README.md

metadata

title: Diego GenAI LLM multi-model story telling fun
emoji: 🤗
sdk: gradio
sdk_version: 4.24.0
license: cc-by-nc-sa-4.0
short_description: Diego's GenAI LLM multi-model story telling fun
colorFrom: yellow
colorTo: gray
app_file: app.py

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

Result

• Multi-models in action
• Story Telling
  • Given a image
  • Generate the caption for the image
  • Generate an background story for the text
• Use LLM models:
  • Salesforce/blip-image-captioning-base for image captioning
  • gpt2 for text generation
  • gTTS for text to speech, gTTS is a Python library and CLI tool to interface with Google Translate's text-to-speech API.
  • openai/whisper-large-v2 for speach recognition
  • pipeline/sentiment-analysis task for sentiment analysis of the text story

Result UI:

Audio Result: