MoYoYoTech/VoiceDialogue at c531bfcefe5a3eb508bf894be8416df88cc3f281

VoiceDialogue / src /voice_dialogue

263 kB

3 contributors

History: 74 commits

liumaolin

更新LLM模型参数，调整top_p值为0.8，并添加max_tokens参数，设置为32768。

c531bfc 6 months ago

api
添加获取TTS模型参考音频的API路由，支持通过模型ID获取音频文件。 6 months ago
cli
Fix help text for `--disable-echo-cancellation` to clarify the default behavior is not disabled 6 months ago
config
更新LLM模型参数，调整top_p值为0.8，并添加max_tokens参数，设置为32768。 6 months ago
core
在`SpeechStateMonitor`类的初始化过程中调用该方法，确保在创建新语音任务时中断任务ID被正确重置。 6 months ago
models
Rename 'src/VoiceDialogue' to 'src/voice_dialogue'. 7 months ago
services
调整prompt的逻辑，确保展示的提示词中不包含/no_think指令 6 months ago
utils
Replace `logging` with centralized `loguru`-based logger across all modules. 6 months ago
__init__.py

539 Bytes

Refactor to replace `EchoCancellingAudioCapture` with `AudioCapture` across the codebase for improved clarity and flexibility 6 months ago