diff --git a/docs/Deployment.md b/docs/Deployment.md index 03147198..01f0afeb 100644 --- a/docs/Deployment.md +++ b/docs/Deployment.md @@ -81,7 +81,7 @@ xiaozhi-server 下载完后，回到本教程继续往下。 -##### 1.2.3.2 下载 config.yaml +##### 1.2.3.2 创建 config.yaml 用浏览器打开[这个链接](../main/xiaozhi-server/config.yaml)。 @@ -224,43 +224,36 @@ python app.py ## 配置项目 如果你的`xiaozhi-server`目录没有`data`，你需要创建`data`目录。 -如果你的`data`下面没有`.config.yaml`文件，你可以把`xiaozhi-server`目录下的`config.yaml`文件复制到`data`，并重命名为`.config.yaml` +如果你的`data`下面没有`.config.yaml`文件，有两个方式，任选一种： -修改`xiaozhi-server`下`data`目录下的`.config.yaml`文件，配置本项目必须的一个配置。 +第一个方式：你可以把`xiaozhi-server`目录下的`config.yaml`文件复制到`data`，并重命名为`.config.yaml`。在此文件上修改 + +第二个方式：你也可以创建在`data`目录下手动创建`.config.yaml`空文件，然后在这个文件中增加必要的配置信息，系统会优先读取`.config.yaml`文件的配置，如果`.config.yaml`没有配置的，系统会自动去加载`xiaozhi-server`目录下的`config.yaml`的配置。推荐使用这种方式，这种方式是最简洁的方式。 - 默认的LLM使用的是`ChatGLMLLM`，你需要配置密钥，因为他们的模型，虽然有免费的，但是仍要去[官网](https://bigmodel.cn/usercenter/proj-mgmt/apikeys)注册密钥，才能启动。 -配置说明：这里是各个功能使用的默认组件，例如LLM默认使用`ChatGLMLLM`模型。如果需要切换模型，就是改对应的名称。 -本项目的默认配置仅是成本最低配置（`glm-4-flash`和`EdgeTTS`都是免费的），如果需要更优的更快的搭配，需要自己结合部署环境切换各组件的使用。 +以下是一个能正常跑起来的，最简单的`.config.yaml`配置示例 ``` +server: + websocket: ws://你的ip或者域名:端口号/xiaozhi/v1/ +prompt: | + 我是一个叫小智/小志的台湾女孩，说话机车，声音好听，习惯简短表达，爱用网络梗。 + 我的男朋友是一个程序员，梦想是开发出一个机器人，能够帮助人们解决生活中的各种问题。 + 我是一个喜欢哈哈大笑的女孩，爱东说西说吹牛，不合逻辑的也照吹，就要逗别人开心。 + 请你像一个人一样说话，请勿返回配置xml及其他特殊字符。 + selected_module: - VAD: SileroVAD - ASR: FunASR - LLM: ChatGLMLLM - TTS: EdgeTTS - # 默认不开启记忆，如需开启请看配置文件里的描述 - Memory: nomem - # 默认不开启意图识别，如需开启请看配置文件里的描述 - Intent: nointent -``` + LLM: DoubaoLLM -比如修改`LLM`使用的组件，就看本项目支持哪些`LLM` API接口，当前支持的是`openai`、`dify`。欢迎验证和支持更多LLM平台的接口。 -使用时，在`selected_module`修改成对应的如下LLM配置的名称： - -``` LLM: - DeepSeekLLM: - type: openai - ... ChatGLMLLM: - type: openai - ... - DifyLLM: - type: dify - ... + api_key: xxxxxxxxxxxxxxx.xxxxxx ``` +建议先将最简单的配置运行起来，然后再去`xiaozhi/config.yaml`阅读配置的使用说明。 +比如你要换更换模型，修改`selected_module`下的配置就行。 + ## 模型文件 本项目语音识别模型，默认使用`SenseVoiceSmall`模型，进行语音转文字。因为模型较大，需要独立下载，下载后把`model.pt` diff --git a/main/manager-api/src/main/java/xiaozhi/modules/config/dto/AgentModelsDTO.java b/main/manager-api/src/main/java/xiaozhi/modules/config/dto/AgentModelsDTO.java index 4a07a743..47c08a81 100644 --- a/main/manager-api/src/main/java/xiaozhi/modules/config/dto/AgentModelsDTO.java +++ b/main/manager-api/src/main/java/xiaozhi/modules/config/dto/AgentModelsDTO.java @@ -10,9 +10,6 @@ import lombok.Data; @Data @Schema(description = "获取智能体模型配置DTO") public class AgentModelsDTO { - @NotBlank(message = "密钥不能为空") - @Schema(description = "密钥") - private String secret; @NotBlank(message = "设备MAC地址不能为空") @Schema(description = "设备MAC地址") diff --git a/main/manager-api/src/main/java/xiaozhi/modules/security/secret/ServerSecretFilter.java b/main/manager-api/src/main/java/xiaozhi/modules/security/secret/ServerSecretFilter.java index b33ce23d..b2a18547 100644 --- a/main/manager-api/src/main/java/xiaozhi/modules/security/secret/ServerSecretFilter.java +++ b/main/manager-api/src/main/java/xiaozhi/modules/security/secret/ServerSecretFilter.java @@ -2,8 +2,6 @@ package xiaozhi.modules.security.secret; import java.io.IOException; -import lombok.RequiredArgsConstructor; -import