feat: add real-time caption CLI prototype with Qwen3-ASR

Add a C++/Qt6/CMake CLI prototype that captures the default sink
monitor through libpulse and transcribes it in-process with Qwen3-ASR
via libllama/libmtmd. Add phase 0/1 verification docs.

新增实时字幕命令行原型：libpulse 采集默认输出 monitor，进程内用
libllama/libmtmd 跑 Qwen3-ASR 推理。附阶段 0/1 验证文档。

experiments/phase0/bench.sh

@@ -0,0 +1,39 @@
+#!/usr/bin/env bash
+# Phase 0 验证脚本：用 llama.cpp + Qwen3-ASR 转写一段音频并测 RTF
+#
+# 依赖（本机验证环境：Deepin 25 / Qt 6.8 / x86_64）：
+#   libllama0, libllama-dev, libggml0, libggml-dev, libmtmd  （系统自带 9951+dfsg-1deepin1）
+#   llama.cpp-tools 的二进制（本脚本从 deb 解包到 LLAMA_TOOLS，不需要 root 安装）
+#
+# 用法: ./bench.sh <audio.wav> [prompt]        # prompt 默认 <__media__>
+# 可选环境变量: THREADS / MODEL / MMPROJ / LLAMA_TOOLS / LLAMA_LIBDIR / TMO
+set -uo pipefail
+
+LLAMA_TOOLS="${LLAMA_TOOLS:-/tmp/opencode/llama-tools}"
+LLAMA_LIBDIR="${LLAMA_LIBDIR:-/usr/lib/x86_64-linux-gnu/llama}"
+MODEL="${MODEL:-/tmp/opencode/models/Qwen3-ASR-0.6B-Q8_0.gguf}"
+MMPROJ="${MMPROJ:-/tmp/opencode/models/mmproj-Qwen3-ASR-0.6B-Q8_0.gguf}"
+AUDIO="${1:?usage: bench.sh <audio> [prompt]}"
+PROMPT="${2:-<__media__>}"
+THREADS="${THREADS:-8}"
+CLI="$LLAMA_TOOLS/usr/bin/llama-cli"
+
+export LD_LIBRARY_PATH="$LLAMA_LIBDIR:$LLAMA_TOOLS/usr/lib/x86_64-linux-gnu/llama"
+
+dur=$(ffprobe -v error -show_entries format=duration -of csv=p=0 "$AUDIO")
+printf '音频: %s (%ss)  模型: %s  线程: %s\n' "$AUDIO" "$dur" "$(basename "$MODEL")" "$THREADS"
+
+# 关键: stdin 必须接 /dev/null 并在外层套 timeout
+# 否则 llama-cli 生成完会回到 stdin 读取循环而挂住
+t0=$(date +%s.%N)
+timeout "${TMO:-300}" "$CLI" -m "$MODEL" --mmproj "$MMPROJ" --audio "$AUDIO" \
+       -p "$PROMPT" -n 256 --temp 0 -t "$THREADS" -st --simple-io \
+       </dev/null >/tmp/lc_out.log 2>/tmp/lc_err.log
+rc=$?
+t1=$(date +%s.%N)
+
+[ "$rc" = 124 ] && echo "(警告: 被 timeout 杀掉)"
+echo "---- 转写结果 ----"
+cat /tmp/lc_out.log
+echo "---- 计时 ----"
+python3 -c "print(f'墙钟总耗时: {$t1-$t0:.2f}s  音频: $dur s  →  RTF(含加载) ≈ {($t1-$t0)/$dur:.3f}')"