arXiv 📖 [ preprint ]

⚒️ Model Description

Ethio-ASR is a suite of Automatic Speech Recognition (ASR) models for Ethiopian languages. This repo contains a monolingual Oromo ASR model based on wav2vec2‑bert-2.0, fine-tuned on the Oromo subset of the WAXAL Speech Dataset.

Developed by: Ethio-ASR Team
Task: Speech Recognition (ASR)
Language: Oromo
License: CC-BY-4.0
Finetuned from: facebook/w2v-bert-2.0

📈 Evaluation on WAXAL Test Set (Oromo)

📌 ASR model in this HF repo

Model	# Params	Oromo WER (↓)
Ethio-ASR (afrihubert)	94M	27.57
Ethio-ASR (mms-300)	300M	26.41
Ethio-ASR (mms-1b)	1B	23.69
Ethio-ASR (w2v-bert-2.0)	600M	24.44
Monolingual SFT (w2v-bert-2.0) 📌	600M	24.29

🎧 Direct Use

from transformers import AutoModelForCTC, AutoProcessor
import torchaudio, torch

processor = AutoProcessor.from_pretrained("badrex/Ethio-ASR-oromo")
model = AutoModelForCTC.from_pretrained("badrex/Ethio-ASR-oromo")

audio, sr = torchaudio.load("audio.wav")
inputs = processor(audio.squeeze(), sampling_rate=sr, return_tensors="pt")

with torch.no_grad():
    logits = model(**inputs).logits

pred_ids = torch.argmax(logits, dim=-1)
transcription = processor.batch_decode(pred_ids)[0]

print(transcription)

🔧 Downstream Use

Voice assistants
Accessibility tools
Research baselines

🚫 Out‑of‑Scope Use

Languages other than Oromo
High‑stakes deployments without human review
Noisy audio without speech enhancement

⚠️ Risks & Limitations

Performance might vary across dialects, genders, ages, and recording quality.

📌 Citation

@misc{ethio_asr_2026,
  author = {
    Abdullah, Badr M. and
    Azime, Israel Abebe and
    Tonja, Atnafu Lambebo and
    Alabi, Jesujoba O. and
    Alemu, Abel Mulat and
    Hagos, Eyob G. and
    Balcha, Bontu Fufa and
    Nerea, Mulubrhan A. and
    Yadeta, Debela Desalegn and
    Marilign, Dagnachew Mekonnen and
    Fentahun, Amanuel Temesgen and
    Kebede, Tadesse and
    Gebru, Israel D. and
    Woldeyohannis, Michael Melese and
    Sewunetie, Walelign Tewabe and
    Möbius, Bernd and
    Klakow, Dietrich
  },
  title = {Ethio-ASR: Joint Multilingual Speech Recognition and Language Identification for Ethiopian Languages},
  year = {2026},
  howpublished = {\url{https://huggingface.co/badrex/Ethio-ASR-multilingual-600M}}
}