Skip to content
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

Audio and Video alt-text generation #16

Merged
merged 8 commits into from
Dec 9, 2024
Merged

Audio and Video alt-text generation #16

merged 8 commits into from
Dec 9, 2024

Conversation

micr0-dev
Copy link
Owner

its what it says on the tin, its super cool, we got audio and video alt-text generation now.

@micr0-dev
Copy link
Owner Author

only thing that is left to test before merging is ollama support

@micr0-dev
Copy link
Owner Author

This pull request includes significant updates to the bot's functionality, particularly in its ability to generate alt-text for various types of media files and improvements to error handling. The changes also include updates to localization strings to support the new media types.

Enhancements to Alt-Text Generation:

  • Added support for generating alt-text for videos and audio files, including detailed descriptions and transcriptions of spoken content. (localizations.json, main.go) [1] [2] [3] [4]
  • Updated the generateAltText function to handle different media types, renaming it to generateImageAltText, and added new functions generateVideoAltText and generateAudioAltText. (main.go) [1] [2]

Localization Updates:

  • Expanded localization strings to include prompts and responses for video and audio alt-text generation in multiple languages. (localizations.json)

Codebase Improvements:

  • Improved error handling for alt-text generation, including logging and localized error messages. (main.go)
  • Updated the bot version to 1.3 to reflect the new features. (main.go)
  • Introduced a new client variable for the generative model client, initializing it in the Setup function. (main.go) [1] [2]

@micr0-dev micr0-dev changed the title Feature/audio video Audio and Video alt-text generation Dec 7, 2024
@mikoxyz
Copy link

mikoxyz commented Dec 8, 2024

looks ok. you'll probably want to implement a max file size though; wouldn't be super fun to end up downloading a file that's unreasonably large

@micr0-dev micr0-dev merged commit e285058 into main Dec 9, 2024
@micr0-dev micr0-dev deleted the feature/audioVideo branch December 9, 2024 04:46
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants