Merge pull request #2 from Sakura-RanChen/main

update: Dockerfile docker测试正常

Author: openrz

Dockerfile

@@ -0,0 +1,31 @@
+# 第一阶段：构建Python依赖
+FROM python:3.10-slim AS builder
+
+WORKDIR /app
+
+COPY requirements.txt .
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+# 第二阶段：生产镜像
+FROM python:3.10-slim
+
+WORKDIR /app
+
+# 安装系统依赖
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends libopus0 ffmpeg && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# 复制Python依赖
+COPY --from=builder /usr/local/lib/python3.10/site-packages /usr/local/lib/python3.10/site-packages
+
+# 复制应用代码
+COPY . .
+
+# 创建临时目录
+RUN mkdir -p /app/tmp
+
+# 启动应用
+CMD ["python", "app.py"]

app.py

@@ -37,7 +37,7 @@ def load_config():
 
 try:
     config = load_config()
-    API_TOKEN = config['server']['token']
+    API_TOKEN = config['server']['authorization']
 except Exception as e:
     logger.error(f"配置加载失败: {e}")
     raise
@@ -99,7 +99,7 @@ def ensure_16k_wav(audio_bytes):
 
 @app.post("/register", summary="声纹注册")
 async def register(
-    token: str = Header(..., description="接口令牌"),
+    authorization: str = Header(..., description="接口令牌", alias="authorization"),
     speaker_id: str = Form(..., description="说话人ID"),
     file: UploadFile = File(..., description="WAV音频文件")
 ):
@@ -112,7 +112,7 @@ async def register(
     返回:
         注册结果
     """
-    check_token(token)
+    check_token(authorization)
     audio_path = None
     try:
         audio_bytes = await file.read()
@@ -131,7 +131,7 @@ async def register(
 
 @app.post("/identify", summary="声纹识别")
 async def identify(
-    token: str = Header(..., description="接口令牌"),
+    authorization: str = Header(..., description="接口令牌", alias="authorization"),
     speaker_ids: str = Form(..., description="候选说话人ID，逗号分隔"),
     file: UploadFile = File(..., description="WAV音频文件")
 ):
@@ -144,7 +144,7 @@ async def identify(
     返回:
         识别结果（说话人ID、相似度分数）
     """
-    check_token(token)
+    check_token(authorization)
     candidate_ids = [x.strip() for x in speaker_ids.split(",") if x.strip()]
     if not candidate_ids:
         logger.warning("候选说话人ID不能为空。")

test_user.py

@@ -1,23 +1,23 @@
 import requests
 
-token = "123456"  # 替换为你的真实token
-base_url = "http://192.168.4.82:8000"
+authorization = "Bearer ac1ab7b959989135c030157ee5b73eb5"
+base_url = "http://192.168.81.200:8004"
 
 # # 注册三个说话人
 # for i in range(3):
 #     wav_path = f"test/test{i}.wav"
 #     speaker_id = f"user_{i}"    
 #     files = {'file': open(wav_path, 'rb')}
 #     data = {'speaker_id': speaker_id}
-#     headers = {'token': token}
+#     headers = {'authorization': authorization}
 #     resp = requests.post(f"{base_url}/register", files=files, data=data, headers=headers)
 #     print(f"注册 {speaker_id}:", resp.json())
 
 # 声纹识别
-wav_path = "test/test2.wav"
+wav_path = "test/test0.wav"
 candidate_ids = "user_0,user_1,user_2" 
 files = {'file': open(wav_path, 'rb')}
 data = {'speaker_ids': candidate_ids}
-headers = {'token': token}
+headers = {'authorization': authorization}
 resp = requests.post(f"{base_url}/identify", files=files, data=data, headers=headers)
 print("识别结果:", resp.json())

voiceprint.yaml

@@ -4,7 +4,7 @@ server:
   # 服务监听端口   
   port: 8004
   # 接口访问令牌，调用API时需在header中携带          
-  token: "your_api_token"  
+  authorization: "Bearer ac1ab7b959989135c030157ee5b73eb5"
 
 mysql:
   # MySQL数据库主机地址