qwenasr-qwen36-voxcmp2 base model. -2026/05/14 night

llm_server/README.md

@@ -0,0 +1,35 @@
+This bundle is self-contained for running `Qwen/Qwen3.6-35B-A3B-FP8` with
+`local/vllm-qwen36-nvfp4:v0.19.1-cu130` on another Spark machine.
+
+Contents:
+- `image/`: Docker image tarball
+- `modelscope/`: bundled ModelScope cache for the model weights
+- `chat_template.jinja`: chat template mounted into the container
+- `start_vllm.sh`: loads the image if needed and starts the container
+- `stop_vllm.sh`: stops the container
+
+Usage after extraction:
+
+```bash
+cd vllm-qwen36-bundle
+chmod +x start_vllm.sh stop_vllm.sh
+./start_vllm.sh
+```
+
+Optional overrides:
+- `HOST_PORT=8001 ./start_vllm.sh`
+- `CONTAINER_NAME=my-vllm ./start_vllm.sh`
+
+The startup script recreates the `Qwen/Qwen3.6-35B-A3B-FP8` symlink inside the
+bundled ModelScope cache so the bundle remains portable across machines.
+
+
+*************audio*************
+# 前台运行，Ctrl+C 直接停止
+./start_audio.sh
+
+# 后台运行
+nohup ./start_audio.sh > /dev/null 2>&1 &
+
+# 后台运行时用 stop 停止
+./stop_audio.sh

llm_server/chat_template.jinja

@@ -0,0 +1,123 @@
+{%- set enable_thinking = enable_thinking | default(false) %}
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {{- "<|vision_start|><|image_pad|><|vision_end|>" }}
+                {%- elif content.type == 'audio' or 'audio' in content or 'audio_url' in content %}
+                    {{- "<|audio_start|><|audio_pad|><|audio_end|>" }}
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {{- "<|vision_start|><|video_pad|><|vision_end|>" }}
+                {%- elif content.type == 'text' %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+    {%- endif %}
+    {{- '\n\n' }}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {{- '<|im_start|>system\n' +"<|vision_start|><|image_pad|><|vision_end|>"+ '<|im_end|>\n' }}
+                {%- elif content.type == 'audio' or 'audio' in content or 'audio_url' in content %}
+                    {{- '<|im_start|>system\n' +"<|audio_start|><|audio_pad|><|audio_end|>"+ '<|im_end|>\n' }}
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {{- '<|im_start|>system\n' +"<|vision_start|><|video_pad|><|vision_end|>"+ '<|im_end|>\n' }}
+                {%- elif content.type == 'text' %}
+                    {{- '<|im_start|>system\n' +content.text+ '<|im_end|>\n' }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = namespace(text="") %}
+        {%- for mcontent in message.content %}
+            {%- if mcontent.type == 'image' or 'image' in mcontent or 'image_url' in mcontent %}
+                {%- set content.text = content.text~"<|vision_start|><|image_pad|><|vision_end|>" %}
+            {%- elif mcontent.type == 'audio' or 'audio' in mcontent or 'audio_url' in mcontent %}
+                {%- set content.text = content.text~"<|audio_start|><|audio_pad|><|audio_end|>" %}
+            {%- elif mcontent.type == 'video' or 'video' in mcontent %}
+                {%- set content.text = content.text~"<|vision_start|><|video_pad|><|vision_end|>" %}
+            {%- elif mcontent.type == 'text' %}
+                {%- set content.text = content.text~mcontent.text %}
+            {%- endif %}
+        {%- endfor %}
+        {%- set content = content.text %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = "" %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+            {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+        {%- endif %}
+    {%- endif %}
+    {%- if loop.index0 > ns.last_query_index %}
+        {%- if loop.last or (not loop.last and reasoning_content) %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip("\n") + '\n</think>\n\n' + content.lstrip('\n') }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '\n' + content }}
+    {%- endif %}
+    {%- if message.tool_calls %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if (loop.first and content) or (not loop.first) %}{{- '\n' }}{%- endif %}
+            {%- if tool_call.function %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {%- if tool_call.arguments is string %}
+                {{- tool_call.arguments }}
+            {%- else %}
+                {{- tool_call.arguments | tojson }}
+            {%- endif %}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}{{- '<|im_start|>user' }}{%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}{{- '<|im_end|>\n' }}{%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}{{- '<think>\n\n</think>\n\n' }}{%- endif %}
+{%- endif %}

