ASR (Automatic Speech Recognition) server tool kit.
- Python 3.8
- pipenv
$ git clone <this repo>
$ cd <this repo>
$ pipenv install
You need to record the speech you want to recognize. Follow the instructions to create voice data.
$ pipenv run record
$ pipenv run build
$ pipenv run train
$ pipenv run start
When the demo-app starts, please speak a voice. The server will recognize it.
$ pipenv run demo