Hass/xiaozhi-esp32-server
1
0
Fork 0
mirror of https://github.com/xinnan-tech/xiaozhi-esp32-server.git synced 2026-07-22 15:13:55 +08:00
Code Issues Packages Projects Releases Wiki Activity
2,077 Commits 12 Branches 75 Tags
e1bcff82e2023b07887a83232fdabe8b00a0fb49
Commit Graph
595 Commits
Author SHA1 Message Date
Sakura-RanChen 0ea18d87a3 fix: asr识别缺字现象，去除无用的变量 2025-08-20 16:22:32 +08:00
Sakura-RanChen 74826c1c59 fix 2025-08-20 09:30:43 +08:00
hrz ad50fbe3c9 fix: #2067 #2070 OTA和流控的音频bug 2025-08-19 00:19:41 +08:00
hrz 61ee21d627 update:给LLM性能测试工具增加系统提示词，更符合本项目的实际效果 2025-08-17 09:35:06 +08:00
hrz 2d75eb76f1 update:引导测试页面启动 2025-08-16 14:36:23 +08:00
hrzandGitHub 9b5e4eb9b7 Merge pull request #2039 from xinnan-tech/py_voiceprint_add_health 
update:优化声纹识别，添加服务器健康检查机制避免运行时超时等待
 2025-08-15 18:27:44 +08:00
hrzandGitHub e2324d3c37 Merge pull request #2044 from xinnan-tech/py_test_audio 
Py test audio
 2025-08-15 17:59:21 +08:00
3030332422 0bfa5cf723 update:feat: 为声纹识别添加缓存机制 2025-08-15 16:58:56 +08:00
Sakura-RanChen d2f29f335e update: 音频流式优化 2025-08-15 16:33:46 +08:00
3030332422 dcf8c134a2 update:优化声纹识别，添加服务器健康检查机制避免运行时超时等待 2025-08-14 17:57:46 +08:00
FAN-yeB 7e63e1d607 update:更新paddlespeech.py 2025-08-13 16:00:33 +08:00
Sakura-RanChenandGitHub 311e5d5cfd Merge pull request #1988 from myifeng/async-handler 
调整OPUS函数式处理，不再以数组方式收集再遍历
 2025-08-12 10:14:43 +08:00
Sakura-RanChen 3eb39ebef2 update: huoshanTTS add config 2025-08-11 17:38:17 +08:00
hrz d742bca205 update:添加indextts 流式语音合成 2025-08-08 17:32:41 +08:00
Sakura-RanChen 8e51d52155 update: 增加单模块IndexTTS 2025-08-08 16:55:17 +08:00
hrzandGitHub b3f603732e Merge pull request #1915 from YourKnight1/main 
调整PaddleSpeechTTS流式传输
 2025-08-07 23:42:16 +08:00
Chingfeng Li 4d50eeb830 修正self错误 2025-08-06 14:53:59 +08:00
Chingfeng Li abf1fa0ef4 调整子类 2025-08-06 11:34:57 +08:00
Chingfeng Li 903c0e51ee 修正剩余文本 2025-08-06 10:13:42 +08:00
Chingfeng Li ce6a711c8e 调整流控参数优化 2025-08-06 10:09:28 +08:00
Chingfeng Li 095fe72db0 待完善流控方式 2025-08-05 18:35:37 +08:00
Chingfeng Li 1b6cd01eaf 增加流式处理方法 2025-08-05 14:53:52 +08:00
Chingfeng Li ac1e19f621 调整流式处理opus 2025-08-05 14:10:55 +08:00
Chingfeng Li faf2890695 增加流式处理 2025-08-04 17:04:46 +08:00
Chingfeng Li 75f0773247 增加流式处理Opus 2025-08-04 14:00:41 +08:00
Chingfeng Li 8b81b918cc 移除未使用的total_duration返回值 2025-08-04 13:49:12 +08:00
