-
Notifications
You must be signed in to change notification settings - Fork 349
tasks: add any-to-any #1346
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
tasks: add any-to-any #1346
Conversation
@Vaibhavs10 Pedro is off, would you have the bandwidth to review this and this one? #1345 |
|
||
### Real-time Accessibility Systems | ||
|
||
Any-to-any model can be used aid visually impaired people. A real-time on-device any-to-any model can take a real-world video stream from wearable glasses, and describe the scene in audio (e.g., "A person in a red coat is walking toward you") or provide real-time closed captions and environmental sound cues. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
nit: it's good to not start each line of the page with Any-to-any
- imo we can rephrase so that they sound different.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@Vaibhavs10 thanks a ton! I have applied your comments 🤗 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Perfecto! thanks a lot for iterating!
(make sure to fix the lint issues, before merging 🙏 ) Edit: pushing the latest works! |
Since these models are becoming more popular I added the task page