Madhuri/vqa_audiobot
5
Use client server approach for model to UI communication.
update refresh chatbot
Remove logo
Add warp for deployment in huggingface
Add gallery to the page for selecting image easily.
Add question validation model in front of VQA
Change avatar for bot and human.
Add grammar module to correct the generated answers.
Update UI texts
Use spinner during long time operations
Move model initialization to separate thread.
Use speechsynthesizer to play audio in client side.
Use pyttsx3 for text to speech
Add chatbot and audiobot pages to application.
initial commit