Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/mehtachandrashekhar/ai-based-translator-tool
AI-based-translator
https://github.com/mehtachandrashekhar/ai-based-translator-tool
english-hindi-translation flask hindi huggingface huggingface-transformers python3 translation
Last synced: about 1 month ago
JSON representation
AI-based-translator
- Host: GitHub
- URL: https://github.com/mehtachandrashekhar/ai-based-translator-tool
- Owner: mehtachandrashekhar
- License: mit
- Created: 2024-03-26T07:42:03.000Z (10 months ago)
- Default Branch: main
- Last Pushed: 2024-06-23T07:03:34.000Z (7 months ago)
- Last Synced: 2024-06-24T07:48:00.506Z (7 months ago)
- Topics: english-hindi-translation, flask, hindi, huggingface, huggingface-transformers, python3, translation
- Language: Jupyter Notebook
- Homepage: https://ai-based-translator.streamlit.app/
- Size: 490 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# AI-Based Language Translation
## Overview
This project implements an AI-based language translation system using same core technologies: Encoder-Decoder architecture, Long Short-Term Memory (LSTM) networks,Bidirectional LSTM networks and Embedding layers. The system is designed to translate text from one language to another by learning from a dataset of parallel sentences.
## Features
- **Encoder-Decoder Architecture**: Utilizes a sequence-to-sequence model to handle input and output sequences of different lengths.
- **LSTM Networks**: Employs LSTM cells to manage long-term dependencies and improve translation accuracy.
- **Embedding Layers**: Converts words into dense vectors that capture semantic meanings, enhancing the model's understanding of language.
- **Bidirectional LSTM Networks**: Improves context capture by processing input sequences in both forward and backward directions.
## Usage
### Training the Model
1. **Prepare your dataset**: Ensure you have a dataset of parallel sentences in the source and target languages.
2. **Preprocess the data**: Tokenize the sentences and create the necessary input-output pairs.
### Translating Text
Once the model is trained, you can use it to translate sentences:
**Translate a sentence**:
```bash
python translate.py --sentence "Your sentence here"
```
## Directory Structure
```
ai-language-translation/
│
├── app/
│ ├── __init__.py # initialization application
| ├── model.py # model from hugging face
| └── routes.py # request api
│
├── models/
│ └── dictionary.pkl # Pre-trained model (if available)
│
├── notebook/
│ ├── testing.ipynb # examplenotebook1
│ └── translator.ipynb # examplenotebook2
│
├── .gitignore # gitignore
├── index.html # web-translator
├── README.md # Readme.md
├── requirements.txt # python requirements
├── run.py # app run
└── style.css # styling to index.html
```
## License
This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.
## Acknowledgements
- This project is inspired by various sequence-to-sequence models in natural language processing.
- Thanks to the open-source community for providing valuable resources and tools.
## Contributors
