Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
@@ -1,19 +1,27 @@
|
|
|
|
|
|
1 |
```markdown
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
|
3 |
# Amharic Text-to-Speech (TTS) Application
|
4 |
-
|
5 |
<div align="center">
|
6 |
-
<img src="
|
7 |
<br>
|
8 |
<em>Convert Amharic text to natural-sounding speech directly in your browser</em>
|
9 |
</div>
|
10 |
|
11 |
-
[](https://www.python.org/downloads/)
|
15 |
-
|
16 |
-
A simple web-based Text-to-Speech application focused on Amharic language support, powered by Microsoft Edge TTS.
|
17 |
|
18 |
## Features β¨
|
19 |
- π£οΈ Native Amharic voice support (Male & Female)
|
@@ -29,51 +37,13 @@ A simple web-based Text-to-Speech application focused on Amharic language suppor
|
|
29 |
| Ameha | Male | `am-ET-AmehaNeural`|
|
30 |
| Mekdes | Female | `am-ET-MekdesNeural`|
|
31 |
|
32 |
-
##
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
### Steps
|
39 |
-
1. Clone repository:
|
40 |
-
```bash
|
41 |
-
git clone https://github.com/snackshell/amharic-tts.git
|
42 |
-
cd amharic-tts
|
43 |
-
```
|
44 |
-
|
45 |
-
2. Create virtual environment:
|
46 |
-
```bash
|
47 |
-
python -m venv venv
|
48 |
-
source venv/bin/activate # Linux/Mac
|
49 |
-
venv\Scripts\activate # Windows
|
50 |
-
```
|
51 |
-
|
52 |
-
3. Install dependencies:
|
53 |
-
```bash
|
54 |
-
pip install -r requirements.txt
|
55 |
-
```
|
56 |
-
|
57 |
-
## Usage π
|
58 |
-
1. Start the application:
|
59 |
-
```bash
|
60 |
-
python app.py
|
61 |
-
```
|
62 |
-
|
63 |
-
2. Access the interface at:
|
64 |
-
```
|
65 |
-
http://localhost:7860
|
66 |
-
```
|
67 |
-
|
68 |
-
3. Enter Amharic text and select a voice:
|
69 |
-
- Type/paste text in the input box
|
70 |
-
- Choose between Ameha (Male) or Mekdes (Female)
|
71 |
-
- Click "α΅αα
αα α" (Generate Audio)
|
72 |
-
|
73 |
-
4. Play generated audio using the built-in player
|
74 |
|
75 |
## Technical Details π§
|
76 |
-
### Architecture
|
77 |
```mermaid
|
78 |
graph TD
|
79 |
A[User Interface] --> B(Gradio Frontend)
|
@@ -81,35 +51,40 @@ graph TD
|
|
81 |
C --> D[Microsoft Cognitive Services]
|
82 |
```
|
83 |
|
84 |
-
###
|
85 |
-
- Python 3.10+
|
86 |
-
- Gradio (Web Interface)
|
87 |
-
- edge-tts (TTS Engine)
|
88 |
-
- asyncio (Async Operations)
|
89 |
-
- tempfile (Audio File Handling)
|
90 |
|
91 |
-
##
|
92 |
-
|
93 |
-
|
94 |
-
|
95 |
-
|
96 |
-
|
97 |
-
|
98 |
|
99 |
## License π
|
100 |
-
This project is licensed under the MIT License
|
101 |
|
102 |
## Acknowledgments π
|
103 |
- Microsoft Edge TTS services
|
104 |
-
-
|
105 |
-
-
|
106 |
-
|
107 |
|
108 |
-
|
109 |
-
|
110 |
-
1. **requirements.txt**
|
111 |
-
```text
|
112 |
-
gradio==4.13.0
|
113 |
-
edge-tts==6.1.3
|
114 |
-
python-dotenv==1.0.0
|
115 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Here's the Hugging Face Spaces compatible README.md:
|
2 |
+
|
3 |
```markdown
|
4 |
+
---
|
5 |
+
title: Amharic Text-to-Speech (TTS) Application
|
6 |
+
emoji: πͺπΉ
|
7 |
+
colorFrom: red
|
8 |
+
colorTo: yellow
|
9 |
+
sdk: gradio
|
10 |
+
sdk_version: 4.13.0
|
11 |
+
app_file: app.py
|
12 |
+
pinned: false
|
13 |
+
license: mit
|
14 |
+
---
|
15 |
|
16 |
# Amharic Text-to-Speech (TTS) Application
|
17 |
+
|
18 |
<div align="center">
|
19 |
+
<img src="https://raw.githubusercontent.com/snackshell/amharic-tts/main/assets/demo.png" alt="Amharic TTS Interface" width="800">
|
20 |
<br>
|
21 |
<em>Convert Amharic text to natural-sounding speech directly in your browser</em>
|
22 |
</div>
|
23 |
|
24 |
+
[](https://huggingface.co/spaces/snackshell/amharic-tts)
|
|
|
|
|
|
|
|
|
|
|
25 |
|
26 |
## Features β¨
|
27 |
- π£οΈ Native Amharic voice support (Male & Female)
|
|
|
37 |
| Ameha | Male | `am-ET-AmehaNeural`|
|
38 |
| Mekdes | Female | `am-ET-MekdesNeural`|
|
39 |
|
40 |
+
## How to Use π
|
41 |
+
1. Type/paste Amharic text in the input box
|
42 |
+
2. Select preferred voice (Ameha or Mekdes)
|
43 |
+
3. Click "α΅αα
αα α" (Generate Audio)
|
44 |
+
4. Play the generated audio using the built-in player
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
45 |
|
46 |
## Technical Details π§
|
|
|
47 |
```mermaid
|
48 |
graph TD
|
49 |
A[User Interface] --> B(Gradio Frontend)
|
|
|
51 |
C --> D[Microsoft Cognitive Services]
|
52 |
```
|
53 |
|
54 |
+
### Built With
|
55 |
+
- π Python 3.10+
|
56 |
+
- ποΈ Gradio (Web Interface)
|
57 |
+
- π edge-tts (TTS Engine)
|
58 |
+
- β‘ asyncio (Async Operations)
|
|
|
59 |
|
60 |
+
## Local Development π»
|
61 |
+
```bash
|
62 |
+
git clone https://github.com/snackshell/amharic-tts.git
|
63 |
+
cd amharic-tts
|
64 |
+
pip install -r requirements.txt
|
65 |
+
python app.py
|
66 |
+
```
|
67 |
|
68 |
## License π
|
69 |
+
This project is licensed under the [MIT License](LICENSE)
|
70 |
|
71 |
## Acknowledgments π
|
72 |
- Microsoft Edge TTS services
|
73 |
+
- Hugging Face for hosting
|
74 |
+
- Gradio team for the web framework
|
75 |
+
- Ethiopian tech community for support
|
76 |
|
77 |
+
[π GitHub Repository](https://github.com/snackshell/amharic-tts) | [π Report Issues](https://github.com/snackshell/amharic-tts/issues)
|
|
|
|
|
|
|
|
|
|
|
|
|
78 |
```
|
79 |
+
|
80 |
+
Key changes made for Hugging Face Spaces:
|
81 |
+
1. Added Spaces metadata header
|
82 |
+
2. Changed image path to absolute URL
|
83 |
+
3. Added "Open in Spaces" badge
|
84 |
+
4. Simplified installation to focus on Space usage
|
85 |
+
5. Reorganized sections for ML Hub context
|
86 |
+
6. Added direct GitHub links at bottom
|
87 |
+
7. Removed redundant contribution instructions (link to GitHub instead)
|
88 |
+
8. Updated acknowledgments to include Hugging Face
|
89 |
+
|
90 |
+
Keep your existing `requirements.txt` file - Hugging Face Spaces will automatically use it for dependency installation.
|