PyPI page
Home page
Author:
Lang Jiaqi
License:
Apache-2.0
Summary:
Left-brain/right-brain memory framework with an audio-native perception layer (scene/speaker/emotion).
Latest version:
0.2.3
Required dependencies:
accelerate
|
fastapi
|
funasr
|
mem0ai
|
modelscope
|
numpy
|
openai
|
pydantic
|
pywebrtc-audio
|
scipy
|
sentence-transformers
|
sherpa-onnx
|
sounddevice
|
soundfile
|
torch
|
torchaudio
|
torchvision
|
transformers
|
uvicorn
|
websockets
Optional dependencies:
audioread
|
peft
|
qwen-omni-utils
Downloads last day:
23
Downloads last week:
489
Downloads last month:
455
7-day smoothing