https://github.com/blacksmithop/whosaidwhat

Find speakers and their dialogue from any text!
https://github.com/blacksmithop/whosaidwhat

Last synced: 8 months ago
JSON representation

Find speakers and their dialogue from any text!

• Host: GitHub
• URL: https://github.com/blacksmithop/whosaidwhat
• Owner: blacksmithop
• Created: 2024-01-28T09:58:55.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-01-28T10:13:11.000Z (over 2 years ago)
• Last Synced: 2025-04-04T20:46:02.860Z (about 1 year ago)
• Language: Python
• Size: 15.6 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: Readme.md

Awesome Lists containing this project

README

          
# Dynamic Narrator

![python](https://img.shields.io/badge/Python-3776ab?style=for-the-badge&logo=python&logoColor=green)

## Installation

1. Get a llam-2 model ([llama-2-7b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Llama-2-7B-GGUF/blob/main/llama-2-7b.Q5_K_M.gguf))

2. Install llama-cpp-python with GPU support

3. Install dependencies

4. Run application `streamlit run app.py`

### Challenges:

- [ ] Minimize hallucination

- [ ] Create chains to validate input

- [ ] Ensure speaker is always extracted (if present)

- [ ] Prompt to accomodate many kinds of speech