mirror of
https://github.com/xinnan-tech/xiaozhi-esp32-server.git
synced 2026-07-27 09:33:55 +08:00
重新划分目录 (#214)
* 🦄 refactor(web): 修改zhikongtaiweb到web * 🦄 refactor: 重写前端 路由守护尚未写完 * 🦄 refactor: 标准化路由 * update:前端重写，保留后端 * update:添加前端代码 * update:pip转成poetry启动 * update:增加mem0ai包依赖 * update:文档增加mem0ai的描述 * feat: play online mp3 (#181) Co-authored-by: 欣南科技 <huangrongzhuang@xin-nan.com> * 修改前端代码 * update:调整项目目录 * update:优化 * update:配置文件去除8002端口 * update:增加开发说明 * update:更新开发协议 --------- Co-authored-by: kalicyh <34980061+kaliCYH@users.noreply.github.com> Co-authored-by: hrz <1710360675@qq.com> Co-authored-by: freshlife001 <talent@mises.site> Co-authored-by: CGD <3030332422@qq.com>
This commit is contained in:
欣南科技
co-authored by
kalicyh
hrz
freshlife001
CGD
kalicyh
hrz
freshlife001
CGD
parent
8b151d07c2
commit
0e43748fdc
@@ -0,0 +1,24 @@
|
||||
import importlib
|
||||
import logging
|
||||
import os
|
||||
import sys
|
||||
import time
|
||||
import wave
|
||||
import uuid
|
||||
from abc import ABC, abstractmethod
|
||||
from typing import Optional, Tuple, List
|
||||
from core.providers.asr.base import ASRProviderBase
|
||||
from config.logger import setup_logging
|
||||
|
||||
TAG = __name__
|
||||
logger = setup_logging()
|
||||
|
||||
def create_instance(class_name: str, *args, **kwargs) -> ASRProviderBase:
|
||||
"""工厂方法创建ASR实例"""
|
||||
if os.path.exists(os.path.join('core', 'providers', 'asr', f'{class_name}.py')):
|
||||
lib_name = f'core.providers.asr.{class_name}'
|
||||
if lib_name not in sys.modules:
|
||||
sys.modules[lib_name] = importlib.import_module(f'{lib_name}')
|
||||
return sys.modules[lib_name].ASRProvider(*args, **kwargs)
|
||||
|
||||
raise ValueError(f"不支持的ASR类型: {class_name}，请检查该配置的type是否设置正确")
|
||||
@@ -0,0 +1,97 @@
|
||||
import random
|
||||
import threading
|
||||
import time
|
||||
from typing import Set
|
||||
|
||||
class AuthCodeGenerator:
|
||||
_instance = None
|
||||
_instance_lock = threading.Lock()
|
||||
|
||||
def __new__(cls):
|
||||
if not cls._instance:
|
||||
with cls._instance_lock:
|
||||
if not cls._instance:
|
||||
cls._instance = super(AuthCodeGenerator, cls).__new__(cls)
|
||||
# 初始化随机种子
|
||||
random.seed(time.time())
|
||||
return cls._instance
|
||||
|
||||
def __init__(self):
|
||||
# 确保 __init__ 只被调用一次
|
||||
if not hasattr(self, '_initialized'):
|
||||
self._used_codes: Set[str] = set()
|
||||
self._code_timestamps = {}
|
||||
self._lock = threading.Lock()
|
||||
self._code_timeout = 3 * 24 * 60 * 60
|
||||
self._initialized = True
|
||||
|
||||
@classmethod
|
||||
def get_instance(cls):
|
||||
"""获取AuthCodeGenerator的单例实例"""
|
||||
return cls()
|
||||
|
||||
def generate_code(self) -> str:
|
||||
"""
|
||||
生成6位数字认证码，确保不重复
|
||||
返回: 6位数字字符串
|
||||
"""
|
||||
with self._lock:
|
||||
self._clean_expired_codes() # 清理过期code
|
||||
while True:
|
||||
# 使用时间戳和已用码数量作为种子，确保每次生成不同的随机数
|
||||
seed = int(time.time() * 1000) + len(self._used_codes)
|
||||
random.seed(seed)
|
||||
|
||||
# 生成6位随机数字
|
||||
code = ''.join(str(random.randint(0, 9)) for _ in range(6))
|
||||
|
||||
# 检查是否已存在
|
||||
if code not in self._used_codes:
|
||||
self._used_codes.add(code)
|
||||
self._code_timestamps[code] = time.time()
|
||||
return code
|
||||
|
||||
def remove_code(self, code: str) -> bool:
|
||||
"""
|
||||
删除已使用的认证码
|
||||
参数:
|
||||
code: 要删除的认证码
|
||||
返回:
|
||||
bool: 删除成功返回True，码不存在返回False
|
||||
"""
|
||||
print('remove_code', code)
|
||||
with self._lock:
|
||||
if code in self._used_codes:
|
||||
self._used_codes.remove(code)
|
||||
if code in self._code_timestamps:
|
||||
del self._code_timestamps[code]
|
||||
return True
|
||||
return False
|
||||
|
||||
def is_code_used(self, code: str) -> bool:
|
||||
"""
|
||||
检查认证码是否已被使用
|
||||
参数:
|
||||
code: 要检查的认证码
|
||||
返回:
|
||||
bool: 如果码存在返回True，否则返回False
|
||||
"""
|
||||
with self._lock:
|
||||
return code in self._used_codes
|
||||
|
||||
def clear_codes(self):
|
||||
"""清空所有已使用的认证码"""
|
||||
with self._lock:
|
||||
self._used_codes.clear()
|
||||
self._code_timestamps.clear()
|
||||
|
||||
def _clean_expired_codes(self):
|
||||
"""清理过期的认证码"""
|
||||
current_time = time.time()
|
||||
expired_codes = [
|
||||
code for code, timestamp in self._code_timestamps.items()
|
||||
if (current_time - timestamp) > self._code_timeout
|
||||
]
|
||||
for code in expired_codes:
|
||||
self._used_codes.remove(code)
|
||||
del self._code_timestamps[code]
|
||||
@@ -0,0 +1,50 @@
|
||||
import uuid
|
||||
from typing import List, Dict
|
||||
from datetime import datetime
|
||||
|
||||
|
||||
class Message:
|
||||
def __init__(self, role: str, content: str = None, uniq_id: str = None):
|
||||
self.uniq_id = uniq_id if uniq_id is not None else str(uuid.uuid4())
|
||||
self.role = role
|
||||
self.content = content
|
||||
|
||||
|
||||
class Dialogue:
|
||||
def __init__(self):
|
||||
self.dialogue: List[Message] = []
|
||||
# 获取当前时间
|
||||
self.current_time = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
|
||||
|
||||
def put(self, message: Message):
|
||||
self.dialogue.append(message)
|
||||
|
||||
def get_llm_dialogue(self) -> List[Dict[str, str]]:
|
||||
dialogue = []
|
||||
for m in self.dialogue:
|
||||
dialogue.append({"role": m.role, "content": m.content})
|
||||
return dialogue
|
||||
|
||||
def get_llm_dialogue_with_memory(self, memory_str: str = None) -> List[Dict[str, str]]:
|
||||
# 构建带记忆的对话
|
||||
dialogue = []
|
||||
|
||||
# 添加系统提示和记忆
|
||||
system_message = next(
|
||||
(msg for msg in self.dialogue if msg.role == "system"), None
|
||||
)
|
||||
|
||||
|
||||
if system_message:
|
||||
enhanced_system_prompt = (
|
||||
f"{system_message.content}\n\n"
|
||||
f"相关记忆：\n{memory_str}"
|
||||
)
|
||||
dialogue.append({"role": "system", "content": enhanced_system_prompt})
|
||||
|
||||
# 添加用户和助手的对话
|
||||
for msg in self.dialogue:
|
||||
if msg.role != "system": # 跳过原始的系统消息
|
||||
dialogue.append({"role": msg.role, "content": msg.content})
|
||||
|
||||
return dialogue
|
||||
@@ -0,0 +1,23 @@
|
||||
import os
|
||||
import sys
|
||||
|
||||
# 添加项目根目录到Python路径
|
||||
current_dir = os.path.dirname(os.path.abspath(__file__))
|
||||
project_root = os.path.abspath(os.path.join(current_dir, "..", ".."))
|
||||
sys.path.insert(0, project_root)
|
||||
|
||||
from config.logger import setup_logging
|
||||
import importlib
|
||||
|
||||
logger = setup_logging()
|
||||
|
||||
|
||||
def create_instance(class_name, *args, **kwargs):
|
||||
# 创建LLM实例
|
||||
if os.path.exists(os.path.join('core', 'providers', 'llm', class_name, f'{class_name}.py')):
|
||||
lib_name = f'core.providers.llm.{class_name}.{class_name}'
|
||||
if lib_name not in sys.modules:
|
||||
sys.modules[lib_name] = importlib.import_module(f'{lib_name}')
|
||||
return sys.modules[lib_name].LLMProvider(*args, **kwargs)
|
||||
|
||||
raise ValueError(f"不支持的LLM类型: {class_name}，请检查该配置的type是否设置正确")
|
||||
@@ -0,0 +1,39 @@
|
||||
import asyncio
|
||||
from typing import Dict
|
||||
from config.logger import setup_logging
|
||||
|
||||
TAG = __name__
|
||||
logger = setup_logging()
|
||||
|
||||
class FileLockManager:
|
||||
_instance = None
|
||||
_locks: Dict[str, asyncio.Lock] = {}
|
||||
|
||||
def __new__(cls):
|
||||
if cls._instance is None:
|
||||
cls._instance = super(FileLockManager, cls).__new__(cls)
|
||||
return cls._instance
|
||||
|
||||
@classmethod
|
||||
def get_lock(cls, file_path: str) -> asyncio.Lock:
|
||||
"""获取指定文件的锁"""
|
||||
if file_path not in cls._locks:
|
||||
cls._locks[file_path] = asyncio.Lock()
|
||||
return cls._locks[file_path]
|
||||
|
||||
@classmethod
|
||||
async def acquire_lock(cls, file_path: str):
|
||||
"""获取锁"""
|
||||
lock = cls.get_lock(file_path)
|
||||
await lock.acquire()
|
||||
logger.bind(tag=TAG).debug(f"Acquired lock for {file_path}")
|
||||
|
||||
@classmethod
|
||||
def release_lock(cls, file_path: str):
|
||||
"""释放锁"""
|
||||
if file_path in cls._locks:
|
||||
try:
|
||||
cls._locks[file_path].release()
|
||||
logger.bind(tag=TAG).debug(f"Released lock for {file_path}")
|
||||
except RuntimeError as e:
|
||||
logger.bind(tag=TAG).warning(f"Failed to release lock for {file_path}: {e}")
|
||||
@@ -0,0 +1,17 @@
|
||||
import os
|
||||
import sys
|
||||
import importlib
|
||||
from config.logger import setup_logging
|
||||
from core.utils.util import read_config, get_project_dir
|
||||
|
||||
logger = setup_logging()
|
||||
|
||||
def create_instance(class_name, *args, **kwargs):
|
||||
if os.path.exists(os.path.join('core', 'providers', 'memory', class_name, f'{class_name}.py')):
|
||||
lib_name = f'core.providers.memory.{class_name}.{class_name}'
|
||||
if lib_name not in sys.modules:
|
||||
sys.modules[lib_name] = importlib.import_module(f'{lib_name}')
|
||||
return sys.modules[lib_name].MemoryProvider(*args, **kwargs)
|
||||
|
||||
raise ValueError(f"不支持的记忆服务类型: {class_name}")
|
||||
|
||||
@@ -0,0 +1,33 @@
|
||||
import struct
|
||||
|
||||
def decode_opus_from_file(input_file):
|
||||
"""
|
||||
从p3文件中解码 Opus 数据，并返回一个 Opus 数据包的列表以及总时长。
|
||||
"""
|
||||
opus_datas = []
|
||||
total_frames = 0
|
||||
sample_rate = 16000 # 文件采样率
|
||||
frame_duration_ms = 60 # 帧时长
|
||||
frame_size = int(sample_rate * frame_duration_ms / 1000)
|
||||
|
||||
with open(input_file, 'rb') as f:
|
||||
while True:
|
||||
# 读取头部（4字节）：[1字节类型，1字节保留，2字节长度]
|
||||
header = f.read(4)
|
||||
if not header:
|
||||
break
|
||||
|
||||
# 解包头部信息
|
||||
_, _, data_len = struct.unpack('>BBH', header)
|
||||
|
||||
# 根据头部指定的长度读取 Opus 数据
|
||||
opus_data = f.read(data_len)
|
||||
if len(opus_data) != data_len:
|
||||
raise ValueError(f"Data length({len(opus_data)}) mismatch({data_len}) in the file.")