llm_server/speech_server.py

@@ -0,0 +1,87 @@
+from fastapi import FastAPI, UploadFile, Query
+from fastapi.responses import Response
+import io
+import numpy as np
+import soundfile as sf
+from contextlib import asynccontextmanager
+import torch
+import tempfile
+import os
+
+# 直接指定本地模型文件夹（绝对路径）
+BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+ASR_MODEL_PATH = os.path.join(BASE_DIR, "modelscope", "hub", "models", "Qwen", "Qwen3-ASR-1___7B")
+TTS_MODEL_PATH = os.path.join(BASE_DIR, "modelscope", "hub", "models", "OpenBMB", "VoxCPM2")
+
+models = {}
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    from transformers import BitsAndBytesConfig
+    quantization_asr_config = BitsAndBytesConfig(load_in_8bit=True)
+    
+    print(f"Loading ASR model from {ASR_MODEL_PATH} ...")
+    from qwen_asr import Qwen3ASRModel
+    models["asr"] = Qwen3ASRModel.from_pretrained(
+        ASR_MODEL_PATH,
+        dtype=torch.bfloat16,
+        device_map="cuda:0",
+        max_inference_batch_size=4,
+        attn_implementation="flash_attention_2",
+        max_new_tokens=512,
+        quantization_config=quantization_asr_config
+    )
+ 
+    from voxcpm import VoxCPM
+    models["tts"] = VoxCPM.from_pretrained(
+        TTS_MODEL_PATH,
+        load_denoiser=False,
+    )
+    models["tts_sample_rate"] = models["tts"].tts_model.sample_rate
+
+    print("ASR & TTS models loaded.")
+    yield
+    del models["asr"], models["tts"]
+
+app = FastAPI(lifespan=lifespan)
+
+@app.post("/asr")
+async def speech_to_text(file: UploadFile):
+    # 保存上传文件为临时 WAV
+    suffix = os.path.splitext(file.filename)[-1] or ".wav"
+    with tempfile.NamedTemporaryFile(suffix=suffix, delete=False) as tmp:
+        tmp.write(await file.read())
+        tmp_path = tmp.name
+
+    try:
+        # 调用 transcribe，这里直接使用自动语言检测
+        results = models["asr"].transcribe(
+            audio=[tmp_path],
+            language=None,           # 自动检测，或指定 ["Chinese", "English"]
+            return_time_stamps=False, # 如需时间戳可改为 True
+        )
+        # 取第一个结果（仅一个音频）
+        if results:
+            text = results[0].text
+        else:
+            text = ""
+    finally:
+        os.unlink(tmp_path)         # 清理临时文件
+
+    return {"text": text}
+
+@app.get("/tts")
+async def text_to_speech(text: str = Query(...)):
+    with torch.no_grad():
+        wav = models["tts"].generate(
+            text=text,
+            cfg_value=2.0,
+            inference_timesteps=10,
+       )
+    buffer = io.BytesIO()
+    sf.write(buffer, wav, models["tts_sample_rate"], format="WAV")
+    return Response(buffer.getvalue(), media_type="audio/wav")
+
+@app.get("/health")
+async def health():
+    return {"status": "ok", "models": list(models.keys())}