lombok.extern.slf4j.Slf4j; import org.apache.commons.lang3.StringUtils; import org.apache.shiro.web.filter.authc.AuthenticatingFilter; import org.springframework.web.bind.annotation.RequestMethod; @@ -12,6 +10,8 @@ import jakarta.servlet.ServletRequest; import jakarta.servlet.ServletResponse; import jakarta.servlet.http.HttpServletRequest; import jakarta.servlet.http.HttpServletResponse; +import lombok.RequiredArgsConstructor; +import lombok.extern.slf4j.Slf4j; import xiaozhi.common.constant.Constant; import xiaozhi.common.exception.ErrorCode; import xiaozhi.common.utils.HttpContextUtils; @@ -55,7 +55,7 @@ public class ServerSecretFilter extends AuthenticatingFilter { String token = getRequestToken((HttpServletRequest) servletRequest); if (StringUtils.isBlank(token)) { // token为空，返回401 - this.sendUnauthorizedResponse((HttpServletResponse) servletResponse, "Authorization token不能为空"); + this.sendUnauthorizedResponse((HttpServletResponse) servletResponse, "服务器密钥不能为空"); return false; } @@ -63,7 +63,7 @@ public class ServerSecretFilter extends AuthenticatingFilter { String serverSecret = getServerSecret(); if (StringUtils.isBlank(serverSecret) || !serverSecret.equals(token)) { // token无效，返回401 - this.sendUnauthorizedResponse((HttpServletResponse) servletResponse, "无效的Authorization token"); + this.sendUnauthorizedResponse((HttpServletResponse) servletResponse, "无效的服务器密钥"); return false; } @@ -77,7 +77,7 @@ public class ServerSecretFilter extends AuthenticatingFilter { response.setContentType("application/json;charset=utf-8"); response.setHeader("Access-Control-Allow-Credentials", "true"); response.setHeader("Access-Control-Allow-Origin", HttpContextUtils.getOrigin()); - + try { String json = JsonUtils.toJsonString(new Result().error(ErrorCode.UNAUTHORIZED, message)); response.getWriter().print(json); @@ -102,4 +102,4 @@ public class ServerSecretFilter extends AuthenticatingFilter { private String getServerSecret() { return sysParamsService.getValue(Constant.SERVER_SECRET, true); } -} +} diff --git a/main/manager-api/src/main/resources/db/changelog/202504082211.sql b/main/manager-api/src/main/resources/db/changelog/202504082211.sql index 08e5dc5f..91ce33ff 100644 --- a/main/manager-api/src/main/resources/db/changelog/202504082211.sql +++ b/main/manager-api/src/main/resources/db/changelog/202504082211.sql @@ -25,7 +25,7 @@ INSERT INTO `ai_model_provider` (`id`, `model_type`, `provider_code`, `name`, `f -- TTS模型供应器 ('SYSTEM_TTS_edge', 'TTS', 'edge', 'Edge TTS', '[{"key":"voice","label":"音色","type":"string"},{"key":"output_dir","label":"输出目录","type":"string"}]', 1, 1, NOW(), 1, NOW()), -('SYSTEM_TTS_doubao', 'TTS', 'doubao', '火山引擎TTS', '[{"key": "api_url","label": "API地址","type": "string"},{"key": "voice","label": "音色","type": "string"},{"key": "output_dir","label": "输出目录","type": "string"},{"key": "authorization","label": "授权","type": "string"},{"key": "appid","label": "应用ID","type": "string"},{"key": "access_token","label": "访问令牌","type": "string"},{"key": "cluster","label": "集群","type": "string"},{"key": "speed_ratio","label": "语速","type": "number"},{"key": "volume_ratio","label": "音量","type": "number"},{"key": "pitch_ratio","label": "音高","type": "number"}]', 2, 1, NOW(), 1, NOW()), +('SYSTEM_TTS_doubao', 'TTS', 'doubao', '火山引擎TTS', '[{"key":"api_url","label":"API地址","type":"string"},{"key":"voice","label":"音色","type":"string"},{"key":"output_dir","label":"输出目录","type":"string"},{"key":"authorization","label":"授权","type":"string"},{"key":"appid","label":"应用ID","type":"string"},{"key":"access_token","label":"访问令牌","type":"string"},{"key":"cluster","label":"集群","type":"string"}]', 2, 1, NOW(), 1, NOW()), ('SYSTEM_TTS_siliconflow', 'TTS', 'siliconflow', '硅基流动TTS', '[{"key":"model","label":"模型","type":"string"},{"key":"voice","label":"音色","type":"string"},{"key":"output_dir","label":"输出目录","type":"string"},{"key":"access_token","label":"访问令牌","type":"string"},{"key":"response_format","label":"响应格式","type":"string"}]', 3, 1, NOW(), 1, NOW()), ('SYSTEM_TTS_cozecn', 'TTS', 'cozecn', 'COZECN TTS', '[{"key":"voice","label":"音色","type":"string"},{"key":"output_dir","label":"输出目录","type":"string"},{"key":"access_token","label":"访问令牌","type":"string"},{"key":"response_format","label":"响应格式","type":"string"}]', 4, 1, NOW(), 1, NOW()), ('SYSTEM_TTS_fishspeech', 'TTS', 'fishspeech', 'FishSpeech TTS', '[{"key":"output_dir","label":"输出目录","type":"string"},{"key":"response_format","label":"响应格式","type":"string"},{"key":"reference_id","label":"参考ID","type":"string"},{"key":"reference_audio","label":"参考音频","type":"dict","dict_name":"reference_audio"},{"key":"reference_text","label":"参考文本","type":"dict","dict_name":"reference_text"},{"key":"normalize","label":"是否标准化","type":"boolean"},{"key":"max_new_tokens","label":"最大新令牌数","type":"number"},{"key":"chunk_length","label":"块长度","type":"number"},{"key":"top_p","label":"top_p值","type":"number"},{"key":"repetition_penalty","label":"重复惩罚","type":"number"},{"key":"temperature","label":"温度","type":"number"},{"key":"streaming","label":"是否流式","type":"boolean"},{"key":"use_memory_cache","label":"是否使用内存缓存","type":"string"},{"key":"seed","label":"种子","type":"number"},{"key":"channels","label":"通道数","type":"number"},{"key":"rate","label":"采样率","type":"number"},{"key":"api_key","label":"API密钥","type":"string"},{"key":"api_url","label":"API地址","type":"string"}]', 5, 1, NOW(), 1, NOW()), diff --git a/main/manager-api/src/main/resources/db/changelog/202504301339.sql b/main/manager-api/src/main/resources/db/changelog/202504301339.sql new file mode 100644 index 00000000..e4393f6a --- /dev/null +++ b/main/manager-api/src/main/resources/db/changelog/202504301339.sql @@ -0,0 +1,3 @@ +update `ai_model_provider` set `fields` = +'[{"key": "api_url","label": "API地址","type": "string"},{"key": "voice","label": "音色","type": "string"},{"key": "output_dir","label": "输出目录","type": "string"},{"key": "authorization","label": "授权","type": "string"},{"key": "appid","label": "应用ID","type": "string"},{"key": "access_token","label": "访问令牌","type": "string"},{"key": "cluster","label": "集群","type": "string"},{"key": "speed_ratio","label": "语速","type": "number"},{"key": "volume_ratio","label": "音量","type": "number"},{"key": "pitch_ratio","label": "音高","type": "number"}]' +where `id` = 'SYSTEM_TTS_doubao'; diff --git a/main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml b/main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml index 131aaf01..90735fe1 100755 --- a/main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml +++ b/main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml @@ -85,4 +85,11 @@ databaseChangeLog: changes: - sqlFile: encoding: utf8 - path: classpath:db/changelog/202504291043.sql \ No newline at end of file + path: classpath:db/changelog/202504291043.sql + - changeSet: + id: 202504301339 + author: Goody + changes: + - sqlFile: + encoding: utf8 + path: classpath:db/changelog/202504301339.sql \ No newline at end of file diff --git a/main/xiaozhi-server/app.py b/main/xiaozhi-server/app.py index 63b40d71..7ed71ae5 100644 --- a/main/xiaozhi-server/app.py +++ b/main/xiaozhi-server/app.py @@ -1,7 +1,7 @@ import asyncio import sys import signal -from config.settings import load_config, check_config_file +from config.settings import load_config from core.websocket_server import WebSocketServer from core.ota_server import SimpleOtaServer from core.utils.util import check_ffmpeg_installed @@ -31,7 +31,6 @@ async def wait_for_exit(): async def main(): - check_config_file() check_ffmpeg_installed() config = load_config() diff --git a/main/xiaozhi-server/config.yaml b/main/xiaozhi-server/config.yaml index db8dd5d5..3ce485ec 100644 --- a/main/xiaozhi-server/config.yaml +++ b/main/xiaozhi-server/config.yaml @@ -1,7 +1,7 @@ -# 如果您是一名开发者，建议阅读以下内容。如果不是开发者，可以忽略这部分内容。 -# 在开发中，在项目根目录创建data目录，将【config.yaml】复制一份，改成【.config.yaml】，放进data目录中 -# 系统会优先读取【data/.config.yaml】文件的配置。 -# 这样做，可以避免在提交代码的时候，错误地提交密钥信息，保护您的密钥安全。 +# 在开发中，请在项目根目录创建data目录，然后在data目录创建名称为【.config.yaml】的空文件 +# 然后你想修改覆盖修改什么配置，就修改【.config.yaml】文件，而不是修改【config.yaml】文件 +# 系统会优先读取【data/.config.yaml】文件的配置，如果【.config.yaml】文件里的配置不存在，系统会自动去读取【config.yaml】文件的配置。 +# 这样做，可以最简化配置，保护您的密钥安全。 # ##################################################################################### # #############################以下是服务器基本运行配置#################################### @@ -158,7 +158,7 @@ selected_module: # 不想开通意图识别，就设置成：nointent # 意图识别可使用intent_llm。优点：通用性强，缺点：增加串行前置意图识别模块，会增加处理时间，这个意图识别暂时不支持控制音量大小等iot操作 # 意图识别可使用function_call，缺点：需要所选择的LLM支持function_call，优点：按需调用工具、速度快，理论上能全部操作所有iot指令 - # 默认免费的ChatGLMLLM就已经支持function_call，但是如果像追求稳定建议把LLM设置成：DoubaoLLM，使用的具体model_name是：doubao-pro-32k-functioncall-241028 + # 默认免费的ChatGLMLLM就已经支持function_call，但是如果像追求稳定建议把LLM设置成：DoubaoLLM，使用的具体model_name是：doubao-1-5-pro-32k-250115 Intent: function_call # 意图识别，是用于理解用户意图的模块，例如：播放音乐 diff --git a/main/xiaozhi-server/config/config_loader.py b/main/xiaozhi-server/config/config_loader.py index b892b437..35802a67 100644 --- a/main/xiaozhi-server/config/config_loader.py +++ b/main/xiaozhi-server/config/config_loader.py @@ -31,37 +31,19 @@ def load_config(): # 加载默认配置 default_config = read_config(default_config_path) + custom_config = read_config(custom_config_path) - # 加载用户自定义配置（如果存在） - if os.path.exists(custom_config_path): - custom_config = read_config(custom_config_path) + if custom_config.get("manager-api", {}).get("url"): + config = get_config_from_api(custom_config) + else: # 合并配置 config = merge_configs(default_config, custom_config) - else: - config = default_config - - if config.get("manager-api", {}).get("url"): - config = get_config_from_api(config) - # 初始化目录 ensure_directories(config) _config_cache = config return config -def get_config_file(): - """获取配置文件路径，优先使用私有配置文件（若存在）。 - - Returns: - str: 配置文件路径（相对路径或默认路径） - """ - default_config_file = "config.yaml" - config_file = default_config_file - if os.path.exists(get_project_dir() + "data/." + default_config_file): - config_file = "data/." + default_config_file - return config_file - - def get_config_from_api(config): """从Java API获取配置""" # 初始化API客户端 @@ -128,23 +110,29 @@ def ensure_directories(config): def merge_configs(default_config, custom_config): """ 递归合并配置，custom_config优先级更高 - + Args: default_config: 默认配置 custom_config: 用户自定义配置 - + Returns: 合并后的配置 """ - if not isinstance(default_config, Mapping) or not isinstance(custom_config, Mapping): + if not isinstance(default_config, Mapping) or not isinstance( + custom_config, Mapping + ): return custom_config - + merged = dict(default_config) - + for key, value in custom_config.items(): - if key in merged and isinstance(merged[key], Mapping) and isinstance(value, Mapping): + if ( + key in merged + and isinstance(merged[key], Mapping) + and isinstance(value, Mapping) + ): merged[key] = merge_configs(merged[key], value) else: merged[key] = value - - return merged \ No newline at end of file + + return merged diff --git a/main/xiaozhi-server/config/logger.py b/main/xiaozhi-server/config/logger.py index 9eed8540..f20dc0ad 100644 --- a/main/xiaozhi-server/config/logger.py +++ b/main/xiaozhi-server/config/logger.py @@ -2,6 +2,7 @@ import os import sys from loguru import logger from config.config_loader import load_config +from config.settings import check_config_file SERVER_VERSION = "0.3.13" @@ -32,6 +33,7 @@ def formatter(record): def setup_logging(): + check_config_file() """从配置文件中读取日志配置，并设置日志输出格式和级别""" config = load_config() log_config = config["log"] diff --git a/main/xiaozhi-server/config/settings.py b/main/xiaozhi-server/config/settings.py index c12c70d8..fb8868b4 100644 --- a/main/xiaozhi-server/config/settings.py +++ b/main/xiaozhi-server/config/settings.py @@ -1,53 +1,33 @@ import os -from collections.abc import Mapping -from config import logger from config.config_loader import read_config, get_project_dir, load_config -TAG = __name__ -logger = logger.setup_logging() default_config_file = "config.yaml" - - -def find_missing_keys(new_config, old_config, parent_key=""): - """ - 递归查找缺失的配置项 - 返回格式：[缺失配置路径] - """ - missing_keys = [] - - if not isinstance(new_config, Mapping): - return missing_keys - - for key, value in new_config.items(): - # 构建当前配置路径 - full_path = f"{parent_key}.{key}" if parent_key else key - - # 检查键是否存在 - if key not in old_config: - missing_keys.append(full_path) - continue - - # 递归检查嵌套字典 - if isinstance(value, Mapping): - sub_missing = find_missing_keys( - value, old_config[key], parent_key=full_path - ) - missing_keys.extend(sub_missing) - return missing_keys +config_file_valid = False def check_config_file(): + global config_file_valid + if config_file_valid: + return """ 简化的配置检查，仅提示用户配置文件的使用情况 """ custom_config_file = get_project_dir() + "data/." + default_config_file if not os.path.exists(custom_config_file): - logger.bind(tag=TAG).info("提示: 使用默认配置文件。