Skip to content
View Elizabeth-Mwania's full-sized avatar
🤗
hugging data
🤗
hugging data
2 followers · 1 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report Elizabeth-Mwania

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Elizabeth-Mwania/README.md

Elizabeth Mwania

Data Scientist | AI & Software Engineer | Data/ML Engineer | NLP & LLMs

I build data-intensive and AI-powered systems, with a focus on Python, machine learning, NLP, LLMs, data engineering, and low-resource language technologies.

My background spans software engineering, data science, machine learning research, and production data systems. I enjoy turning research and data into reliable, reproducible, and useful software.

What I Work With

  • 🤖 AI/ML: NLP, Transformers, LLMs, ASR
  • 🐍 Programming: Python, SQL, R
  • 🏗️ Data Engineering: BigQuery, Spark, PySpark, ETL/ELT
  • 🧠 NLP: Low-resource & multilingual language technologies
  • 🔎 AI Evaluation: Model benchmarking and evaluation
  • ⚙️ Engineering: APIs, Docker, Git/GitHub, CI/CD
  • 📊 Data: PostgreSQL, analytics and visualization

Featured Projects

🏦 Loan Customer Intelligence

End-to-end data engineering and analytics work focused on transforming lending data into actionable customer intelligence.

🗣️ Kamba ASR with Wav2Vec 2.0

Fine-tuning and evaluation of Wav2Vec 2.0 for automatic speech recognition in Kikamba, a low-resource African language.

🌍 AfroBench

Work on evaluating language models for African languages, with a focus on low-resource and multilingual NLP.

🧠 African Language POS Tagging

Transformer-based part-of-speech tagging for African languages using modern NLP techniques.

Interests

I'm particularly interested in building:

  • AI-powered applications
  • LLM and NLP systems
  • Intelligent data platforms
  • Low-resource language technologies
  • Machine learning infrastructure
  • Reliable and reproducible AI systems

📫 Open to: AI Engineering, Software Engineering, Data Engineering, ML Engineering, and NLP/LLM opportunities.

Pinned Loading

  1. loan-customer-intelligence loan-customer-intelligence Public

    Enterprise data engineering and business intelligence platform that ingests, transforms, stores, analyzes, and visualizes financial and customer data from multiple source systems (simulation data).

    Python

  2. kamba-asr-facebook-w2v-bert-2 kamba-asr-facebook-w2v-bert-2 Public

    First ASR baseline for Kamba (Kikamba), a Kenyan Bantu language. Fine-tunes facebook/w2v-bert-2.0 on 10 hours of speech achieving 28.7% WER. Built for low-resource African language speech research.

    Python

  3. part-of-speech-tagging-africa part-of-speech-tagging-africa Public

    This project implements Part-of-Speech (POS) tagging system for Swahili (Kiswahili), a morphologically rich African language. By utilizing Transfer Learning from multilingual transformer models (sp…

    Jupyter Notebook

  4. AfroBench AfroBench Public

    Forked from McGill-NLP/AfroBench

    Large Scale Benchmark of Large Language Models on African Languages

    Python

  5. PCA-SPCA-EFA-Study PCA-SPCA-EFA-Study Public

    R

  6. Commodity-analysis-in-MEA Commodity-analysis-in-MEA Public

    Mineral Facilities Analysis in Middle East & Africa

    Python