-
-
Notifications
You must be signed in to change notification settings - Fork 122
Enhance Emotion Detection with Specialized Transformer Model #89
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
base: revert-51-Sql_Database
Are you sure you want to change the base?
Enhance Emotion Detection with Specialized Transformer Model #89
Conversation
…1-Sql_Database Revert "[Feature]: Pull request for Adding database capabilities to the chat-interface.py to make it more personalized eccentriccoder01#41"
…ermita18/UI-Enhancements-#39
- Add profile.py module with complete profile functionality - Integrate profile component in sidebar.py - Update main TalkHeal.py to support profile features - Implement profile picture upload and management - Add user preferences (name, font size) functionality - Fix text input color visibility issue
…management-module Add user profile management module with avatar support
…ermita18/UI-Enhancements-#39
…Enhancements-#39 UI-Enhancements eccentriccoder01#39
Added Yoga for Mental Health feature based on mood (GSSoC'25 Level 2)
Added breathing exercise to components folder
Update README.md
Added Templates
…is-support Enhance Crisis Support with GeoIP-based helpline detection
fix: hide sidebar and chat UI on login screen using session_state
…ider-keyboard-navigation Add Keyboard Navigation for Mood Slider with ARIA Attributes.
Hi @AquarlisPrime, it looks like there might be some confusion around how pull requests work. Could you clarify whether you've already made changes to the app and are submitting them through this PR, or if you're simply requesting to work on the issue? If you're just getting started, note that a pull request usually comes after you've been assigned to an issue. The general workflow is:
Let us know how you’d like to proceed, we'll be happy to guide you through the steps! |
Current distilBERT is general-purpose. You can improve accuracy with a better finetuned model (like j-hartmann/emotion-english-distilroberta-base or EmotionRoBERTa).
How:
Replace model loading and tokenizer logic.
Add performance comparison (F1, confusion matrix).
Write a fallback in case HuggingFace model fails.