Upload 4 files
Browse files- .gitignore +36 -0
- README.md +73 -13
- app.py +2 -0
- requirements.txt +0 -0
.gitignore
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Byte-compiled / optimized / DLL files
|
| 2 |
+
__pycache__/
|
| 3 |
+
*.py[cod]
|
| 4 |
+
*$py.class
|
| 5 |
+
|
| 6 |
+
# Virtual environment
|
| 7 |
+
.env/
|
| 8 |
+
venv/
|
| 9 |
+
.venv/
|
| 10 |
+
|
| 11 |
+
# Environment variables
|
| 12 |
+
.env
|
| 13 |
+
|
| 14 |
+
# Jupyter Notebook checkpoints
|
| 15 |
+
.ipynb_checkpoints/
|
| 16 |
+
|
| 17 |
+
# Audio and data outputs
|
| 18 |
+
data/audio/
|
| 19 |
+
data/transcripts/
|
| 20 |
+
data/summaries/
|
| 21 |
+
|
| 22 |
+
# Model files
|
| 23 |
+
models/
|
| 24 |
+
*.pt
|
| 25 |
+
*.pth
|
| 26 |
+
*.onnx
|
| 27 |
+
|
| 28 |
+
# Logs
|
| 29 |
+
*.log
|
| 30 |
+
|
| 31 |
+
# OS files
|
| 32 |
+
.DS_Store
|
| 33 |
+
Thumbs.db
|
| 34 |
+
|
| 35 |
+
# VSCode settings (optional)
|
| 36 |
+
.vscode/
|
README.md
CHANGED
|
@@ -1,13 +1,73 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
\# Arabic Podcast Summarizer | مُلخّص بودكاستات عربية
|
| 2 |
+
|
| 3 |
+
|
| 4 |
+
|
| 5 |
+
A professional-quality tool that takes a YouTube podcast link and returns a structured Arabic summary using local, open-source ML models.
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
أداة بجودة احترافية تأخذ رابط بودكاست يوتيوب وتُنتج ملخّصًا عربيًا منظمًا باستخدام نماذج ذكاء اصطناعي محليّة ومفتوحة المصدر.
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
\## Features | الميزات
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
\- Download \& transcribe Arabic audio | تحميل وتفريغ صوتي باللغة العربية
|
| 22 |
+
|
| 23 |
+
\- Speaker diarization (host/guest) | التعرف على المتحدثين (مُضيف/ضيف)
|
| 24 |
+
|
| 25 |
+
\- Arabic Named Entity Recognition | استخراج الكيانات (أشخاص، شركات...)
|
| 26 |
+
|
| 27 |
+
\- Arabic Summarization | تلخيص نص عربي مُنظم
|
| 28 |
+
|
| 29 |
+
\- Simple UI (Streamlit or Gradio) | واجهة استخدام سهلة
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
---
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
\## Tech Stack | التقنيات
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
\- `yt-dlp`, `Whisper`, `pyannote-audio`, `CAMeL Tools` or `AraBERT`, `mT5`
|
| 42 |
+
|
| 43 |
+
\- Python 3.10+, Local inference preferred (no cloud APIs)
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
---
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
\## Usage | طريقة الاستخدام
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
1\. Install dependencies:
|
| 56 |
+
|
| 57 |
+
```
|
| 58 |
+
pip install -r requirements.txt
|
| 59 |
+
```
|
| 60 |
+
|
| 61 |
+
2\. Run the app:
|
| 62 |
+
```
|
| 63 |
+
streamlit run app/ui.py
|
| 64 |
+
```
|
| 65 |
+
3\. Paste a YouTube link and get your summary!
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
In Progress | المشروع قيد التطوير
|
| 73 |
+
|
app.py
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from app.ui import demo # `demo` is the Gradio Blocks object
|
| 2 |
+
demo.launch()
|
requirements.txt
ADDED
|
File without changes
|