Add comprehensive language documentation

LANGUAGES.md

@@ -0,0 +1,255 @@
+# 🌍 JamboGPT - Supported Languages
+
+JamboGPT now supports **10 African languages** covering East Africa, West Africa, and beyond!
+
+## 📍 Language Coverage Map
+
+### East Africa (5 Languages)
+
+| Language | Region | Speakers | Code | Model |
+|----------|--------|----------|------|-------|
+| **Swahili** | Kenya, Tanzania, Uganda | ~100M+ | swh | facebook/mms-tts-swh |
+| **Kikuyu** | Central Kenya | ~7M | ki | BrianMwangi/African-Kikuyu-TTS |
+| **Luo** | Western Kenya | ~4M | luo | facebook/mms-tts-luo |
+| **Luhya** | Western Kenya | ~5M | luy | facebook/mms-tts-luy |
+| **Kamba** | Eastern Kenya | ~3M | kam | facebook/mms-tts-kam |
+
+### West Africa (3 Languages)
+
+| Language | Region | Speakers | Code | Model |
+|----------|--------|----------|------|-------|
+| **Yoruba** | Nigeria | ~45M | yor | facebook/mms-tts-yor |
+| **Igbo** | Nigeria | ~27M | ibo | facebook/mms-tts-ibo |
+| **Hausa** | Nigeria, Niger | ~90M | hau | facebook/mms-tts-hau |
+
+### East Africa - Horn of Africa (1 Language)
+
+| Language | Region | Speakers | Code | Model |
+|----------|--------|----------|------|-------|
+| **Amharic** | Ethiopia | ~32M | amh | facebook/mms-tts-amh |
+
+### Global (1 Language)
+
+| Language | Region | Speakers | Code | Model |
+|----------|--------|----------|------|-------|
+| **English** | Global | 1.5B+ | eng | facebook/mms-tts-eng |
+
+---
+
+## 🎯 Language Details
+
+### Kenyan Languages (5)
+
+#### 1. **Swahili** 🇰🇪 🇹🇿 🇺🇬
+- **Native Speakers**: ~100 million+
+- **Regions**: Kenya, Tanzania, Uganda, Democratic Republic of Congo
+- **Script**: Latin alphabet
+- **Status**: Official language in Kenya and Tanzania
+- **Use Cases**: Business, education, media, government
+- **Model**: Meta MMS TTS (facebook/mms-tts-swh)
+
+#### 2. **Kikuyu** 🇰🇪
+- **Native Speakers**: ~7 million
+- **Regions**: Central Kenya (Mount Kenya region)
+- **Script**: Latin alphabet
+- **Status**: Widely spoken in Kiambu, Muranga, Nyeri counties
+- **Use Cases**: Local media, education, community engagement
+- **Model**: BrianMwangi/African-Kikuyu-TTS (fine-tuned MMS)
+
+#### 3. **Luo** 🇰🇪
+- **Native Speakers**: ~4 million
+- **Regions**: Western Kenya (Kisumu, Siaya, Homa Bay, Migori)
+- **Script**: Latin alphabet
+- **Status**: Widely spoken in Nyanza region
+- **Use Cases**: Local broadcasting, education, cultural preservation
+- **Model**: Meta MMS TTS (facebook/mms-tts-luo)
+
+#### 4. **Luhya** 🇰🇪
+- **Native Speakers**: ~5 million
+- **Regions**: Western Kenya (Kakamega, Bungoma, Vihiga)
+- **Script**: Latin alphabet
+- **Status**: Widely spoken in Western region
+- **Use Cases**: Local media, education, community services
+- **Model**: Meta MMS TTS (facebook/mms-tts-luy)
+
+#### 5. **Kamba** 🇰🇪
+- **Native Speakers**: ~3 million
+- **Regions**: Eastern Kenya (Makueni, Kajiado, Taita-Taveta)
+- **Script**: Latin alphabet
+- **Status**: Widely spoken in Eastern region
+- **Use Cases**: Local broadcasting, education, tourism
+- **Model**: Meta MMS TTS (facebook/mms-tts-kam)
+
+---
+
+### Nigerian Languages (3)
+
+#### 6. **Yoruba** 🇳🇬
+- **Native Speakers**: ~45 million
+- **Regions**: Nigeria (Southwest), Benin, Togo
+- **Script**: Latin alphabet
+- **Status**: Major West African language
+- **Use Cases**: Media, entertainment, education, business
+- **Model**: Meta MMS TTS (facebook/mms-tts-yor)
+
+#### 7. **Igbo** 🇳🇬
+- **Native Speakers**: ~27 million
+- **Regions**: Nigeria (Southeast)
+- **Script**: Latin alphabet
+- **Status**: Major West African language
+- **Use Cases**: Media, education, business, cultural content
+- **Model**: Meta MMS TTS (facebook/mms-tts-ibo)
+
+#### 8. **Hausa** 🇳🇬 🇳🇪
+- **Native Speakers**: ~90 million (including second language speakers)
+- **Regions**: Nigeria, Niger, and across West Africa
+- **Script**: Latin alphabet (also Arabic script)
+- **Status**: Lingua franca of West Africa
+- **Use Cases**: Trade, media, education, cross-border communication
+- **Model**: Meta MMS TTS (facebook/mms-tts-hau)
+
+---
+
+### Ethiopian Language (1)
+
+#### 9. **Amharic** 🇪🇹
+- **Native Speakers**: ~32 million
+- **Regions**: Ethiopia (official language)
+- **Script**: Ge'ez script
+- **Status**: Official language of Ethiopia
+- **Use Cases**: Government, education, media, business
+- **Model**: Meta MMS TTS (facebook/mms-tts-amh)
+
+---
+
+### Global Language (1)
+
+#### 10. **English** 🌍
+- **Native Speakers**: ~370 million
+- **Global Speakers**: 1.5+ billion
+- **Regions**: Worldwide
+- **Script**: Latin alphabet
+- **Status**: International lingua franca
+- **Use Cases**: Business, education, technology, global communication
+- **Model**: Meta MMS TTS (facebook/mms-tts-eng)
+
+---
+
+## 📊 Statistics
+
+### Total Coverage
+- **Total Languages**: 10
+- **Total Native Speakers**: 300+ million
+- **Total Regions**: 4 (East Africa, West Africa, Horn of Africa, Global)
+- **Countries**: Kenya, Nigeria, Niger, Tanzania, Uganda, Ethiopia, Benin, Togo, DRC
+
+### Regional Breakdown
+- **East Africa**: 5 languages (Swahili, Kikuyu, Luo, Luhya, Kamba)
+- **West Africa**: 3 languages (Yoruba, Igbo, Hausa)
+- **Horn of Africa**: 1 language (Amharic)
+- **Global**: 1 language (English)
+
+---
+
+## 🚀 Use Cases by Language
+
+### Education
+- **Swahili**: Curriculum content, educational videos
+- **Kikuyu, Luo, Luhya, Kamba**: Local language instruction
+- **Yoruba, Igbo, Hausa**: Mother tongue education
+- **Amharic**: Ethiopian education system
+- **English**: International education
+
+### Media & Entertainment
+- **Swahili**: News, podcasts, music
+- **Kikuyu, Luo, Luhya, Kamba**: Local radio, community content
+- **Yoruba, Igbo, Hausa**: Entertainment, music, drama
+- **Amharic**: Ethiopian media
+- **English**: Global media
+
+### Business & Commerce
+- **Swahili**: East African business communication
+- **Hausa**: West African trade and commerce
+- **English**: International business
+- **All others**: Local business and commerce
+
+### Accessibility
+- **All languages**: Making technology accessible to speakers
+- **Visually impaired users**: Audio content
+- **Language learners**: Pronunciation and learning
+
+### Cultural Preservation
+- **All languages**: Documenting and preserving languages
+- **Digital archives**: Recording language content
+- **Community engagement**: Supporting language communities
+
+---
+
+## 🔧 Technical Details
+
+### Model Architecture
+All models use **Meta's Massively Multilingual Speech (MMS)** architecture, except Kikuyu which uses a fine-tuned version.
+
+### Audio Output
+- **Sample Rate**: 16 kHz
+- **Bit Depth**: 16-bit
+- **Format**: WAV
+- **Quality**: Natural-sounding speech synthesis
+
+### Performance
+- **Inference Time**: 2-5 seconds per 100 words (CPU)
+- **GPU Acceleration**: <1 second (with CUDA)
+- **Max Text Length**: 1000 characters per request
+
+---
+
+## 🌟 Future Expansions
+
+Planned languages for future versions:
+- **Chichewa** (Malawi, Zambia)
+- **Xhosa** (South Africa)
+- **Zulu** (South Africa)
+- **Twi/Akan** (Ghana)
+- **Wolof** (Senegal)
+- **Somali** (Somalia)
+- **Tigrinya** (Eritrea, Ethiopia)
+- **Oromo** (Ethiopia)
+- **Afar** (Ethiopia, Eritrea, Djibouti)
+- And more...
+
+---
+
+## 📚 Resources
+
+### Language Information
+- [Ethnologue](https://www.ethnologue.com/) - Comprehensive language database
+- [Wikipedia Language Lists](https://en.wikipedia.org/wiki/Languages_of_Africa) - African languages overview
+- [Glottolog](https://glottolog.org/) - Language classification
+
+### Models & Datasets
+- [Meta MMS](https://huggingface.co/facebook/mms-tts-swh) - Multilingual speech models
+- [Hugging Face Hub](https://huggingface.co/models?language=african-languages) - African language models
+- [Masakhane](https://www.masakhane.io/) - African NLP community
+
+### Communities
+- [CLEAR Global](https://www.clear-global.org/) - African language AI research
+- [Sunbird AI](https://sunbird.ai/) - African language technology
+- [Lelapa AI](https://www.lelapa.ai/) - African language models
+
+---
+
+## 🤝 Contributing
+
+Want to add more languages or improve existing ones? We welcome contributions!
+
+- Add new language models
+- Improve audio quality
+- Contribute datasets
+- Report issues
+- Suggest improvements
+
+---
+
+**JamboGPT - Making AI accessible in African languages! 🌍**
+
+*Last Updated: May 11, 2026*