Chidhambararajan
Chidhambararajan
Sorry for the delayed response, the model was currently trained on single words , however its should work in simple phrases like Hey xxx though . Moreover the current model...
sorry for the delay , didn't have time to clean the repository which held the training code , the same is built using keras https://github.com/Ant-Brain/wakeword_dataset_generator . It has both the...
Extremely sorry for the delay, my bad forgot to add the notebook which contained the training code https://colab.research.google.com/drive/1hH6q3cGneIWxNRLwbVAKIBzHoVVFlEO3?usp=sharing
Currently working on a newer model with better perfomance and higher hotword length, will be available in a month's time
I was able to run the 1280x960 in a 16gb GPU t4 system , so may be you can try running it in cpu? or colab
Sorry about the late reply, i am unable to reproduce the error, what mic are you using, it is advised to use a mic with defaut 16khz sampling frequency
Ok I am using a Samsung m20 with android 10, i am too having this issue or similar I guess The smaller and the bigger widgets.. both aren't showing any...
I am too experiencing the same issue I am using foxyproxy plugin in firefox to connect to green tunnel When I am not connected to green tunnel stackoverflow works fine...
This is happening because of the sliding window approach
You can controll it in the following snippet ``` mic_stream = SimpleMicStream( window_length_secs=1.5, sliding_window_secs=0.75, ) ```