Chidhambararajan
Chidhambararajan
I am currently looking at a clip like architecture to better boost the perfomance of the system
Like @damian-666 pointed out voice assistants employ directional mics to combat the same problem. The idea is that noise heard by the all mics would be uniform but the volume...
sure, make sense will include the same in the next rollouts. Thanks for the contribution!!
@jrsarath Thanks for your contribution, will test and update tomorrow
Interesting, I think this can possibly happen when the expected speed of the system is lower as a result the buffer may overflow or that the audio source is probably...
Hi thanks for the pr, its just the model weights and the dataset which where present in our academic VM got deleted, so that's kind of a bummer. But still...
Thank you for the kind words, kindly share us your thesis upon completion, I'll happily add it in community projects 😄
There should not be much issues w.r.t using the 90MB model in a pi zero in standalone, however using it with other code or other model could be problematic. The...
Sure will do that shortly , sorry for the super delayed response though, didnt come up in GitHub notifications for some reason
Like. @aman-17 pointed out it can be better to train the model from scratch as there is very little to no similarities in the pronunciations between arabian language and english...