Spaces:
Sleeping
Sleeping
Update README.md
Browse files
README.md
CHANGED
@@ -11,4 +11,101 @@ license: apache-2.0
|
|
11 |
short_description: language_detector
|
12 |
---
|
13 |
|
14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
short_description: language_detector
|
12 |
---
|
13 |
|
14 |
+
# Language Detection with Gradio
|
15 |
+
|
16 |
+
This repository contains a simple language detection application built with [Gradio](https://gradio.app/) and [Transformers](https://huggingface.co/transformers/). The application leverages a pre-trained language detection model to identify the language of a given text input. The user interface is created using Gradio, making it easy to run and share as a web app.
|
17 |
+
|
18 |
+
## Features
|
19 |
+
|
20 |
+
- **Language Detection:** Enter text in any language and the model will output the detected language.
|
21 |
+
- **Interactive UI:** A Gradio interface provides an easy-to-use web interface for testing and demos.
|
22 |
+
- **Examples:** Predefined examples in multiple languages (English, French, Spanish, Arabic) are provided for quick testing.
|
23 |
+
|
24 |
+
## Code Overview
|
25 |
+
|
26 |
+
The main script performs the following tasks:
|
27 |
+
|
28 |
+
1. **Importing Libraries:**
|
29 |
+
- Imports `gradio` for building the web interface.
|
30 |
+
- Imports `pipeline` from `transformers` to load the pre-trained language detection model.
|
31 |
+
|
32 |
+
2. **Defining the Language Detection Function:**
|
33 |
+
- `detect_language(text)`: This function takes a text string as input, processes it through the language detection model, and returns the detected language label.
|
34 |
+
- **Note:** Ensure that the variable `language_detector` is properly initialized with a language detection pipeline (e.g., using `pipeline("text-classification", model="your-model-name")`). This snippet assumes that `language_detector` is already defined elsewhere or should be added before using the function.
|
35 |
+
|
36 |
+
3. **Setting Up Examples:**
|
37 |
+
- A list of example inputs in English, French, Spanish, and Arabic to demonstrate the functionality.
|
38 |
+
|
39 |
+
4. **Creating the Gradio Interface:**
|
40 |
+
- An instance of `gr.Interface` is created with the function `detect_language`, input and output components, title, description, and examples.
|
41 |
+
- The interface is then launched with `iface.launch()`.
|
42 |
+
|
43 |
+
## Installation
|
44 |
+
|
45 |
+
1. **Clone the Repository:**
|
46 |
+
|
47 |
+
```bash
|
48 |
+
git clone https://github.com/yourusername/language-detection-app.git
|
49 |
+
cd language-detection-app
|
50 |
+
```
|
51 |
+
|
52 |
+
2. **Set Up a Virtual Environment (Optional but Recommended):**
|
53 |
+
|
54 |
+
```bash
|
55 |
+
python -m venv venv
|
56 |
+
source venv/bin/activate # On Windows: venv\Scripts\activate
|
57 |
+
```
|
58 |
+
|
59 |
+
3. **Install the Required Dependencies:**
|
60 |
+
|
61 |
+
```bash
|
62 |
+
pip install gradio transformers
|
63 |
+
```
|
64 |
+
|
65 |
+
4. **Initialize the Language Detector:**
|
66 |
+
|
67 |
+
Before running the code, ensure that the `language_detector` pipeline is initialized. For example, you might add the following code at the top of your script:
|
68 |
+
|
69 |
+
```python
|
70 |
+
from transformers import pipeline
|
71 |
+
|
72 |
+
language_detector = pipeline("text-classification", model="papluca/xlm-roberta-base-language-detection")
|
73 |
+
```
|
74 |
+
|
75 |
+
Replace `"papluca/xlm-roberta-base-language-detection"` with the model of your choice if needed.
|
76 |
+
|
77 |
+
## Usage
|
78 |
+
|
79 |
+
1. **Run the Application:**
|
80 |
+
|
81 |
+
```bash
|
82 |
+
python your_script_name.py
|
83 |
+
```
|
84 |
+
|
85 |
+
2. **Access the Gradio Interface:**
|
86 |
+
|
87 |
+
Once the script is running, a local URL (e.g., http://127.0.0.1:7860) will be displayed in your terminal. Open this URL in your web browser to interact with the language detection application.
|
88 |
+
|
89 |
+
3. **Test the Application:**
|
90 |
+
|
91 |
+
- Type or paste text into the input textbox.
|
92 |
+
- Click the "Submit" button to see the detected language.
|
93 |
+
- You can also use the provided examples to test the functionality.
|
94 |
+
|
95 |
+
## Customization
|
96 |
+
|
97 |
+
- **Model Choice:** You can swap out the language detection model by changing the model parameter in the `pipeline` initialization.
|
98 |
+
- **Interface Customization:** Modify the Gradio interface parameters (e.g., title, description, input/output types) to better suit your needs.
|
99 |
+
- **Deployment:** The Gradio app can be easily shared or deployed using services like [Hugging Face Spaces](https://huggingface.co/spaces).
|
100 |
+
|
101 |
+
## Contributing
|
102 |
+
|
103 |
+
Contributions are welcome! Feel free to open issues or submit pull requests to enhance the functionality of this project.
|
104 |
+
|
105 |
+
## License
|
106 |
+
|
107 |
+
This project is licensed under the [MIT License](LICENSE).
|
108 |
+
|
109 |
+
---
|
110 |
+
|
111 |
+
Enjoy building and sharing your language detection app!
|