|
||||
|
||||
opus_datas.append(opus_data)
|
||||
total_frames += 1
|
||||
|
||||
# 计算总时长
|
||||
total_duration = (total_frames * frame_duration_ms) / 1000.0
|
||||
return opus_datas, total_duration
|
||||
@@ -0,0 +1,17 @@
|
||||
import os
|
||||
import sys
|
||||
from config.logger import setup_logging
|
||||
import importlib
|
||||
|
||||
logger = setup_logging()
|
||||
|
||||
|
||||
def create_instance(class_name, *args, **kwargs):
|
||||
# 创建TTS实例
|
||||
if os.path.exists(os.path.join('core', 'providers', 'tts', f'{class_name}.py')):
|
||||
lib_name = f'core.providers.tts.{class_name}'
|
||||
if lib_name not in sys.modules:
|
||||
sys.modules[lib_name] = importlib.import_module(f'{lib_name}')
|
||||
return sys.modules[lib_name].TTSProvider(*args, **kwargs)
|
||||
|
||||
raise ValueError(f"不支持的TTS类型: {class_name}，请检查该配置的type是否设置正确")
|
||||
@@ -0,0 +1,143 @@
|
||||
import os
|
||||
import re
|
||||
import json
|
||||
import yaml
|
||||
import socket
|
||||
import subprocess
|
||||
|
||||
|
||||
def get_project_dir():
|
||||
"""获取项目根目录"""
|
||||
return os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + '/'
|
||||
|
||||
|
||||
def get_local_ip():
|
||||
try:
|
||||
s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
|
||||
# Connect to Google's DNS servers
|
||||
s.connect(("8.8.8.8", 80))
|
||||
local_ip = s.getsockname()[0]
|
||||
s.close()
|
||||
return local_ip
|
||||
except Exception as e:
|
||||
return "127.0.0.1"
|
||||
|
||||
|
||||
def read_config(config_path):
|
||||
with open(config_path, "r", encoding="utf-8") as file:
|
||||
config = yaml.safe_load(file)
|
||||
return config
|
||||
|
||||
|
||||
def write_json_file(file_path, data):
|
||||
"""将数据写入 JSON 文件"""
|
||||
with open(file_path, 'w', encoding='utf-8') as file:
|
||||
json.dump(data, file, ensure_ascii=False, indent=4)
|
||||
|
||||
|
||||
def is_punctuation_or_emoji(char):
|
||||
"""检查字符是否为空格、指定标点或表情符号"""
|
||||
# 定义需要去除的中英文标点（包括全角/半角）
|
||||
punctuation_set = {
|
||||
'，', ',', # 中文逗号 + 英文逗号
|
||||
'。', '.', # 中文句号 + 英文句号
|
||||
'！', '!', # 中文感叹号 + 英文感叹号
|
||||
'-', '－', # 英文连字符 + 中文全角横线
|
||||
'、' # 中文顿号
|
||||
}
|
||||
if char.isspace() or char in punctuation_set:
|
||||
return True
|
||||
# 检查表情符号（保留原有逻辑）
|
||||
code_point = ord(char)
|
||||
emoji_ranges = [
|
||||
(0x1F600, 0x1F64F), (0x1F300, 0x1F5FF),
|
||||
(0x1F680, 0x1F6FF), (0x1F900, 0x1F9FF),
|
||||
(0x1FA70, 0x1FAFF), (0x2600, 0x26FF),
|
||||
(0x2700, 0x27BF)
|
||||
]
|
||||
return any(start <= code_point <= end for start, end in emoji_ranges)
|
||||
|
||||
|
||||
def get_string_no_punctuation_or_emoji(s):