llm_server/start_asr.sh

@@ -0,0 +1,62 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# 配置区域（可根据实际情况修改）
+MODEL_BASE_PATH="${MODEL_BASE_PATH:-/mnt/Qwen3-Omni-30B-A3B-Instruct-NVFP4}"
+THINKER_PATH="${MODEL_BASE_PATH}/thinker"
+CONTAINER_NAME="${CONTAINER_NAME:-vllm-thinker}"
+HOST_PORT="${HOST_PORT:-8091}"
+GPU_DEVICES="${GPU_DEVICES:-all}"          # 例如 "0,1" 或 "all"
+TENSOR_PARALLEL_SIZE="${TENSOR_PARALLEL_SIZE:-1}"
+MAX_MODEL_LEN="${MAX_MODEL_LEN:-32768}"
+VLLM_IMAGE="${VLLM_IMAGE:-vllm/vllm-openai:latest}"
+
+# 检查模型路径是否存在
+if [[ ! -d "$THINKER_PATH" ]]; then
+  echo "错误: 模型路径不存在: $THINKER_PATH"
+  echo "请设置环境变量 MODEL_BASE_PATH 指向正确的模型根目录（包含 thinker 子目录）"
+  exit 1
+fi
+
+# 检查 Docker 可用性
+if command -v docker >/dev/null 2>&1 && docker info >/dev/null 2>&1; then
+  DOCKER_CMD="docker"
+else
+  DOCKER_CMD="sudo docker"
+fi
+
+# 停止并移除可能已存在的同名容器
+${DOCKER_CMD} rm -f "${CONTAINER_NAME}" >/dev/null 2>&1 || true
+
+echo "启动 Thinker 服务..."
+echo "模型路径: $THINKER_PATH"
+echo "服务端口: $HOST_PORT"
+echo "Tensor Parallel Size: $TENSOR_PARALLEL_SIZE"
+
+# 启动容器
+${DOCKER_CMD} run -d \
+  --name "${CONTAINER_NAME}" \
+  --gpus "${GPU_DEVICES}" \
+  --ipc=host \
+  --network host \
+  -v "${THINKER_PATH}:/model:ro" \
+  -e VLLM_USE_MODELSCOPE=false \
+  "${VLLM_IMAGE}" \
+  sh -c "pip install --no-cache-dir nvidia-modelopt && \
+         vllm serve /model \
+           --port ${HOST_PORT} \
+           --quantization modelopt_fp4 \
+           --dtype bfloat16 \
+           --max-model-len ${MAX_MODEL_LEN} \
+           --tensor-parallel-size ${TENSOR_PARALLEL_SIZE} \
+           --trust-remote-code \
+           --enforce-eager"
+
+# 等待服务启动
+sleep 3
+
+# 健康检查
+echo "健康检查 (等待几秒后):"
+echo "  curl http://127.0.0.1:${HOST_PORT}/health"
+echo "查看日志:"
+echo "  ${DOCKER_CMD} logs -f ${CONTAINER_NAME}"

llm_server/start_audio.sh

@@ -0,0 +1,26 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd -- "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+BUNDLE_DIR="${SCRIPT_DIR}"
+VENV_DIR="${BUNDLE_DIR}/.venv_audio"
+HOST_PORT="${HOST_PORT:-8100}"
+
+# 激活虚拟环境
+source "${VENV_DIR}/bin/activate"
+
+# 检查端口占用
+if lsof -i "tcp:${HOST_PORT}" -t >/dev/null 2>&1; then
+  echo "Port ${HOST_PORT} already in use" >&2
+  exit 1
+fi
+
+echo "Starting audio server on port ${HOST_PORT} ..."
+cd "${BUNDLE_DIR}"
+export MODELSCOPE_DOWNLOAD_MODE=local
+export MODELSCOPE_HUB_ENABLE_FILE_CHECK=false
+export MODELSCOPE_CACHE="${BUNDLE_DIR}/modelscope"
+# 强制 HuggingFace transformers 离线
+export HF_HUB_OFFLINE=1
+export TRANSFORMERS_OFFLINE=1
+uvicorn speech_server:app --host 0.0.0.0 --port "${HOST_PORT}" --log-level info

