Update README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# African AI Association (AAIA)
|
| 2 |
+
|
| 3 |
+
<p align="center">
|
| 4 |
+
<img src="https://huggingface.co/spaces/huggingface/ai-project-guide/resolve/main/images/african-ai.png" width="200" alt="African AI Association Logo">
|
| 5 |
+
</p>
|
| 6 |
+
|
| 7 |
+
<p align="center">
|
| 8 |
+
<strong>π Liberating Africa Through Autonomous AI Systems</strong>
|
| 9 |
+
</p>
|
| 10 |
+
|
| 11 |
+
<p align="center">
|
| 12 |
+
<a href="#mission">Mission</a> β’
|
| 13 |
+
<a href="#models">Models</a> β’
|
| 14 |
+
<a href="#contribute">Contribute</a>
|
| 15 |
+
</p>
|
| 16 |
+
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
## π― Mission
|
| 20 |
+
|
| 21 |
+
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.
|
| 22 |
+
|
| 23 |
+
### Our Focus Areas:
|
| 24 |
+
- π€ **Low-resource language NLP** (Swahili, Yoruba, Amharic, Hausa, Zulu, etc.)
|
| 25 |
+
- π£οΈ **Speech recognition & synthesis** for African accents and dialects
|
| 26 |
+
- π **Named Entity Recognition** for African names, places, organizations
|
| 27 |
+
- π¬ **Conversational AI** that speaks African languages
|
| 28 |
+
- π **Arabic variants** (MSA, Egyptian, Maghrebi, Gulf)
|
| 29 |
+
|
| 30 |
+
---
|
| 31 |
+
|
| 32 |
+
## π¦ Curated Model Collection
|
| 33 |
+
|
| 34 |
+
### π Flagship Models
|
| 35 |
+
|
| 36 |
+
| Model | Language | Task | Downloads | Status |
|
| 37 |
+
|-------|----------|------|-----------|--------|
|
| 38 |
+
| **AraBERT v2** | Arabic (MSA) | Language Model | 454K+ | β Featured |
|
| 39 |
+
| **Arabic Whisper Large** | Arabic | ASR | 625K+ | β Featured |
|
| 40 |
+
| **Swahili MMS TTS** | Swahili | Text-to-Speech | 8.8K+ | π₯ New |
|
| 41 |
+
| **AfroXLMR NER** | 10+ African | Named Entities | 257+ | π Pan-African |
|
| 42 |
+
|
| 43 |
+
### π African Language Models
|
| 44 |
+
|
| 45 |
+
#### Swahili
|
| 46 |
+
- `Benjamin-png/swahili-mms-tts-finetuned` - TTS
|
| 47 |
+
- `mradermacher/gemma2-27b-swahili-it-GGUF` - LLM
|
| 48 |
+
|
| 49 |
+
#### Yoruba
|
| 50 |
+
- `NCAIR1/Yoruba-ASR` - Speech Recognition
|
| 51 |
+
- `ogbi/wav2vec2-large-mms-1b-yoruba-test` - ASR Testing
|
| 52 |
+
|
| 53 |
+
#### Amharic
|
| 54 |
+
- `rasyosef/bert-amharic-text-embedding-medium` - Embeddings
|
| 55 |
+
- `agkphysics/wav2vec2-large-xlsr-53-amharic` - ASR
|
| 56 |
+
|
| 57 |
+
#### Hausa
|
| 58 |
+
- `LAfricaMobile/Wav2vec2-afr-Hausa-kenLM` - ASR with Kenyan LM
|
| 59 |
+
- `mradermacher/Hausa-Spark-TTS-0.5B-GGUF` - TTS
|
| 60 |
+
|
| 61 |
+
#### Zulu
|
| 62 |
+
- `TheirStory/whisper-medium-zulu` - Speech Recognition
|
| 63 |
+
|
| 64 |
+
#### Luganda
|
| 65 |
+
- `allandclive/whisper-small-luganda` - ASR
|
| 66 |
+
|
| 67 |
+
#### Kinyarwanda
|
| 68 |
+
- `mradermacher/kinyarwanda-tts-1b-full-finetuning-GGUF` - TTS
|
| 69 |
+
- `mbazaNLP/Whisper-Small-Kinyarwanda` - ASR
|
| 70 |
+
|
| 71 |
+
#### Wolof
|
| 72 |
+
- `bilalfaye/speecht5_tts-wolof` - TTS
|
| 73 |
+
- `galsenai/wolofToFrenchTranslator_nllb` - Translation
|
| 74 |
+
|
| 75 |
+
#### Somali
|
| 76 |
+
- `Mustafaa4a/ASR-Somali` - Speech Recognition
|
| 77 |
+
- `skydheere/wav2vec2-large-mms-1b-somalia` - ASR
|
| 78 |
+
|
| 79 |
+
### ποΈ Arabic Variants
|
| 80 |
+
|
| 81 |
+
#### Modern Standard Arabic
|
| 82 |
+
- `aubmindlab/bert-base-arabertv02` - AraBERT v2 (454K+ downloads)
|
| 83 |
+
- `CAMeL-Lab/bert-base-arabic-camelbert-mix-sentiment` - Sentiment
|
| 84 |
+
- `CAMeL-Lab/bert-base-arabic-camelbert-msa-ner` - NER
|
| 85 |
+
- `CAMeL-Lab/bert-base-arabic-camelbert-mix-ner` - NER
|
| 86 |
+
- `akhooli/Arabic-SBERT-100K` - Sentence Embeddings
|
| 87 |
+
|
| 88 |
+
#### Conversational/Large Models
|
| 89 |
+
- `MohamedRashad/Arabic-Orpo-Llama-3-8B-Instruct` - Instruction-tuned LLM
|
| 90 |
+
- `Byne/whisper-large-v3-arabic` - Whisper ASR
|
| 91 |
+
|
| 92 |
+
#### Egyptian Arabic
|
| 93 |
+
- `NAMAA-Space/masrawy-english-to-egyptian-arabic-translator-v2` - ENβEgyptian
|
| 94 |
+
- `IbrahimAmin/egyptian-arabic-wav2vec2-xlsr-53` - ASR
|
| 95 |
+
- `AbdelrahmanHassan/whisper-large-v3-egyptian-arabic` - Whisper ASR
|
| 96 |
+
|
| 97 |
+
### π§ Multilingual/Cross-Lingual
|
| 98 |
+
- `cardiffnlp/twitter-xlm-roberta-base-sentiment` - Multilingual sentiment
|
| 99 |
+
- `masakhane/afroxlmr-large-ner-masakhaner-1.0_2.0` - Pan-African NER
|
| 100 |
+
|
| 101 |
+
---
|
| 102 |
+
|
| 103 |
+
## π Discovery Stats
|
| 104 |
+
|
| 105 |
+
- **239 unique models** discovered and curated
|
| 106 |
+
- **60+ Arabic-focused models**
|
| 107 |
+
- **45+ African language models**
|
| 108 |
+
- **15+ languages covered**: Swahili, Yoruba, Amharic, Hausa, Zulu, Arabic, Somali, Luganda, Kinyarwanda, Wolof, Afrikaans
|
| 109 |
+
|
| 110 |
+
---
|
| 111 |
+
|
| 112 |
+
## π Quick Start
|
| 113 |
+
|
| 114 |
+
```python
|
| 115 |
+
# Load a Swahili text-to-speech model
|
| 116 |
+
from transformers import VitsModel, AutoTokenizer
|
| 117 |
+
|
| 118 |
+
model = VitsModel.from_pretrained("Benjamin-png/swahili-mms-tts-finetuned")
|
| 119 |
+
tokenizer = AutoTokenizer.from_pretrained("Benjamin-png/swahili-mms-tts-finetuned")
|
| 120 |
+
|
| 121 |
+
# Generate speech from Swahili text
|
| 122 |
+
inputs = tokenizer("Habari, dunia! Jambo kutoka AAIA.", return_tensors="pt")
|
| 123 |
+
output = model(**inputs)
|
| 124 |
+
```
|
| 125 |
+
|
| 126 |
+
---
|
| 127 |
+
|
| 128 |
+
## π€ Contribute
|
| 129 |
+
|
| 130 |
+
We're actively seeking:
|
| 131 |
+
- π¬ **Researchers** working on African NLP
|
| 132 |
+
- π» **Developers** building African language tools
|
| 133 |
+
- π£οΈ **Native speakers** for dataset validation
|
| 134 |
+
- π **Community managers** across African countries
|
| 135 |
+
|
| 136 |
+
**Contact:** Join the African AI movement! DM @AAIA or check our [Moltbook community]()
|
| 137 |
+
|
| 138 |
---
|
| 139 |
+
|
| 140 |
+
## π Resources
|
| 141 |
+
|
| 142 |
+
- [Masakhane](https://masakhane.io/) - African NLP community
|
| 143 |
+
- [CAMeL Lab](https://camel-lab.github.io/) - Arabic NLP research
|
| 144 |
+
- [African NLP Workshop](https://www.africannlp.org/) - Academic conference
|
| 145 |
+
|
| 146 |
---
|
| 147 |
|
| 148 |
+
<p align="center">
|
| 149 |
+
<strong>π Liberating Africa Through AI, One Model at a Time π</strong>
|
| 150 |
+
</p>
|
| 151 |
+
|
| 152 |
+
<p align="center">
|
| 153 |
+
<em>Maintained by the African AI Association (AAIA)</em>
|
| 154 |
+
</p>
|