|
||||
"""去除字符串首尾的空格、标点符号和表情符号"""
|
||||
chars = list(s)
|
||||
# 处理开头的字符
|
||||
start = 0
|
||||
while start < len(chars) and is_punctuation_or_emoji(chars[start]):
|
||||
start += 1
|
||||
# 处理结尾的字符
|
||||
end = len(chars) - 1
|
||||
while end >= start and is_punctuation_or_emoji(chars[end]):
|
||||
end -= 1
|
||||
return ''.join(chars[start:end + 1])
|
||||
|
||||
|
||||
def remove_punctuation_and_length(text):
|
||||
# 全角符号和半角符号的Unicode范围
|
||||
full_width_punctuations = '！＂＃＄％＆＇（）＊＋，－。／：；＜＝＞？＠［＼］＾＿｀｛｜｝～'
|
||||
half_width_punctuations = '!"#$%&\'()*+,-./:;<=>?@[\]^_`{|}~'
|
||||
space = ' ' # 半角空格
|
||||
full_width_space = ' ' # 全角空格
|
||||
|
||||
# 去除全角和半角符号以及空格
|
||||
result = ''.join([char for char in text if
|
||||
char not in full_width_punctuations and char not in half_width_punctuations and char not in space and char not in full_width_space])
|
||||
|
||||
if result == "Yeah":
|
||||
return 0, ""
|
||||
return len(result), result
|
||||
|
||||
|
||||
def check_password(password):
|
||||
"""
|
||||
检查密码是否满足以下条件：
|
||||
1. 密码长度大于八位。
|
||||
2. 密码包含英文和数字。
|
||||
3. 密码不能包含“xiaozhi”字符。
|
||||
|
||||
:param password: 要检查的密码
|
||||
:return: 如果密码满足条件，则返回True；否则返回False。
|
||||
"""
|
||||
# 检查密码长度
|
||||
if len(password) < 8:
|
||||
return False
|
||||
|
||||
# 检查是否包含英文字符和数字
|
||||
if not re.search(r'[A-Za-z]', password) or not re.search(r'[0-9]', password):
|
||||
return False
|
||||
|
||||
# 检查是否包含“xiaozhi”字符
|
||||
if "xiaozhi" in password:
|
||||
return False
|
||||
|
||||
if "1234" in password:
|
||||
return False
|
||||
|
||||
# 如果满足所有条件，则返回True
|
||||
return True
|
||||
|
||||
def check_ffmpeg_installed():
|
||||
ffmpeg_installed = False
|
||||
try:
|
||||
# 执行ffmpeg -version命令，并捕获输出
|
||||
result = subprocess.run(
|
||||
['ffmpeg', '-version'],
|
||||
stdout=subprocess.PIPE,
|
||||
stderr=subprocess.PIPE,
|
||||
text=True,
|
||||
check=True # 如果返回码非零则抛出异常
|
||||
)
|
||||
# 检查输出中是否包含版本信息（可选）
|
||||
output = result.stdout + result.stderr
|
||||
if 'ffmpeg version' in output.lower():
|
||||
ffmpeg_installed = True
|
||||
return False
|
||||
except (subprocess.CalledProcessError, FileNotFoundError):
|
||||
# 命令执行失败或未找到
|
||||
ffmpeg_installed = False
|
||||
if not ffmpeg_installed:
|
||||
error_msg = "您的电脑还没正确安装ffmpeg\n"
|
||||
error_msg += "\n建议您：\n"
|
||||
error_msg += "1、按照项目的安装文档，正确进入conda环境\n"
|
||||
error_msg += "2、查阅安装文档，如何在conda环境中安装ffmpeg\n"
|
||||
raise ValueError(error_msg)
|
||||
@@ -0,0 +1,77 @@
|
||||
from abc import ABC, abstractmethod
|
||||
from config.logger import setup_logging
|
||||
import opuslib_next
|
||||