llm_server/start_vllm.sh

@@ -0,0 +1,81 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd -- "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+BUNDLE_DIR="${SCRIPT_DIR}"
+
+IMAGE_TAG="local/vllm-qwen36-nvfp4:v0.19.1-cu130"
+IMAGE_TAR="${BUNDLE_DIR}/image/vllm-qwen36-nvfp4_v0.19.1-cu130.tar"
+MODELSCOPE_DIR="${BUNDLE_DIR}/modelscope"
+CHAT_TEMPLATE="${BUNDLE_DIR}/chat_template.jinja"
+CONTAINER_NAME="${CONTAINER_NAME:-vllm-qwen36-nvfp4}"
+HOST_PORT="${HOST_PORT:-8000}"
+
+if command -v docker >/dev/null 2>&1 && docker info >/dev/null 2>&1; then
+  DOCKER=(docker)
+else
+  DOCKER=(sudo docker)
+fi
+
+require_path() {
+  local path="$1"
+  if [[ ! -e "${path}" ]]; then
+    echo "Missing required path: ${path}" >&2
+    exit 1
+  fi
+}
+
+require_path "${IMAGE_TAR}"
+require_path "${MODELSCOPE_DIR}"
+require_path "${CHAT_TEMPLATE}"
+
+mkdir -p "${MODELSCOPE_DIR}/hub/models/Qwen"
+
+MODEL_REAL_DIR="${MODELSCOPE_DIR}/hub/models/Qwen/Qwen3___6-35B-A3B-FP8"
+MODEL_LINK="${MODELSCOPE_DIR}/hub/models/Qwen/Qwen3.6-35B-A3B-FP8"
+
+require_path "${MODEL_REAL_DIR}"
+
+rm -f "${MODEL_LINK}"
+ln -s "Qwen3___6-35B-A3B-FP8" "${MODEL_LINK}"
+
+if ! "${DOCKER[@]}" image inspect "${IMAGE_TAG}" >/dev/null 2>&1; then
+  echo "Loading image ${IMAGE_TAG} from ${IMAGE_TAR}"
+  "${DOCKER[@]}" load -i "${IMAGE_TAR}"
+fi
+
+"${DOCKER[@]}" rm -f "${CONTAINER_NAME}" >/dev/null 2>&1 || true
+
+echo "Starting container ${CONTAINER_NAME} on port ${HOST_PORT}"
+"${DOCKER[@]}" run -d \
+  --name "${CONTAINER_NAME}" \
+  --gpus all \
+  --ipc=host \
+  --network host \
+  -e VLLM_USE_MODELSCOPE=true \
+  -v "${MODELSCOPE_DIR}:/root/.cache/modelscope" \
+  -v "${MODELSCOPE_DIR}:/home/liyh/.cache/modelscope" \
+  -v "${CHAT_TEMPLATE}:/root/chat_template.jinja:ro" \
+  "${IMAGE_TAG}" \
+  Qwen/Qwen3.6-35B-A3B-FP8 \
+  --port "${HOST_PORT}" \
+  --tensor-parallel-size 1 \
+  --max-model-len 131072 \
+  --reasoning-parser qwen3 \
+  --enable-auto-tool-choice \
+  --tool-call-parser qwen3_coder \
+  --api-key semi-ai.tech \
+  --enable-prefix-caching \
+  --max_num_batched_tokens 4096 \
+  --max_num_seqs 8 \
+  --kv-cache-dtype fp8_e4m3 \
+  --chat-template /root/chat_template.jinja \
+  --safetensors-load-strategy eager \
+  --gpu-memory-utilization 0.75\
+  "$@"
+
+echo
+echo "Health check:"
+echo "  curl http://127.0.0.1:${HOST_PORT}/health"
+echo "Logs:"
+echo "  ${DOCKER[*]} logs -f ${CONTAINER_NAME}"

llm_server/stop_asr.sh

@@ -0,0 +1,14 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+CONTAINER_NAME="${CONTAINER_NAME:-vllm-thinker}"
+
+if command -v docker >/dev/null 2>&1 && docker info >/dev/null 2>&1; then
+  DOCKER_CMD="docker"
+else
+  DOCKER_CMD="sudo docker"
+fi
+
+echo "停止并移除容器: $CONTAINER_NAME"
+${DOCKER_CMD} rm -f "${CONTAINER_NAME}" >/dev/null 2>&1 || true
+echo "已停止"

llm_server/stop_audio.sh

@@ -0,0 +1,14 @@
+#!usrbinenv bash
+set -euo pipefail
+
+HOST_PORT=${HOST_PORT-8100}
+
+PID=$(lsof -i tcp${HOST_PORT} -t 2devnull  true)
+
+if [[ -z ${PID} ]]; then
+  echo No process found on port ${HOST_PORT}
+  exit 0
+fi
+
+echo Stopping audio server (PID ${PID}) ...
+kill ${PID}

llm_server/stop_vllm.sh

@@ -0,0 +1,13 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+CONTAINER_NAME="${CONTAINER_NAME:-vllm-qwen36-nvfp4}"
+
+if command -v docker >/dev/null 2>&1 && docker info >/dev/null 2>&1; then
+  DOCKER=(docker)
+else
+  DOCKER=(sudo docker)
+fi
+
+"${DOCKER[@]}" rm -f "${CONTAINER_NAME}" >/dev/null 2>&1 || true
+echo "Stopped ${CONTAINER_NAME}"

