Skip to content

Ryuk17/ten-vad-edge

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ten_vad_edge

Depoly TEN VAD on edge device.

Usage

build
1) mkdir build
2) cd build
3) cmake ..
4) make -j4

run
1) ../bin/ten_vad input.wav output.txt

RTF

Model bits FFT RTF
float32 FFTW 0.129
int8 FFTW 0.105
int8 NEON 0.093

*Due to CPU fluctuations, the above data is for reference only.

Dependencies

  • MNN : a blazing fast, lightweight deep learning framework

  • NEON FFT : a fast fft implementation based on NEON

About

Light-weight vad model(ten-vad) on edge device

Resources

License

Stars

Watchers

Forks

Packages

 
 
 

Contributors