The objective of the project is to predict and translate American Sign Language (ASL) fingerspelling from a set of video frames into text and voice.
first, you need collect the data for the train.
Initialize with create a new enviroment:
python -m venv venv
Activate the enviroment:
source venv/bin/activate
Now, install the requirements:
pip install -r requirements.txt
Now, you need run the next script:
python ./collected_data.py