AI & ML interests
None defined yet.
Recent Activity
แตแแ โ Ethiopian Languages AI ๐ช๐น
แแขแตแฎแตแซ 80+ แแแแแฝ แญแแต แแแญ แจแตแแฝ AI
Open-source speech AI for Ethiopia's 80+ languages
๐ค Amharic TTS Model โข ๐๏ธ Live Demo โข ๐ Voices For All
๐ฏ Mission / แฐแแแฎ
แตแแ (Demtse โ "my voice") builds free, open-source speech AI so 120M+ Ethiopians can access technology in their mother tongue.
Ethiopia has 80+ living languages. Big Tech supports almost none of them. We're changing that โ one language at a time, starting with the highest-quality open Amharic TTS ever built.
๐ฃ๏ธ Models
OmniVoice Amharic โ TTS + Voice Cloning
| What it does | Converts Amharic text to natural speech; clones any voice from 10s audio |
| Architecture | Non-autoregressive discrete diffusion (612.6M params) |
| Training data | 331 hours across 4 datasets |
| Best loss | 3.9518 |
| License | Apache 2.0 โ completely free |
| Try it | โถ๏ธ Live Demo |
| Download | ๐ฆ Model |
# Quick start โ runs on free Colab T4
!pip install -q omnivoice soundfile
from omnivoice import OmniVoice, OmniVoiceGenerationConfig
import torch
model = OmniVoice.from_pretrained("ethiopian-Demtse/omnivoice-amharic", device_map="cuda:0", dtype=torch.float16)
audio = model.generate(text="แฐแแแฃ แฅแแณแ แฐแ
แ แแฃแฝแ!", language="Amharic",
generation_config=OmniVoiceGenerationConfig(num_step=32, guidance_scale=2.0))
๐ช๐น Roadmap โ Ethiopian Languages
| แแแ / Language | แฐแแแช / Speakers | แแแณ / Status |
|---|---|---|
| แ แแญแ Amharic | 60M+ | โ TTS + Voice Cloning |
| แฆแฎแแ Afaan Oromoo | 40M+ | ๐ Next |
| แตแแญแ Tigrinya | 10M+ | ๐ Planned |
| แถแแแ Somali | 7M+ | ๐ Planned |
| แฒแณแแ Sidamo | 4M+ | ๐ Future |
| แแแญแตแ Wolaytta | 3M+ | ๐ Future |
| แแซแแ Gurage | 2M+ | ๐ Future |
| แแฒแญแ Hadiyya | 2M+ | ๐ Future |
| แ แแญแ Afar | 2M+ | ๐ Future |
| แแแ Gamo | 1.5M+ | ๐ Future |
Goal: TTS + voice cloning for every Ethiopian language with 50h+ available audio.
๐ Training Data
| Dataset | Hours | Language |
|---|---|---|
| google/WaxalNLP | ~200h | Amharic |
| gheero-Leyu/leyu-amharic-addis-ababa-dialect | ~50h | Amharic (Addis) |
| surafelabebe/amharic_clear_audio_tts | ~40h | Amharic |
| chappM/amharic-bdu-asr | ~41h | Amharic |
| Total | ~331h |
We actively collect data for Oromo, Tigrinya, and other Ethiopian languages. If you have audio recordings in any Ethiopian language, please reach out.
๐ ๏ธ What We Build
| Project | Description | Status |
|---|---|---|
| Text-to-Speech (TTS) | แฝแแ โ แแแแญ | โ Amharic done |
| Voice Cloning | 10 แฐแจแแต แแแ โ แแแแแ แตแแฝ | โ Amharic done |
| Speech Recognition (ASR) | แแแแญ โ แฝแแ | ๐ Planned |
| Language Models (NLP) | แจแแแ แแดแแฝ | ๐ Planned |
| Machine Translation | แตแญแแ แ แขแตแฎแตแซ แแแแแฝ | ๐ Planned |
๐ค How to Contribute
We welcome contributions from anyone:
| Way to help | Description |
|---|---|
| ๐๏ธ Donate audio | Record or share speech in any Ethiopian language (any dialect, any speaker) |
| ๐ป Code | Open Issues, submit PRs, improve training pipelines |
| ๐ Data | Text transcriptions, translations, text-audio pairs |
| ๐ซ Institutions | Universities and organizations: partner with us for data collection |
| ๐งช Evaluate | Native speakers: test our models and give feedback on naturalness |
| ๐ฐ Fund | Support compute costs and data collection |
๐ Part of Voices For All
แตแแ is the Ethiopian chapter of Voices For All (african-low-resource) โ a pan-African initiative building speech AI for languages left behind by Big Tech.
| Initiative | Focus |
|---|---|
| african-low-resource | Pan-African: Amharic, Wolof, Hausa, Swahili, Somali |
| ethiopian-Demtse | Ethiopia-specific: all 80+ Ethiopian languages |
๐ฌ Contact
- Organization: ethiopian-Demtse
- Lead: demeleww
- Email: sowwen0@gmail.com
- Parent: Voices For All / african-low-resource
๐ Citation
@software{ethiopian_demtse_2026,
author = {demeleww and ethiopian-Demtse},
title = {แตแแ: Open Speech AI for Ethiopian Languages},
year = {2026},
url = {https://huggingface.co/ethiopian-Demtse},
license = {Apache-2.0}
}
โค๏ธ แ120 แแแฎแ+ แขแตแฎแตแซแแซแ โ แ แซแณแธแ แแแ แจ AI แตแแฝ แญแแฃแธแแแข
For 120M+ Ethiopians who deserve a voice in AI.