{"id":23592799,"url":"https://github.com/tushar2704/hinglish","last_synced_at":"2026-05-19T19:10:20.611Z","repository":{"id":187446605,"uuid":"676928277","full_name":"tushar2704/HINGLISH","owner":"tushar2704","description":"This project focuses on building a Neural Machine Translation (NMT) system to translate English sentences to Hindi.","archived":false,"fork":false,"pushed_at":"2023-08-16T11:01:18.000Z","size":34,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-12-27T08:16:45.209Z","etag":null,"topics":["data-science","hindi-english-translation","nlp","nmt","python"],"latest_commit_sha":null,"homepage":"https://tushar-aggarwal.com","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tushar2704.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-08-10T10:34:50.000Z","updated_at":"2023-08-10T10:46:24.000Z","dependencies_parsed_at":null,"dependency_job_id":"5b10d688-a2ba-4328-8788-2e55f58a4e9f","html_url":"https://github.com/tushar2704/HINGLISH","commit_stats":null,"previous_names":["tushar2704/hinglish"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tushar2704%2FHINGLISH","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tushar2704%2FHINGLISH/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tushar2704%2FHINGLISH/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tushar2704%2FHINGLISH/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tushar2704","download_url":"https://codeload.github.com/tushar2704/HINGLISH/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239432754,"owners_count":19637798,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["data-science","hindi-english-translation","nlp","nmt","python"],"created_at":"2024-12-27T08:15:47.369Z","updated_at":"2026-05-19T19:10:20.545Z","avatar_url":"https://github.com/tushar2704.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# English to Hindi Neural Machine Translation\n\n![Python](https://img.shields.io/badge/Python-3776AB.svg?style=for-the-badge\u0026logo=Python\u0026logoColor=white)\n![Pandas](https://img.shields.io/badge/pandas-%23150458.svg?style=for-the-badge\u0026logo=pandas\u0026logoColor=white)\n![PyTorch](https://img.shields.io/badge/PyTorch-%23EE4C2C.svg?style=for-the-badge\u0026logo=PyTorch\u0026logoColor=white)\n![TensorFlow](https://img.shields.io/badge/TensorFlow-%23FF6F00.svg?style=for-the-badge\u0026logo=TensorFlow\u0026logoColor=white)\n![Microsoft Excel](https://img.shields.io/badge/Microsoft_Excel-217346?style=for-the-badge\u0026logo=microsoft-excel\u0026logoColor=white)\n![Canva](https://img.shields.io/badge/Canva-%2300C4CC.svg?style=for-the-badge\u0026logo=Canva\u0026logoColor=white)\n![Visual Studio Code](https://img.shields.io/badge/Visual%20Studio%20Code-0078d7.svg?style=for-the-badge\u0026logo=visual-studio-code\u0026logoColor=white)\n![Markdown](https://img.shields.io/badge/markdown-%23000000.svg?style=for-the-badge\u0026logo=markdown\u0026logoColor=white)\n![Microsoft Office](https://img.shields.io/badge/Microsoft_Office-D83B01?style=for-the-badge\u0026logo=microsoft-office\u0026logoColor=white)\n![Microsoft Word](https://img.shields.io/badge/Microsoft_Word-2B579A?style=for-the-badge\u0026logo=microsoft-word\u0026logoColor=white)\n![GitHub](https://img.shields.io/badge/github-%23121011.svg?style=for-the-badge\u0026logo=github\u0026logoColor=white)\n![Windows Terminal](https://img.shields.io/badge/Windows%20Terminal-%234D4D4D.svg?style=for-the-badge\u0026logo=windows-terminal\u0026logoColor=white)\n## Overview\n\nThis project focuses on building a Neural Machine Translation (NMT) system to translate English sentences to Hindi. NMT has revolutionized the field of language translation by leveraging deep learning techniques to produce more accurate and natural-sounding translations.\n\n## Features\n\n- **Encoder-Decoder Architecture**: The NMT system employs an encoder-decoder architecture, where the encoder encodes the input English sentence into a fixed-size context vector, and the decoder generates the corresponding Hindi translation from the context vector.\n  \n- **Attention Mechanism**: To handle longer sentences and capture relevant information effectively, an attention mechanism is integrated. This allows the model to focus on different parts of the input sentence while generating the output.\n\n- **Data Preprocessing**: The project includes data preprocessing steps to clean and normalize input sentences, ensuring better alignment and accuracy in translation.\n\n- **Training and Evaluation**: The model is trained on a parallel corpus of English-Hindi sentence pairs. During training, the model learns to minimize the translation loss. The evaluation process demonstrates the model's translation quality with selected input sentences.\n\n- **Visualization of Attention**: The project offers a visualization of attention weights, showing how the model attends to different parts of the input during translation.\n\n## Usage\n\n1. **Data Preparation**: Prepare your parallel corpus of English-Hindi sentence pairs. Ensure that your data is properly formatted and cleaned.\n\n2. **Model Configuration**: Set up the encoder and attention-based decoder architecture in the code. Define the hyperparameters, such as hidden size, learning rate, and dropout rate.\n\n3. **Training**: Train the model using the provided training functions. Adjust the number of training iterations, print intervals, and other parameters as needed.\n\n4. **Evaluation and Visualization**: Evaluate the model's translation quality using the `evaluateAndShowAttention` function. Provide your English input sentences and observe both the translated output and attention visualization.\n\n## Dependencies\n\n- Python 3.x\n- PyTorch\n- Matplotlib\n\n## Contributing\n\nContributions to this project are welcome! Whether it's improving the model's performance, enhancing the visualization, or extending the features, your contributions can make a significant impact.\n\n## License\n\nThis project is licensed under the [MIT License](LICENSE).\n\n**Refrences**\n-  [Learning Phrase Representations using RNN Encoder-Decoder for\n   Statistical Machine Translation](https://arxiv.org/abs/1406.1078)_\n-  [Sequence to Sequence Learning with Neural\n   Networks](https://arxiv.org/abs/1409.3215)_\n-  [Neural Machine Translation by Jointly Learning to Align and\n   Translate](https://arxiv.org/abs/1409.0473)_\n-  [A Neural Conversational Model](https://arxiv.org/abs/1506.05869)_\n\n\n## Author\n- \u003cins\u003e\u003cb\u003e©2023 Tushar Aggarwal. All rights reserved\u003c/b\u003e\u003c/ins\u003e\n- \u003cb\u003e[LinkedIn](https://www.linkedin.com/in/tusharaggarwalinseec/)\u003c/b\u003e\n- \u003cb\u003e[Medium](https://medium.com/@tushar_aggarwal)\u003c/b\u003e \n- \u003cb\u003e[Tushar-Aggarwal.com](https://www.tushar-aggarwal.com/)\u003c/b\u003e\n- \u003cb\u003e[New Kaggle](https://www.kaggle.com/tagg27)\u003c/b\u003e \n\n## Contact me!\nIf you have any questions, suggestions, or just want to say hello, you can reach out to us at [Tushar Aggarwal](mailto:info@tushar-aggarwal.com). We would love to hear from you!\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftushar2704%2Fhinglish","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftushar2704%2Fhinglish","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftushar2704%2Fhinglish/lists"}