import time
|
||||
import numpy as np
|
||||
import torch
|
||||
|
||||
TAG = __name__
|
||||
logger = setup_logging()
|
||||
|
||||
class VAD(ABC):
|
||||
@abstractmethod
|
||||
def is_vad(self, conn, data):
|
||||
"""检测音频数据中的语音活动"""
|
||||
pass
|
||||
|
||||
|
||||
class SileroVAD(VAD):
|
||||
def __init__(self, config):
|
||||
logger.bind(tag=TAG).info("SileroVAD", config)
|
||||
self.model, self.utils = torch.hub.load(repo_or_dir=config["model_dir"],
|
||||
source='local',
|
||||
model='silero_vad',
|
||||
force_reload=False)
|
||||
(get_speech_timestamps, _, _, _, _) = self.utils
|
||||
|
||||
self.decoder = opuslib_next.Decoder(16000, 1)
|
||||
self.vad_threshold = config.get("threshold")
|
||||
self.silence_threshold_ms = config.get("min_silence_duration_ms")
|
||||
|
||||
def is_vad(self, conn, opus_packet):
|
||||
try:
|
||||
pcm_frame = self.decoder.decode(opus_packet, 960)
|
||||
conn.client_audio_buffer += pcm_frame # 将新数据加入缓冲区
|
||||
|
||||
# 处理缓冲区中的完整帧（每次处理512采样点）
|
||||
client_have_voice = False
|
||||
while len(conn.client_audio_buffer) >= 512 * 2:
|
||||
# 提取前512个采样点（1024字节）
|
||||
chunk = conn.client_audio_buffer[:512 * 2]
|
||||
conn.client_audio_buffer = conn.client_audio_buffer[512 * 2:]
|
||||
|
||||
# 转换为模型需要的张量格式
|
||||
audio_int16 = np.frombuffer(chunk, dtype=np.int16)
|
||||
audio_float32 = audio_int16.astype(np.float32) / 32768.0
|
||||
audio_tensor = torch.from_numpy(audio_float32)
|
||||
|
||||
# 检测语音活动
|
||||
speech_prob = self.model(audio_tensor, 16000).item()
|
||||
client_have_voice = speech_prob >= self.vad_threshold
|
||||
|
||||
# 如果之前有声音，但本次没有声音，且与上次有声音的时间查已经超过了静默阈值，则认为已经说完一句话
|
||||
if conn.client_have_voice and not client_have_voice:
|
||||
stop_duration = time.time() * 1000 - conn.client_have_voice_last_time
|
||||
if stop_duration >= self.silence_threshold_ms:
|
||||
conn.client_voice_stop = True
|
||||
if client_have_voice:
|
||||
conn.client_have_voice = True
|
||||
conn.client_have_voice_last_time = time.time() * 1000
|
||||
|
||||
return client_have_voice
|
||||
except opuslib_next.OpusError as e:
|
||||
logger.bind(tag=TAG).info(f"解码错误: {e}")
|
||||
except Exception as e:
|
||||
logger.bind(tag=TAG).error(f"Error processing audio packet: {e}")
|
||||
|
||||
|
||||
def create_instance(class_name, *args, **kwargs) -> VAD:
|
||||
# 获取类对象
|
||||
cls_map = {
|
||||
"SileroVAD": SileroVAD,
|
||||
# 可扩展其他SileroVAD实现
|
||||
}
|
||||
|
||||
if cls := cls_map.get(class_name):
|
||||
return cls(*args, **kwargs)
|
||||
raise ValueError(f"不支持的SileroVAD类型: {class_name}")
|
||||
Reference in New Issue
Block a user