Inspiration
I was going through the TensorFlow website and saw the hand detection model. I was thinking of ways that I could use this to help people.
What it does
It currently has the functionality to do transcribe speech. I have started the process of training the model by using images that I took. Theoretically, at the end of the that process it would be able to detect hello, thank you, no, yes, and I love you.
How we built it
I used python to build this while taking in the model for English speech recognition from VOSK. I wrote all of the this in Jupyter Lab.
Challenges we ran into
Throughout the project I realized that I needed to download a lot of new programs. I also ran into a lot of errors while working in Jupyter notebook which was difficult for me to identify because it was my first time using Jupyter. Currently I ran into the error of labeling the images to train the model
Accomplishments that we're proud of
I am happy that I got the speech to text translation to work as well as begun the process and captured images for the sign language translation.
What we learned
What's next for SignLanguageTranslator
Built With
- jupyter
- python
- tensorflow
- vosk
Log in or sign up for Devpost to join the conversation.