Kleineres Modell

scripts/download_qwen3_tts_base.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+set -euo pipefail
+cd "$(dirname "$0")"
+MODEL="${QWEN3_TTS_BASE_MODEL:-Qwen/Qwen3-TTS-12Hz-1.7B-Base}"
+CACHE_ROOT="/home/guru/vllm/data/root"
+mkdir -p "$CACHE_ROOT/.cache/huggingface"
+
+printf "Lade %s in gemeinsamen Container-Cache...\n" "$MODEL"
+docker run --rm \
+  -e HF_HOME=/root/.cache/huggingface \
+  -v "$CACHE_ROOT:/root" \
+  vllm/vllm-omni:latest-aarch64 \
+  python3 -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id='$MODEL')"
+
+printf "Fertig. Danach: ./start_dialog_tts.sh\n"