Upload README.md
Browse files
README.md
CHANGED
@@ -1,62 +1,62 @@
|
|
1 |
-
---
|
2 |
-
title: RAWI Voice to Story Generator
|
3 |
-
emoji: π
|
4 |
-
colorFrom: indigo
|
5 |
-
colorTo: green
|
6 |
-
sdk: gradio
|
7 |
-
sdk_version:
|
8 |
-
app_file: app.py
|
9 |
-
pinned: false
|
10 |
-
python_version: 3.9
|
11 |
-
---
|
12 |
-
|
13 |
-
# RAWI Voice to Story Generator
|
14 |
-
|
15 |
-
This Hugging Face Space converts Arabic voice recordings into polished stories using Whisper for speech recognition and DeepSeek API for creative text generation.
|
16 |
-
|
17 |
-
## How It Works
|
18 |
-
|
19 |
-
1. Upload or record an Arabic audio clip
|
20 |
-
2. The system transcribes the speech using OpenAI's Whisper model
|
21 |
-
3. The transcript is sent to DeepSeek API to generate an enhanced story
|
22 |
-
4. Both the original transcript and the generated story are displayed
|
23 |
-
|
24 |
-
## Setup
|
25 |
-
|
26 |
-
This Space requires a DeepSeek API key to work properly. When deploying:
|
27 |
-
|
28 |
-
1. Go to the Settings tab of your Space
|
29 |
-
2. Add your DeepSeek API key as a secret named `DEEPSEEK_API_KEY`
|
30 |
-
3. (Optional) If needed, change the API endpoint by adding `DEEPSEEK_API_URL`
|
31 |
-
|
32 |
-
## Deploying to Hugging Face Spaces
|
33 |
-
|
34 |
-
To deploy this application to Hugging Face Spaces:
|
35 |
-
|
36 |
-
1. Create a new Space on [Hugging Face](https://huggingface.co/spaces)
|
37 |
-
2. Select "Gradio" as the SDK
|
38 |
-
3. Upload the contents of this directory to your Space
|
39 |
-
4. Set the required secrets in the Space settings
|
40 |
-
5. Choose a suitable hardware tier (recommend at least CPU-M)
|
41 |
-
|
42 |
-
## Local Development
|
43 |
-
|
44 |
-
To run this project locally:
|
45 |
-
|
46 |
-
1. Clone this repository
|
47 |
-
2. Install dependencies: `pip install -r requirements.txt`
|
48 |
-
3. Set environment variables:
|
49 |
-
```
|
50 |
-
export DEEPSEEK_API_KEY=your_deepseek_api_key
|
51 |
-
```
|
52 |
-
4. Run the application: `python app.py`
|
53 |
-
|
54 |
-
## Technologies Used
|
55 |
-
|
56 |
-
- Whisper: AI-powered speech recognition model
|
57 |
-
- Gradio: Web interface for ML applications
|
58 |
-
- DeepSeek API: Arabic text generation and enhancement
|
59 |
-
|
60 |
-
## Note
|
61 |
-
|
62 |
-
This application is designed for Arabic language content. Using other languages may result in suboptimal performance.
|
|
|
1 |
+
---
|
2 |
+
title: RAWI Voice to Story Generator
|
3 |
+
emoji: π
|
4 |
+
colorFrom: indigo
|
5 |
+
colorTo: green
|
6 |
+
sdk: gradio
|
7 |
+
sdk_version: 3.50.2
|
8 |
+
app_file: app.py
|
9 |
+
pinned: false
|
10 |
+
python_version: 3.9
|
11 |
+
---
|
12 |
+
|
13 |
+
# RAWI Voice to Story Generator
|
14 |
+
|
15 |
+
This Hugging Face Space converts Arabic voice recordings into polished stories using Whisper for speech recognition and DeepSeek API for creative text generation.
|
16 |
+
|
17 |
+
## How It Works
|
18 |
+
|
19 |
+
1. Upload or record an Arabic audio clip
|
20 |
+
2. The system transcribes the speech using OpenAI's Whisper model
|
21 |
+
3. The transcript is sent to DeepSeek API to generate an enhanced story
|
22 |
+
4. Both the original transcript and the generated story are displayed
|
23 |
+
|
24 |
+
## Setup
|
25 |
+
|
26 |
+
This Space requires a DeepSeek API key to work properly. When deploying:
|
27 |
+
|
28 |
+
1. Go to the Settings tab of your Space
|
29 |
+
2. Add your DeepSeek API key as a secret named `DEEPSEEK_API_KEY`
|
30 |
+
3. (Optional) If needed, change the API endpoint by adding `DEEPSEEK_API_URL`
|
31 |
+
|
32 |
+
## Deploying to Hugging Face Spaces
|
33 |
+
|
34 |
+
To deploy this application to Hugging Face Spaces:
|
35 |
+
|
36 |
+
1. Create a new Space on [Hugging Face](https://huggingface.co/spaces)
|
37 |
+
2. Select "Gradio" as the SDK
|
38 |
+
3. Upload the contents of this directory to your Space
|
39 |
+
4. Set the required secrets in the Space settings
|
40 |
+
5. Choose a suitable hardware tier (recommend at least CPU-M)
|
41 |
+
|
42 |
+
## Local Development
|
43 |
+
|
44 |
+
To run this project locally:
|
45 |
+
|
46 |
+
1. Clone this repository
|
47 |
+
2. Install dependencies: `pip install -r requirements.txt`
|
48 |
+
3. Set environment variables:
|
49 |
+
```
|
50 |
+
export DEEPSEEK_API_KEY=your_deepseek_api_key
|
51 |
+
```
|
52 |
+
4. Run the application: `python app.py`
|
53 |
+
|
54 |
+
## Technologies Used
|
55 |
+
|
56 |
+
- Whisper: AI-powered speech recognition model
|
57 |
+
- Gradio: Web interface for ML applications
|
58 |
+
- DeepSeek API: Arabic text generation and enhancement
|
59 |
+
|
60 |
+
## Note
|
61 |
+
|
62 |
+
This application is designed for Arabic language content. Using other languages may result in suboptimal performance.
|