#!/usr/bin/env bash
# ============================================================================
# Install a dedicated MeloTTS (Korean voice) venv at /opt/melo.
#
# Why a SEPARATE venv (not the brain-bridge /opt/venv):
#   - MeloTTS pins old deps (transformers 4.27.4 / tokenizers 0.13.3 / fugashi)
#     whose binary wheels exist only for cp311, so we use python3.11 here even
#     though the image's default interpreter is 3.12.
#   - It isolates the heavy torch/transformers stack from the slim bridge env,
#     which pins numpy<2 for faster-whisper.
#
# torch is the CUDA (cu128) build so MeloTTS runs on the GPU alongside Ollama +
# Whisper. CPU synth serialised under concurrent load (whisper STT + bot) and
# blew TTS up to 7-8s per reply; on the GPU a sentence synthesises in ~0.3s.
# cu128 is the Blackwell (sm_120) wheel verified on this host's RTX 5050.
# The worker selects the device via MELO_DEVICE=cuda (compose).
# ============================================================================
set -euxo pipefail

export DEBIAN_FRONTEND=noninteractive

apt-get update
# Build deps for fugashi / mecab-python3 + a system MeCab dict, plus python3.11.
apt-get install -y --no-install-recommends \
    software-properties-common build-essential pkg-config swig \
    libmecab-dev mecab mecab-ipadic-utf8
add-apt-repository -y ppa:deadsnakes/ppa
apt-get update
apt-get install -y --no-install-recommends python3.11 python3.11-venv python3.11-dev
rm -rf /var/lib/apt/lists/*

python3.11 -m venv /opt/melo
/opt/melo/bin/pip install --no-cache-dir --upgrade pip wheel setuptools

# CUDA (cu128) torch first, so MeloTTS's unpinned `torch` dep is already
# satisfied with the GPU build. Pinned to the Blackwell-verified versions
# (2.11.0+cu128) for reproducible rebuilds.
/opt/melo/bin/pip install --no-cache-dir torch==2.11.0+cu128 torchaudio==2.11.0+cu128 \
    --index-url https://download.pytorch.org/whl/cu128

# MeloTTS from GitHub. The PyPI sdist is broken (its setup.py reads a
# requirements.txt that is not shipped in the sdist), so install from the repo.
# Pinned to a commit (not refs/heads/main) so rebuilds are reproducible.
/opt/melo/bin/pip install --no-cache-dir \
    "https://github.com/myshell-ai/MeloTTS/archive/209145371cff8fc3bd60d7be902ea69cbdb7965a.tar.gz"

# Korean g2p backend. MeloTTS otherwise tries to pip-install this on the first
# Korean request, which fails in a network-isolated container at runtime.
/opt/melo/bin/pip install --no-cache-dir python-mecab-ko python-mecab-ko-dic

# Remove the full `unidic` package (its dictionary is never downloaded, only a
# stub) so mecab-python3 falls back to the bundled `unidic_lite` dict. Without
# this, importing melo's Japanese module fails with a missing-mecabrc error.
/opt/melo/bin/pip uninstall -y unidic || true

# Pre-cache every model asset MeloTTS pulls at runtime, so the worker starts
# offline and the first Discord turn pays no download cost. Importing melo.api
# fetches the Japanese (tohoku-nlp/bert-base-japanese-v3) and Korean
# (kykim/bert-kor-base) BERT tokenizers plus nltk g2p data; loading the KR voice
# downloads the OpenVoice KR config+checkpoint, and a real synth pulls the
# Korean BERT weights. All of these go through huggingface_hub.
#
# CRITICAL: at runtime docker-compose mounts the `whisper_cache` named volume
# over /root/.cache/huggingface (for faster-whisper). That volume would SHADOW
# anything baked into the default HF cache, so we pin the melo worker to a
# DEDICATED, non-volume cache dir (/opt/melo-cache) here AND in supervisord, and
# warm it once. nltk_data (/root/nltk_data) is not volume-mounted so it stays.
export HF_HOME=/opt/melo-cache
mkdir -p "$HF_HOME"
MELO_LANGUAGE=KR HF_HOME=/opt/melo-cache /opt/melo/bin/python - <<'PY'
import tempfile
from melo.api import TTS

model = TTS(language="KR", device="cpu")
out = tempfile.mktemp(suffix=".wav")
model.tts_to_file("초기화 워밍업입니다.", model.hps.data.spk2id["KR"], out, speed=1.5)
print("[setup-melo] warm-up KR synth OK ->", out)
PY

echo "[setup-melo] MeloTTS venv ready at /opt/melo"