Apply automatic speech recognition model on a dataset of audio files and make any needed correction on the text generated.

Requirements

run ./install.sh to setup your environment.

I assume you're using linux, using windows should work fine but with some few tweaks. This link may help you run .sh file on windows.

Or you can create your virtual environment on python3.7 then install the requirements by running

pip install -r requirements.txt

then run

python install.py

Run the program

python demo.py