hrzandGitHub 8aa5537029 Merge pull request #1963 from myifeng/fix-tts-message 
移除无用的TTS消息
 2025-08-02 08:55:12 +08:00
Chingfeng Li f40c3ec0f6 恢复sentence_start判断 2025-07-31 16:59:52 +08:00
Chingfeng Li 71eef4693d 仅在首句发送TTS消息 2025-07-31 14:15:39 +08:00
hrzandGitHub 775f754ff3 Merge pull request #1953 from yaotutu/feature/sherpa-paraformer-support 
feat: 添加 Sherpa-ONNX Paraformer 模型支持
 2025-07-31 13:35:03 +08:00
Chingfeng Li ef25e82544 移除无用的tts消息sentence_end 2025-07-31 13:21:29 +08:00
hrzandGitHub ef0099b3c9 Update connection.py 2025-07-30 20:31:17 +08:00
chan c8a2c9bbd4 fix: 修复qwen模型返回toolcall的arguments为None时导致后续请求400 2025-07-30 18:53:48 +08:00
yaotutu 9edd083411 feat: 添加 Sherpa-ONNX Paraformer 模型支持 
- 在 sherpa_onnx_local.py 中添加 model_type 参数，支持 paraformer 和 sense_voice 两种模型类型
- 在 config.yaml 中添加 SherpaParaformerASR 配置示例
- 添加详细的 Paraformer 使用文档 (docs/sherpa-paraformer-guide.md)
- 保持向后兼容，默认使用 sense_voice 模型

这个改动允许用户在低性能设备（如 RK3566）上使用更轻量的 Paraformer 模型，
相比 SenseVoice (894MB)，Paraformer-small (78MB) 可以提供 4-6 倍的识别速度提升。
 2025-07-30 10:41:27 +08:00
Sakura-RanChen e5d3048fb2 fix: 时间被固定 2025-07-29 09:55:32 +08:00
hrzandGitHub 67c4622ca7 Merge pull request #1935 from myifeng/aliyun-internal 
如果配置的是ECS内网地址，则使用ws协议，默认是wss协议
 2025-07-29 08:59:34 +08:00
hrz ff9fb9eb1b update:优化最后活动时间 2025-07-28 22:38:48 +08:00
Chingfeng Li b07a8796ff 阿里云ECS内网访问协议设置 2025-07-28 17:06:53 +08:00
root 04746961f2 调整PaddleSpeechTTS流式传输 2025-07-25 10:09:04 +08:00
hrz dff8b8ccec Merge branch 'main' into py_test_tts 2025-07-24 16:18:39 +08:00
hrz 78e5c52932 Merge branch 'main' into py_test_tts 2025-07-24 15:15:44 +08:00
Sakura-RanChen 2f5e8c2019 fix: 补充None值判断 2025-07-24 15:07:35 +08:00
hrz 2508d3f965 update:获取nginx转发的ip地址 2025-07-24 14:38:56 +08:00
hrzandGitHub 3699d28dd0 Merge pull request #1893 from Hmmrrr/main 
feat：添加minimax单向双向流式
 2025-07-24 14:18:19 +08:00
Sakura-RanChen 84ff897b46 fix: LLM携带空文本时错误判断 2025-07-24 09:31:44 +08:00
Sakura-RanChen 83ded8458a Merge branch 'py_test_tts' of https://github.com/xinnan-tech/xiaozhi-esp32-server into py_test_tts 2025-07-23 14:40:14 +08:00
Sakura-RanChen e93053d412 fix: 文本重复发送 2025-07-23 14:35:59 +08:00
Hmmrrr fadf18b7fc feat：添加minimax单向双向流式 2025-07-22 18:13:05 +08:00
欣南科技andGitHub 710218b5b5 Merge pull request #1716 from xinnan-tech/py_test_tts 
update:添加阿里云流式asr
 2025-07-22 13:27:41 +08:00
hrz 60cbe1571c update:修复cosyvoice非流式合成方法 2025-07-22 13:25:54 +08:00