99 lines
3.2 KiB
Bash
99 lines
3.2 KiB
Bash
 
|
#!/usr/bin/env bash
|
||
|
|
# Create the isolated environment for the Polish number normalizer.
|
||
|
|
#
|
||
|
|
# ./setup.sh venv + dependencies
|
||
|
|
# ./setup.sh --model also download the model (needs HF_TOKEN)
|
||
|
|
# ./setup.sh --cpu CPU-only torch, for a machine without an NVIDIA GPU
|
||
|
|
#
|
||
|
|
# Kept separate from the ComfyUI environment on purpose: this needs
|
||
|
|
# transformers >= 5, and the TTS install must not be disturbed.
|
||
|
|
|
||
|
|
set -euo pipefail
|
||
|
|
|
||
|
|
HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||
|
|
VENV="$HERE/venv"
|
||
|
|
MODEL_DIR="$HERE/model"
|
||
|
|
MODEL_REPO="Folx/qwen3-0.6b-pl-text-normalization"
|
||
|
|
TORCH_INDEX="https://download.pytorch.org/whl/cu128" # same wheels as ComfyUI
|
||
|
|
|
||
|
|
WANT_MODEL=0
|
||
|
|
CPU_ONLY=0
|
||
|
|
for arg in "$@"; do
|
||
|
|
case "$arg" in
|
||
|
|
--model) WANT_MODEL=1 ;;
|
||
|
|
--cpu) CPU_ONLY=1 ;;
|
||
|
|
-h|--help) sed -n '2,10p' "${BASH_SOURCE[0]}" | sed 's/^# \?//'; exit 0 ;;
|
||
|
|
*) echo "Unknown option: $arg" >&2; exit 2 ;;
|
||
|
|
esac
|
||
|
|
done
|
||
|
|
|
||
|
|
say() { printf '\n\033[1;36m==> %s\033[0m\n' "$1"; }
|
||
|
|
|
||
|
|
say "Creating $VENV"
|
||
|
|
python3 -m venv "$VENV"
|
||
|
|
"$VENV/bin/pip" install --upgrade pip --quiet
|
||
|
|
|
||
|
|
say "Installing torch"
|
||
|
|
if [ "$CPU_ONLY" = 1 ]; then
|
||
|
|
"$VENV/bin/pip" install torch --index-url https://download.pytorch.org/whl/cpu
|
||
|
|
else
|
||
|
|
"$VENV/bin/pip" install torch --index-url "$TORCH_INDEX"
|
||
|
|
fi
|
||
|
|
|
||
|
|
say "Installing transformers, accelerate, num2words"
|
||
|
|
"$VENV/bin/pip" install "transformers>=5.0.0" "accelerate>=0.26.0" "num2words>=0.5.13"
|
||
|
|
|
||
|
|
if [ "$WANT_MODEL" = 1 ]; then
|
||
|
|
say "Downloading $MODEL_REPO"
|
||
|
|
"$VENV/bin/pip" install --quiet "huggingface_hub[cli]"
|
||
|
|
|
||
|
|
# Either an HF_TOKEN in the environment or a stored `hf auth login` works;
|
||
|
|
# the CLI picks up both on its own. Only say something when there is
|
||
|
|
# neither, because the failure then is a confusing "access denied".
|
||
|
|
if [ -z "${HF_TOKEN:-}" ] && ! "$VENV/bin/hf" auth whoami >/dev/null 2>&1; then
|
||
|
|
cat >&2 <<EOF
|
||
|
|
No Hugging Face credentials. The repo is gated (approval is automatic, but it
|
||
|
|
has to be your account that asks):
|
||
|
|
|
||
|
|
1. Open https://huggingface.co/$MODEL_REPO while signed in and accept the terms
|
||
|
|
2. Either $VENV/bin/hf auth login
|
||
|
|
or HF_TOKEN=hf_... $0 --model
|
||
|
|
|
||
|
|
EOF
|
||
|
|
exit 1
|
||
|
|
fi
|
||
|
|
"$VENV/bin/hf" download "$MODEL_REPO" --local-dir "$MODEL_DIR"
|
||
|
|
fi
|
||
|
|
|
||
|
|
say "Checking the installation"
|
||
|
|
"$VENV/bin/python" - <<'PY'
|
||
|
|
import sys
|
||
|
|
try:
|
||
|
|
import torch, transformers
|
||
|
|
print(f" torch {torch.__version__} cuda_available={torch.cuda.is_available()}")
|
||
|
|
if torch.cuda.is_available():
|
||
|
|
print(f" device: {torch.cuda.get_device_name(0)}")
|
||
|
|
print(f" transformers {transformers.__version__}")
|
||
|
|
if int(transformers.__version__.split('.')[0]) < 5:
|
||
|
|
print(" WARNING: transformers < 5 produces wrong output with this model",
|
||
|
|
file=sys.stderr)
|
||
|
|
except ImportError as exc:
|
||
|
|
print(f" {exc}", file=sys.stderr); sys.exit(1)
|
||
|
|
PY
|
||
|
|
|
||
|
|
"$VENV/bin/python" "$HERE/normalizer.py" --status
|
||
|
|
|
||
|
|
if [ ! -f "$MODEL_DIR/config.json" ]; then
|
||
|
|
cat <<EOF
|
||
|
|
|
||
|
|
The environment is ready, but the model is not downloaded yet, so the
|
||
|
|
normalizer will run on the degraded num2words fallback.
|
||
|
|
|
||
|
|
1. Accept the terms at https://huggingface.co/$MODEL_REPO
|
||
|
|
2. HF_TOKEN=hf_... $HERE/setup.sh --model
|
||
|
|
|
||
|
|
EOF
|
||
|
|
else
|
||
|
|
say "Ready. Try: $VENV/bin/python $HERE/normalizer.py 'Wygrał 1247 złotych.'"
|
||
|
|
fi
|