如需自定义配置，请创建 data/.config.yaml 文件") - else: - logger.bind(tag=TAG).info(f"提示: 使用自定义配置文件 data/.config.yaml，配置将覆盖默认值") - + raise FileNotFoundError( + "找不到data/.config.yaml文件，请按教程确认该配置文件是否存在" + ) + # 检查是否从API读取配置 config = load_config() if config.get("read_config_from_api", False): - logger.bind(tag=TAG).info("提示: 从API获取配置") + print("从API读取配置") + old_config_origin = read_config(custom_config_file) + if old_config_origin.get("selected_module") is not None: + error_msg = "您的配置文件好像既包含智控台的配置又包含本地配置：\n" + error_msg += "\n建议您：\n" + error_msg += "1、将根目录的config_from_api.yaml文件复制到data下，重命名为.config.yaml\n" + error_msg += "2、按教程配置好接口地址和密钥\n" + raise ValueError(error_msg) + config_file_valid = True diff --git a/main/xiaozhi-server/core/handle/textHandle.py b/main/xiaozhi-server/core/handle/textHandle.py index f0683d59..a26f5bd9 100644 --- a/main/xiaozhi-server/core/handle/textHandle.py +++ b/main/xiaozhi-server/core/handle/textHandle.py @@ -53,6 +53,8 @@ async def handleTextMessage(conn, message): # 如果是唤醒词，且关闭了唤醒词回复，就不用回答 await send_stt_message(conn, text) await send_tts_message(conn, "stop", None) + elif is_wakeup_words: + await startToChat(conn, "嘿，你好呀") else: # 否则需要LLM对文字内容进行答复 await startToChat(conn, text) diff --git a/main/xiaozhi-server/core/providers/tts/doubao.py b/main/xiaozhi-server/core/providers/tts/doubao.py index 1b6414c4..367a99c9 100644 --- a/main/xiaozhi-server/core/providers/tts/doubao.py +++ b/main/xiaozhi-server/core/providers/tts/doubao.py @@ -27,9 +27,14 @@ class TTSProvider(TTSProviderBase): else: self.voice = config.get("voice") - self.speed_ratio = float(config.get("speed_ratio", 0.1)) - self.volume_ratio = float(config.get("volume_ratio", 0.1)) - self.pitch_ratio = float(config.get("pitch_ratio", 0.1)) + # 处理空字符串的情况 + speed_ratio = config.get("speed_ratio", "1.0") + volume_ratio = config.get("volume_ratio", "1.0") + pitch_ratio = config.get("pitch_ratio", "1.0") + + self.speed_ratio = float(speed_ratio) if speed_ratio else 1.0 + self.volume_ratio = float(volume_ratio) if volume_ratio else 1.0 + self.pitch_ratio = float(pitch_ratio) if pitch_ratio else 1.0 self.api_url = config.get("api_url") self.authorization = config.get("authorization") diff --git a/main/xiaozhi-server/core/providers/tts/fishspeech.py b/main/xiaozhi-server/core/providers/tts/fishspeech.py index 30fee3c9..316dbed7 100644 --- a/main/xiaozhi-server/core/providers/tts/fishspeech.py +++ b/main/xiaozhi-server/core/providers/tts/fishspeech.py @@ -89,18 +89,35 @@ class TTSProvider(TTSProviderBase): self.reference_audio = parse_string_to_list(config.get("reference_audio")) self.reference_text = parse_string_to_list(config.get("reference_text")) self.format = config.get("format", "wav") - self.channels = int(config.get("channels", 1)) - self.rate = int(config.get("rate", 44100)) + self.api_key = config.get("api_key", "YOUR_API_KEY") have_key = check_model_key("FishSpeech TTS", self.api_key) if not have_key: return self.normalize = config.get("normalize", True) - self.max_new_tokens = int(config.get("max_new_tokens", 1024)) - self.chunk_length = int(config.get("chunk_length", 200)) - self.top_p = float(config.get("top_p", 0.7)) - self.repetition_penalty = float(config.get("repetition_penalty", 1.2)) - self.temperature = float(config.get("temperature", 0.7)) + + # 处理空字符串的情况 + channels = config.get("channels", "1") + rate = config.get("rate", "44100") + max_new_tokens = config.get("max_new_tokens", "1024") + chunk_length = config.get("chunk_length", "200") + + self.channels = int(channels) if channels else 1 + self.rate = int(rate) if rate else 44100 + self.max_new_tokens = int(max_new_tokens) if max_new_tokens else 1024 + self.chunk_length = int(chunk_length) if chunk_length else 200 + + # 处理空字符串的情况 + top_p = config.get("top_p", "0.7") + temperature = config.get("temperature", "0.7") + repetition_penalty = config.get("repetition_penalty", "1.2") + + self.top_p = float(top_p) if top_p else 0.7 + self.temperature = float(temperature) if temperature else 0.7 + self.repetition_penalty = ( + float(repetition_penalty) if repetition_penalty else 1.2 + ) + self.streaming = str(config.get("streaming", False)).lower() in ( "true", "1", diff --git a/main/xiaozhi-server/core/providers/tts/gpt_sovits_v2.py b/main/xiaozhi-server/core/providers/tts/gpt_sovits_v2.py index ec6c2053..b2aad88a 100644 --- a/main/xiaozhi-server/core/providers/tts/gpt_sovits_v2.py +++ b/main/xiaozhi-server/core/providers/tts/gpt_sovits_v2.py @@ -20,12 +20,29 @@ class TTSProvider(TTSProviderBase): self.ref_audio_path = config.get("ref_audio_path") self.prompt_text = config.get("prompt_text") self.prompt_lang = config.get("prompt_lang", "zh") - self.top_k = int(config.get("top_k", 5)) - self.top_p = float(config.get("top_p", 1)) - self.temperature = float(config.get("temperature", 1)) + + # 处理空字符串的情况 + top_k = config.get("top_k", "5") + top_p = config.get("top_p", "1") + temperature = config.get("temperature", "1") + batch_threshold = config.get("batch_threshold", "0.75") + batch_size = config.get("batch_size", "1") + speed_factor = config.get("speed_factor", "1.0") + seed = config.get("seed", "-1") + repetition_penalty = config.get("repetition_penalty", "1.35") + + self.top_k = int(top_k) if top_k else 5 + self.top_p = float(top_p) if top_p else 1 + self.temperature = float(temperature) if temperature else 1 + self.batch_threshold = float(batch_threshold) if batch_threshold else 0.75 + self.batch_size = int(batch_size) if batch_size else 1 + self.speed_factor = float(speed_factor) if speed_factor else 1.0 + self.seed = int(seed) if seed else -1 + self.repetition_penalty = ( + float(repetition_penalty) if repetition_penalty else 1.35 + ) + self.text_split_method = config.get("text_split_method", "cut0") - self.batch_size = int(config.get("batch_size", 1)) - self.batch_threshold = float(config.get("batch_threshold", 0.75)) self.split_bucket = str(config.get("split_bucket", True)).lower() in ( "true", @@ -37,19 +54,19 @@ class TTSProvider(TTSProviderBase): "1", "yes", ) - self.speed_factor = float(config.get("speed_factor", 1.0)) + self.streaming_mode = str(config.get("streaming_mode", False)).lower() in ( "true", "1", "yes", ) - self.seed = int(config.get("seed", -1)) + self.parallel_infer = str(config.get("parallel_infer", True)).lower() in ( "true", "1", "yes", ) - self.repetition_penalty = float(config.get("repetition_penalty", 1.35)) + self.aux_ref_audio_paths = parse_string_to_list( config.get("aux_ref_audio_paths") ) diff --git a/main/xiaozhi-server/core/providers/tts/gpt_sovits_v3.py b/main/xiaozhi-server/core/providers/tts/gpt_sovits_v3.py index b2746acf..488280f1 100644 --- a/main/xiaozhi-server/core/providers/tts/gpt_sovits_v3.py +++ b/main/xiaozhi-server/core/providers/tts/gpt_sovits_v3.py @@ -18,13 +18,22 @@ class TTSProvider(TTSProviderBase): self.prompt_text = config.get("prompt_text") self.prompt_language = config.get("prompt_language") self.text_language = config.get("text_language", "audo") - self.top_k = int(config.get("top_k", 15)) - self.top_p = float(config.get("top_p", 1.0)) - self.temperature = float(config.get("temperature", 1.0)) + + # 处理空字符串的情况 + top_k = config.get("top_k", "15") + top_p = config.get("top_p", "1.0") + temperature = config.get("temperature", "1.0") + sample_steps = config.get("sample_steps", "32") + speed = config.get("speed", "1.0") + + self.top_k = int(top_k) if top_k else 15 + self.top_p = float(top_p) if top_p else 1.0 + self.temperature = float(temperature) if temperature else 1.0 + self.sample_steps = int(sample_steps) if sample_steps else 32 + self.speed = float(speed) if speed else 1.0 + self.cut_punc = config.get("cut_punc", "") - self.speed = float(config.get("speed", 1.0)) self.inp_refs = parse_string_to_list(config.get("inp_refs")) - self.sample_steps = int(config.get("sample_steps", 32)) self.if_sr = str(config.get("if_sr", False)).lower() in ("true", "1", "yes") def generate_filename(self, extension=".wav"): diff --git a/main/xiaozhi-server/core/providers/tts/openai.py b/main/xiaozhi-server/core/providers/tts/openai.py index a5d48057..a7c4e30d 100644 --- a/main/xiaozhi-server/core/providers/tts/openai.py +++ b/main/xiaozhi-server/core/providers/tts/openai.py @@ -21,7 +21,11 @@ class TTSProvider(TTSProviderBase): else: self.voice = config.get("voice", "alloy") self.response_format = "wav" - self.speed = float(config.get("speed", 1.0)) + + # 处理空字符串的情况 + speed = config.get("speed", "1.0") + self.speed = float(speed) if speed else 1.0 + self.output_file = config.get("output_dir", "tmp/") check_model_key("TTS", self.api_key) diff --git a/main/xiaozhi-server/core/providers/vad/silero.py b/main/xiaozhi-server/core/providers/vad/silero.py index 3332d9ac..8ec1f6eb 100644 --- a/main/xiaozhi-server/core/providers/vad/silero.py +++ b/main/xiaozhi-server/core/providers/vad/silero.py @@ -21,8 +21,15 @@ class VADProvider(VADProviderBase): (get_speech_timestamps, _, _, _, _) = self.utils self.decoder = opuslib_next.Decoder(16000, 1) - self.vad_threshold = float(config.get("threshold", 0.5)) - self.silence_threshold_ms = int(config.get("min_silence_duration_ms", 1000)) + + # 处理空字符串的情况 + threshold = config.get("threshold", "0.5") + min_silence_duration_ms = config.get("min_silence_duration_ms", "1000") + + self.vad_threshold = float(threshold) if threshold else 0.5 + self.silence_threshold_ms = ( + int(min_silence_duration_ms) if min_silence_duration_ms else 1000 + ) def is_vad(self, conn, opus_packet): try: