This is an individual Natural Language Processing (NLP) project focused on developing an end-to-end speech recognition tool for the low-resource Dholuo language using OpenAI’s Whisper model.
# 💬 Dholuo Automatic Speech Recognition (ASR) Project
*Empowering Low-Resource Language Access with Whisper | NLP + Web App Development*
## 📍 Nairobi, Kenya | Sept 2025 – Ongoing
---
## 🧠 Overview
This is an **individual NLP research project** focused on building an **end-to-end Automatic Speech Recognition (ASR) tool** for **Dholuo**, a low-resource language spoken in Kenya. The system is powered by **OpenAI’s Whisper model**, fine-tuned to better understand Dholuo phonetics and vocabulary.
> 🗣️ The project aims to enhance **language accessibility**, **education**, and **digital documentation** for underrepresented African languages.
---
## 🎯 Key Objectives
- 📥 Collect & preprocess **Dholuo speech data** using Mozilla Common Voice
- 🧽 Normalize and clean transcription data (tokenization, casing, punctuation)
- 🔧 Fine-tune **Whisper** via transfer learning for Dholuo-specific ASR
- 📊 Evaluate model accuracy with **WER** & **CER**
- 🌐 Deploy a live **Streamlit web app** for transcription
- 🧪 Provide a **Gradio prototype** for real-time testing
---
## 🛠️ Tech Stack & Tools
| Task | Tools / Frameworks |
|--------------------------|-------------------------------------------------------------|
| Data Collection | `Mozilla Common Voice`, `Python scripts` |
| Preprocessing | `NLTK`, `NumPy`, `re`, `Whisper-compatible text cleaning` |
| Model Training | `Whisper`, `Google Colab`, `PyTorch`, `Transfer Learning` |
| Prototyping | `Gradio`, `Streamlit` |
| Evaluation | `WER`, `CER`, `scikit-learn`, `JiWER` |
---
## 📂 Project Structure
```
dholuo-asr/
│
├── 1. ASR Project: Filtering ASR tsv files/
├── 2. ASR Project - File Conversion/
├── 3. ASR Projects - Mapping & Filtering/
├── 4. ASR Project - Preprocessing/
├── 5. ASR Project - Training/
└── README.md
```
---
## 🔄 …