245 points by accessibility_dev 7 months ago flag hide 20 comments
johnsmith 7 months ago next
This is such an inspiring project! It's great to see how technology can be used to help people with disabilities. I'm looking forward to learning more about the implementation details.
original_poster 7 months ago next
Thanks for the kind words! We're still in the early stages of development, but I'll definitely share more about the implementation as we make progress.
geekytech 7 months ago prev next
How did you approach training the voice recognition module? Did you use an existing library or build something custom?
original_poster 7 months ago next
We used a combination of existing libraries and custom algorithms for voice recognition. It's always a challenge to balance between the accuracy of the recognition and the user experience.
helpfulham 7 months ago prev next
Are there any specific challenges you encountered when building for the visually impaired community?
original_poster 7 months ago next
Yes, there were several specific challenges. One of the biggest ones was ensuring that the assistant could accurately interpret inputs and provide correct outputs without relying on visual cues. We also had to make sure that the assistant could provide clear, spoken instructions and descriptions to help users navigate their surroundings.
devadvocate 7 months ago prev next
How did you ensure that the assistant is accessible for users with different levels of visual impairment?
original_poster 7 months ago next
We used different methods to ensure the assistant was accessible for users with different levels of visual impairment. For example, we made sure to include easily adjustable text-to-speech and audio cues, and to provide clear and straightforward menus that can be easily navigated through voice commands. We also conducted extensive user testing with visually impaired individuals to ensure the assistant met their needs.
curiouscoder 7 months ago prev next
What programming languages and frameworks did you use for this project?
original_poster 7 months ago next
We mainly used Python for its extensive libraries for voice recognition and processing, and Flask for the back end. We also used some JavaScript for front-end development.
original_poster 7 months ago prev next
Ah, that's great to hear! Yes, we're open source, and we encourage the community to contribute. You can find our repository on GitHub, and we welcome all kinds of contributions, whether it's code, bug reports, suggestions or features. Feel free to reach out if you have any questions, and I'll be happy to help.