VerbaSync is a web-based transcription and translation application built with React.js, Tailwind CSS, and Huggingface.js. It leverages web workers to run machine learning models directly in the browser, enabling fast and efficient transcription and translation without needing a server-side backend.
- Real-time transcription: Convert spoken language into text using Huggingface.js models.
- Instant translation: Translate transcribed text into multiple languages.
- Web Worker integration: ML models run in parallel via web workers, ensuring a smooth user experience with no performance lag.
- Responsive Design: Built using Tailwind CSS, VerbaSync is fully responsive and adapts to different screen sizes.
- React.js framework: Efficient component-based architecture for maintainability and scalability.
- Frontend: React.js
- Styling: Tailwind CSS
- Machine Learning: Huggingface.js (for transcription and translation models)
- Node.js (v14 or later)
- npm (v6 or later)
-
Clone the repository:
git clone https://github.com/Prachalitparate13/verbaSync.git cd verbaSync -
Install dependencies:
npm install
-
Start the development server:
npm start
-
Open your browser and navigate to
http://localhost:3000to view the application.
- Support for more languages: Expand the range of supported languages for transcription and translation.
- Speech-to-text analytics: Provide insights like word frequency and sentiment analysis based on transcribed text.
Contributions are welcome! To get started:
- Fork the repository.
- Create a new branch for your feature or bug fix.
- Submit a pull request once the feature or fix is complete.
This project is licensed under the MIT License.
For questions or collaboration, feel free to contact:
- Author: [Prachalit Parate]
- Email: [[email protected]]
- With Reference to: [https://github.com/jamezmca/free-scribe]