the image). `cpu` falls back to CPU —
# fine for low-volume dev use; ~4-8× slower on this host.
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