https://github.com/uday160386/image-audio-hf-openai

generate a meaningful audio from uploaded photo using HuggingFace + Langchain+ Open AI
https://github.com/uday160386/image-audio-hf-openai

huggingface-transformers langchain openai text-audio

Last synced: about 2 months ago
JSON representation

generate a meaningful audio from uploaded photo using HuggingFace + Langchain+ Open AI

• Host: GitHub
• URL: https://github.com/uday160386/image-audio-hf-openai
• Owner: uday160386
• Created: 2024-05-20T15:01:18.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2024-05-20T15:13:02.000Z (8 months ago)
• Last Synced: 2024-05-20T17:32:04.286Z (8 months ago)
• Topics: huggingface-transformers, langchain, openai, text-audio
• Language: Python
• Homepage:
• Size: 3.87 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Gen AI: generate a meaningful audio from uploaded photo using HuggingFace + Langchain+ Open AI

### Pre-requisites:

Install below libraries from requirements.txt file

```sh

pip install -r requirements.txt 

```

## Design info:

-   used hugging face to consume ready made AI models.

-   for image-to-text with model as "(salesforce/blip-image-captioning-base)" 

-   for text to audio with model as "kan-bayashi_ljspeech_vits". 

-   used langchain+Chat GPT to geenrate a text

-   published image to audio using streamlit

        

## Build and run?

    streamlit run app.py

## Image to Audio:

![screenshot](./images/output.png)

Read more [here](./images/gen_audio_from_photo.flac)