Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
MoYoYoTech
/
VoiceDialogue
like
2
Follow
MoYoYoTech
24
Text-to-Speech
Transformers
ONNX
GGUF
Chinese
English
voice-dialogue
speech-recognition
large-language-model
asr
tts
llm
chinese
english
real-time
conversational
License:
mit
Model card
Files
Files and versions
xet
Community
1
Deploy
Use this model
main
VoiceDialogue
/
src
/
voice_dialogue
/
core
11.3 kB
3 contributors
History:
12 commits
liumaolin
refactor(core): Architecturally decouple Audio, ASR, and TTS modules
60f8238
6 months ago
__init__.py
0 Bytes
Rename 'src/VoiceDialogue' to 'src/voice_dialogue'.
7 months ago
base.py
947 Bytes
Standardize service lifecycle management by replacing `stop` with `exit` and introducing `is_exited` check
7 months ago
constants.py
2.8 kB
Enable debug mode with global configuration and detailed task logging when active
6 months ago
enums.py
107 Bytes
Rename 'src/VoiceDialogue' to 'src/voice_dialogue'.
7 months ago
launcher.py
4.83 kB
refactor(core): Architecturally decouple Audio, ASR, and TTS modules
6 months ago
session_manager.py
1.08 kB
Rename 'src/VoiceDialogue' to 'src/voice_dialogue'.
7 months ago
state_manager.py
1.58 kB
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