Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Prekshagp/A-Neural-Approach-to-Speech-to-Text-Translation-of-Low-Resource-Lamguage

Domain:

natural language processing

Record type:

software
Creator:
Pre
Host:
# Konkani Vakya 🌍 **Konkani Vakya** is a modern, AI-powered web application designed to bridge the gap between spoken Konkani and written English. Using advanced linguistic AI patterns, it transcribes Konkani speech and provides accurate English translations, empowering users to learn and preserve the Konkani language. --- ## ✨ Key Features - 🎙️ **Simultaneous Transcription & Translation**: Speak in Konkani and watch as the app transcribes your words into Devanagari script and translates them into English in real-time. - 🗂️ **Personal Flashcards**: Save your translations as flashcards to practice and build your vocabulary. - 🌓 **Modern & Responsive UI**: A premium user interface built with Radix UI and Tailwind CSS, featuring a beautiful dark-mode inspired aesthetic. - 🤖 **AI-Driven Pipeline**: Powered by Genkit and Google Gemini, the app uses a sophisticated multi-step pipeline for language identification, grammatical correction, and transliteration. --- ## 🚀 Tech Stack - **Framework**: Next.js 14 (App Router) - **AI Framework**: Genkit - **Database & Auth**: Firebase (Firestore & Auth) - **Styling**: Tailwind CSS - **Components**: Radix UI & Lucide React - **Validation**: Zod --- ## 🛠️ Getting Started ### Prerequisites - Node.js 18+ - A Google Cloud Project with Gemini API access - A Firebase project for Authentication and Firestore ### Installation 1. **Clone the repository**: ```bash git clone github.com cd konkani-vakya ``` 2. **Install dependencies**: ```bash npm install ``` 3. **Set up environment variables**: Create a `.env.local` file in the root directory and add your Firebase and Genkit credentials: ```env GOOGLE_GENAI_API_KEY=your_gemini_api_key NEXT_PUBLIC_FIREBASE_API_KEY=your_key NEXT_PUBLIC_FIREBASE_AUTH_DOMAIN=your_project.firebaseapp.com NEXT_PUBLIC_FIREBASE_PROJECT_ID=your_project_id # ... other firebase vars ``` 4. **Run the development server**: ```bash npm run dev ``` --- ## 🧠 How …

Visit

github.com

Tasks

automatic speech recognitionmachine translationspeech processingspeech translation

Similar

Adversarial Text-to-Speech for low-resource languagesText-To-Speech Data Augmentation for Low Resource Speech RecognitionStrategies for improving low resource speech to text translation relying on pre-trained ASR modelsBreaking the Curse ofMultilinguality inMany-to-Many Speech-to-Text Translation via a Resource-AwareMixture of Speech EncodersSyarotto/speech-to-text-translationMachine Learning Approach to English-Afaan Oromo Text-Text Translation: Using Attention based Neural Machine Translation

Adversarial Text-to-Speech for low-resource languages

Improving the adversarial TTS models for low-resource languages by utilizing the high-frequency similarities between the different languages.

Text-To-Speech Data Augmentation for Low Resource Speech Recognition

Nowadays, the main problem of deep learning techniques used in the development of automatic speech r

Strategies for improving low resource speech to text translation relying on pre-trained ASR models

This paper presents techniques and findings for improving the performance of low-resource speech to

Breaking the Curse ofMultilinguality inMany-to-Many Speech-to-Text Translation via a Resource-AwareMixture of Speech Encoders

Multimodal large language models (MLLMs) have achieved significant success in speech-to-text transla

Syarotto/speech-to-text-translation

Code for the final project "Speech-to-Text Translation in Swahili" of LING 575C: Speech Technology f

Machine Learning Approach to English-Afaan Oromo Text-Text Translation: Using Attention based Neural Machine Translation