Help Use Deepspeech to build a Speech Recognization

Hi Maix Team, have one project, plan to to Maix for our voice command process processor, after review the system, it is a prefect device for voice recognization.

However, the github model, which is a c based voice recognization model. We are plan to have a TF build like Deepspeech model, to run on Maix.

Do you have any plan to have sample project we could start with or any suggest we could start to try?


1 Like

Iā€™m also looking for a tutorial to use deepspeech database to train MaixGo KPU.