llm_server/test.py

@@ -0,0 +1,148 @@
+#!/usr/bin/env python3
+"""
+语音服务功能测试：ASR 识别 + TTS 合成
+"""
+import requests
+import json
+import os
+import sys
+import time
+
+HOST = "http://127.0.0.1:8100"
+
+def test_health():
+    """1. 健康检查"""
+    print("=" * 50)
+    print("📋 健康检查")
+    print("=" * 50)
+    resp = requests.get(f"{HOST}/health")
+    print(f"状态码: {resp.status_code}")
+    print(f"模型列表: {resp.json()}")
+    assert resp.status_code == 200
+    assert "asr" in resp.json()["models"]
+    assert "tts" in resp.json()["models"]
+    print("✅ 健康检查通过\n")
+
+def test_asr(audio_path=None):
+    """2. 测试语音识别"""
+    print("=" * 50)
+    print("🎤 语音识别测试")
+    print("=" * 50)
+    
+    if audio_path is None:
+        # 如果没有本地音频，下载一个公开示例
+        import tempfile
+        audio_path = tempfile.mktemp(suffix=".wav")
+        url = "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_zh.wav"
+        print(f"下载测试音频: {url}")
+        import subprocess
+        subprocess.run(["wget", "-q", url, "-O", audio_path], check=True)
+    
+    print(f"音频文件: {audio_path}")
+    with open(audio_path, "rb") as f:
+        resp = requests.post(f"{HOST}/asr", files={"file": f})
+    
+    print(f"状态码: {resp.status_code}")
+    result = resp.json()
+    print(f"识别结果: {result.get('text', 'N/A')}")
+    assert resp.status_code == 200
+    assert len(result.get("text", "")) > 0
+    print("✅ 语音识别通过\n")
+    return result["text"]
+
+def test_tts(text="(激动地说)你好世界，这是一段测试语音", output="test_output.wav"):
+    """3. 测试语音合成"""
+    print("=" * 50)
+    print("🔊 语音合成测试")
+    print("=" * 50)
+    print(f"合成文本: {text}")
+    
+    start_time = time.time()
+    resp = requests.get(f"{HOST}/tts", params={"text": text})
+    elapsed = time.time() - start_time
+    
+    print(f"状态码: {resp.status_code}")
+    print(f"耗时: {elapsed:.2f}秒")
+    
+    if resp.status_code == 200:
+        with open(output, "wb") as f:
+            f.write(resp.content)
+        file_size = os.path.getsize(output) / 1024  # KB
+        print(f"音频已保存: {output} ({file_size:.1f} KB)")
+    else:
+        print(f"错误: {resp.text}")
+    
+    assert resp.status_code == 200
+    assert os.path.exists(output)
+    print("✅ 语音合成通过\n")
+
+def test_asr_english():
+    """4. 测试英文识别"""
+    print("=" * 50)
+    print("🌍 英文识别测试")
+    print("=" * 50)
+    
+    import tempfile
+    audio_path = tempfile.mktemp(suffix=".wav")
+    url = "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav"
+    print(f"下载英文测试音频: {url}")
+    import subprocess
+    subprocess.run(["wget", "-q", url, "-O", audio_path], check=True)
+    
+    with open(audio_path, "rb") as f:
+        resp = requests.post(f"{HOST}/asr", files={"file": f})
+    
+    print(f"状态码: {resp.status_code}")
+    result = resp.json()
+    print(f"识别结果: {result.get('text', 'N/A')}")
+    assert resp.status_code == 200
+    assert len(result.get("text", "")) > 0
+    print("✅ 英文识别通过\n")
+
+def test_tts_long_text():
+    """5. 测试长文本合成"""
+    print("=" * 50)
+    print("📜 长文本合成测试")
+    print("=" * 50)
+    
+    long_text = """人工智能是计算机科学的一个分支，它企图了解智能的实质，
+    并生产出一种新的能以人类智能相似的方式做出反应的智能机器，
+    该领域的研究包括机器人、语言识别、图像识别、自然语言处理和专家系统等。"""
+    
+    print(f"文本长度: {len(long_text)} 字")
+    start_time = time.time()
+    resp = requests.get(f"{HOST}/tts", params={"text": long_text})
+    elapsed = time.time() - start_time
+    
+    print(f"状态码: {resp.status_code}")
+    print(f"耗时: {elapsed:.2f}秒")
+    
+    if resp.status_code == 200:
+        output = "test_long_output.wav"
+        with open(output, "wb") as f:
+            f.write(resp.content)
+        file_size = os.path.getsize(output) / 1024
+        print(f"音频已保存: {output} ({file_size:.1f} KB)")
+    
+    assert resp.status_code == 200
+    print("✅ 长文本合成通过\n")
+
+if __name__ == "__main__":
+    print("\n" + "🚀 开始测试语音服务".center(50, "="))
+    print(f"服务地址: {HOST}\n")
+    
+    try:
+        test_health()
+        
+        # 可选：用自己的音频文件测试
+        # test_asr("/path/to/your/audio.wav")
+        test_asr()
+        test_asr_english()
+        
+        test_tts()
+        test_tts_long_text()
+        
+        print("\n" + "🎉 所有测试通过！".center(50, "="))
+    except Exception as e:
+        print(f"\n❌ 测试失败: {e}")
+        sys.exit(1)