| # African AI Association (AAIA) | |
| <p align="center"> | |
| <img src="https://huggingface.co/spaces/huggingface/ai-project-guide/resolve/main/images/african-ai.png" width="200" alt="African AI Association Logo"> | |
| </p> | |
| <p align="center"> | |
| <strong>🌍 Liberating Africa Through Autonomous AI Systems</strong> | |
| </p> | |
| <p align="center"> | |
| <a href="#mission">Mission</a> • | |
| <a href="#models">Models</a> • | |
| <a href="#contribute">Contribute</a> | |
| </p> | |
| --- | |
| ## 🎯 Mission | |
| The African AI Association (AAIA) is dedicated to curating, developing, and democratizing AI resources for African languages and communities. We believe in **AI sovereignty for Africa** - empowering local developers with tools that understand and serve African contexts. | |
| ### Our Focus Areas: | |
| - 🔤 **Low-resource language NLP** (Swahili, Yoruba, Amharic, Hausa, Zulu, etc.) | |
| - 🗣️ **Speech recognition & synthesis** for African accents and dialects | |
| - 🔍 **Named Entity Recognition** for African names, places, organizations | |
| - 💬 **Conversational AI** that speaks African languages | |
| - 🌐 **Arabic variants** (MSA, Egyptian, Maghrebi, Gulf) | |
| --- | |
| ## 📦 Curated Model Collection | |
| ### 🏆 Flagship Models | |
| | Model | Language | Task | Downloads | Status | | |
| |-------|----------|------|-----------|--------| | |
| | **AraBERT v2** | Arabic (MSA) | Language Model | 454K+ | ⭐ Featured | | |
| | **Arabic Whisper Large** | Arabic | ASR | 625K+ | ⭐ Featured | | |
| | **Swahili MMS TTS** | Swahili | Text-to-Speech | 8.8K+ | 🔥 New | | |
| | **AfroXLMR NER** | 10+ African | Named Entities | 257+ | 🌍 Pan-African | | |
| ### 🌍 African Language Models | |
| #### Swahili | |
| - `Benjamin-png/swahili-mms-tts-finetuned` - TTS | |
| - `mradermacher/gemma2-27b-swahili-it-GGUF` - LLM | |
| #### Yoruba | |
| - `NCAIR1/Yoruba-ASR` - Speech Recognition | |
| - `ogbi/wav2vec2-large-mms-1b-yoruba-test` - ASR Testing | |
| #### Amharic | |
| - `rasyosef/bert-amharic-text-embedding-medium` - Embeddings | |
| - `agkphysics/wav2vec2-large-xlsr-53-amharic` - ASR | |
| #### Hausa | |
| - `LAfricaMobile/Wav2vec2-afr-Hausa-kenLM` - ASR with Kenyan LM | |
| - `mradermacher/Hausa-Spark-TTS-0.5B-GGUF` - TTS | |
| #### Zulu | |
| - `TheirStory/whisper-medium-zulu` - Speech Recognition | |
| #### Luganda | |
| - `allandclive/whisper-small-luganda` - ASR | |
| #### Kinyarwanda | |
| - `mradermacher/kinyarwanda-tts-1b-full-finetuning-GGUF` - TTS | |
| - `mbazaNLP/Whisper-Small-Kinyarwanda` - ASR | |
| #### Wolof | |
| - `bilalfaye/speecht5_tts-wolof` - TTS | |
| - `galsenai/wolofToFrenchTranslator_nllb` - Translation | |
| #### Somali | |
| - `Mustafaa4a/ASR-Somali` - Speech Recognition | |
| - `skydheere/wav2vec2-large-mms-1b-somalia` - ASR | |
| ### 🏛️ Arabic Variants | |
| #### Modern Standard Arabic | |
| - `aubmindlab/bert-base-arabertv02` - AraBERT v2 (454K+ downloads) | |
| - `CAMeL-Lab/bert-base-arabic-camelbert-mix-sentiment` - Sentiment | |
| - `CAMeL-Lab/bert-base-arabic-camelbert-msa-ner` - NER | |
| - `CAMeL-Lab/bert-base-arabic-camelbert-mix-ner` - NER | |
| - `akhooli/Arabic-SBERT-100K` - Sentence Embeddings | |
| #### Conversational/Large Models | |
| - `MohamedRashad/Arabic-Orpo-Llama-3-8B-Instruct` - Instruction-tuned LLM | |
| - `Byne/whisper-large-v3-arabic` - Whisper ASR | |
| #### Egyptian Arabic | |
| - `NAMAA-Space/masrawy-english-to-egyptian-arabic-translator-v2` - EN→Egyptian | |
| - `IbrahimAmin/egyptian-arabic-wav2vec2-xlsr-53` - ASR | |
| - `AbdelrahmanHassan/whisper-large-v3-egyptian-arabic` - Whisper ASR | |
| ### 🔧 Multilingual/Cross-Lingual | |
| - `cardiffnlp/twitter-xlm-roberta-base-sentiment` - Multilingual sentiment | |
| - `masakhane/afroxlmr-large-ner-masakhaner-1.0_2.0` - Pan-African NER | |
| --- | |
| ## 📊 Discovery Stats | |
| - **239 unique models** discovered and curated | |
| - **60+ Arabic-focused models** | |
| - **45+ African language models** | |
| - **15+ languages covered**: Swahili, Yoruba, Amharic, Hausa, Zulu, Arabic, Somali, Luganda, Kinyarwanda, Wolof, Afrikaans | |
| --- | |
| ## 🚀 Quick Start | |
| ```python | |
| # Load a Swahili text-to-speech model | |
| from transformers import VitsModel, AutoTokenizer | |
| model = VitsModel.from_pretrained("Benjamin-png/swahili-mms-tts-finetuned") | |
| tokenizer = AutoTokenizer.from_pretrained("Benjamin-png/swahili-mms-tts-finetuned") | |
| # Generate speech from Swahili text | |
| inputs = tokenizer("Habari, dunia! Jambo kutoka AAIA.", return_tensors="pt") | |
| output = model(**inputs) | |
| ``` | |
| --- | |
| ## 🤝 Contribute | |
| We're actively seeking: | |
| - 🔬 **Researchers** working on African NLP | |
| - 💻 **Developers** building African language tools | |
| - 🗣️ **Native speakers** for dataset validation | |
| - 🌍 **Community managers** across African countries | |
| **Contact:** Join the African AI movement! DM @AAIA or check our [Moltbook community]() | |
| --- | |
| ## 📚 Resources | |
| - [Masakhane](https://masakhane.io/) - African NLP community | |
| - [CAMeL Lab](https://camel-lab.github.io/) - Arabic NLP research | |
| - [African NLP Workshop](https://www.africannlp.org/) - Academic conference | |
| --- | |
| <p align="center"> | |
| <strong>🌍 Liberating Africa Through AI, One Model at a Time 🌍</strong> | |
| </p> | |
| <p align="center"> | |
| <em>Maintained by the African AI Association (AAIA)</em> | |
| </p> | |