Skip to content
@GhanaNLP

Ghana NLP

Open Source Initiative focused on Natural Language Processing (NLP) of Ghanaian Languages, & its Applications to Local Problems
README.adoc

We are currently working on research projects that improve machine translation, speech syhthesis and speech recognition for African languages Our community is made up of over 500 contributers who support several projects on a voluntary basis. We believe in community driven projects that drive innovation in natural language processing for Ghanaian languages.

You can join our community by sending a request via email - info@ghananlp.org.

Featured Projects

  • nsanku, Evaluating zero-shot translation performance of LLMs for Ghanaian languages

  • GhanaLLM, A project to experiment with LLMs for Ghanaian languages

  • nkrane, Terminolgy Controlled Machine Translation for Ghanaian languages

Popular repositories Loading

  1. kasa kasa Public

    English to Twi translation system being put together by the GhanaNLP team

    Jupyter Notebook 39 17

  2. ABENA ABENA Public

    Training Scripts for Various Language Models - BERT/mBERT, distilBERT, etc

    Python 24 7

  3. nsanku nsanku Public

    Evaluating zero-shot translation performance of LLMs for Ghanaian languages

    HTML 15 7

  4. ghanaian-nlp-datasets-models ghanaian-nlp-datasets-models Public

    This repository curates NLP datasets and models for languages spoken in Ghana.

    10 6

  5. ghananlp.github.io ghananlp.github.io Public

    Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

    JavaScript 5 8

  6. OCR-on-pdf OCR-on-pdf Public

    Chararacter recognition of PDF file to text file

    Jupyter Notebook 5 1

Repositories

Showing 10 of 70 repositories
  • nsanku-tts-benchmark Public

    Benchmarking TTS models on Ghanaian languages — ASR character error rate across 12 Ghanaian language varieties

    GhanaNLP/nsanku-tts-benchmark's past year of commit activity
    Python 0 0 0 0 Updated Sep 12, 2026
  • nsanku-asr-benchmark Public

    Benchmarking ASR models on Ghanaian languages — WER/CER evaluation across 41 Ghanaian language varieties

    GhanaNLP/nsanku-asr-benchmark's past year of commit activity
    Python 0 1 0 0 Updated Sep 11, 2026
  • website Public
    GhanaNLP/website's past year of commit activity
    HTML 4 3 5 (1 issue needs help) 0 Updated Sep 10, 2026
  • ghana-voice-chat Public

    Speak Twi, get a Twi reply — a full-stack voice chat with ASR (griot-nano-1), Gemini, and Twi TTS on Modal

    GhanaNLP/ghana-voice-chat's past year of commit activity
    Python 0 0 0 0 Updated Sep 9, 2026
  • ghana-speech-id Public

    Language identification for Ghanaian and West African speech, over IPA phonemes

    GhanaNLP/ghana-speech-id's past year of commit activity
    Python 0 1 0 0 Updated Aug 27, 2026
  • azure-api-management-monetization Public Forked from microsoft/azure-api-management-monetization
    GhanaNLP/azure-api-management-monetization's past year of commit activity
    TypeScript 0 MIT 38 0 0 Updated Aug 22, 2026
  • poto-tts Public

    Ghanaian English text-to-speech: Kokoro on sherpa-onnx, with 44,321 Ghanaian words compiled into an espeak-ng dictionary so names, places and titles are pronounced properly

    GhanaNLP/poto-tts's past year of commit activity
    Python 0 MIT 1 0 0 Updated Aug 20, 2026
  • ghana-english-g2p Public

    Ghanaian English grapheme-to-phoneme: a 104k-word Ghanaian pronunciation lexicon, with espeak-ng behind it for out-of-vocabulary words.

    GhanaNLP/ghana-english-g2p's past year of commit activity
    Python 0 MIT 1 0 0 Updated Aug 20, 2026
  • ghana-speech-english-ipa-latents-data-prep Public

    Data prep for the VoxCPM-2 Ghanaian TTS finetune: phoneme ASR, AudioVAE latent precompute, and the IPA latent datasets it publishes

    GhanaNLP/ghana-speech-english-ipa-latents-data-prep's past year of commit activity
    Python 0 1 0 0 Updated Aug 13, 2026
  • speecheval-builder Public
    GhanaNLP/speecheval-builder's past year of commit activity
    Python 0 1 0 0 Updated Aug 13, 2026
View all repositories

Top languages

Loading…

Most used topics

Loading…