CamiloVega commited on
Commit
2a16b08
Β·
verified Β·
1 Parent(s): f1d02c3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +24 -40
README.md CHANGED
@@ -8,57 +8,41 @@ sdk_version: 5.0.0
8
  app_file: app.py
9
  pinned: false
10
  license: apache-2.0
11
- short_description: 'AI-Powered News Generator'
12
  ---
13
 
14
  # πŸ“° NewsIA - AI News Generator
15
 
16
- NewsIA is an application that uses artificial intelligence to generate professional news articles from multiple sources such as documents, audio, video, URLs, and social media.
17
 
18
  ## Features
19
 
20
- - **Multiple input sources**: Documents (PDF, DOCX, XLSX, CSV), audio, video, URLs, and social media.
21
- - **Automatic transcription**: Automatically transcribes audio and video files.
22
- - **Information extraction**: Extracts relevant content from web pages and documents.
23
- - **Optimized generation**: Uses optimized models to generate news quickly and efficiently.
24
- - **Customization**: Allows adjusting the tone and length of generated news articles.
25
 
26
- ## Technologies used
27
 
28
- - **TinyLlama**: Base model optimized for performance in environments with limited resources
29
- - **Whisper**: For audio and video transcription
30
- - **Gradio**: For the user interface
31
- - **Hugging Face Spaces**: For hosting with ZeroGPU
 
 
 
 
32
 
33
- ## How to use
34
 
35
- 1. Provide **instructions** and **main facts** for your news article
36
- 2. Adjust the desired **length** and **tone**
37
- 3. Add additional sources (optional):
38
- - **Documents**: Upload PDF, DOCX, XLSX or CSV files
39
- - **Audio/Video**: Upload audio or video files for transcription
40
- - **URLs**: Add links to relevant web pages
41
- - **Social Media**: Add links to social media posts
42
- 4. Click on **Generate News**
43
 
44
  ## Installation
45
 
46
- To run this application locally:
47
-
48
- 1. Clone this repository
49
- 2. Install the required dependencies with `pip install -r requirements.txt`
50
- 3. Run the application with `python app.py`
51
-
52
- ## Environment Variables
53
-
54
- The application uses the following environment variables:
55
-
56
- - `HUGGINGFACE_TOKEN`: Your Hugging Face API token (required to access the models)
57
-
58
- ## Technical Details
59
-
60
- NewsIA uses a two-stage approach:
61
- 1. **Data Processing**: Extracts and processes information from various sources
62
- 2. **News Generation**: Uses a language model to create a coherent news article based on the processed data
63
-
64
- The application is designed to run efficiently on Hugging Face Spaces with ZeroGPU resources, using optimized memory management techniques to improve performance.
 
8
  app_file: app.py
9
  pinned: false
10
  license: apache-2.0
11
+ short_description: AI-Powered News Generator
12
  ---
13
 
14
  # πŸ“° NewsIA - AI News Generator
15
 
16
+ NewsIA is an application that uses artificial intelligence to generate professional news articles from multiple sources using optimized models.
17
 
18
  ## Features
19
 
20
+ - **Multiple input sources**: Documents (PDF, DOCX, XLSX, CSV), audio, video, URLs, and social media
21
+ - **Automatic transcription**: Transcribes audio/video files using Whisper
22
+ - **Efficient generation**: Uses Unsloth-optimized TinyLlama for fast inference
23
+ - **Memory management**: Automatic model reset for ZeroGPU compatibility
24
+ - **Customization**: Adjustable length and tone
25
 
26
+ ## How to Use
27
 
28
+ 1. Provide **instructions** and **key facts**
29
+ 2. Adjust desired **length** (100-500 words) and **tone**
30
+ 3. Add optional sources:
31
+ - Upload documents
32
+ - Add audio/video files for transcription
33
+ - Include relevant URLs
34
+ - Add social media links
35
+ 4. Click **Generate News**
36
 
37
+ ## Technical Improvements
38
 
39
+ - πŸš€ 4x faster inference with Unsloth
40
+ - πŸ”’ Secure model loading (weights_only=True)
41
+ - πŸ’» Full English interface
42
+ - 🧠 Optimized memory management for ZeroGPU
43
+ - πŸ“ˆ Updated dependencies for Gradio 5.x
 
 
 
44
 
45
  ## Installation
46
 
47
+ ```bash
48
+ pip install -r requirements.txt