Downloads · 30 days
16
30% of all-time downloads
arabic_eou_model
raghad23/arabic_eou_model
arabic_eou_model is a machine learning model from raghad23. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
High-performance End-of-Utterance (EOU) detection model for real-time Arabic voice agents (LiveKit, etc.).
All-time downloads
54
Public
Parameters
135M
541 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors541 MB · 100%
At a glance
- Model type
- bert
- Access
- Public
- Created
- Dec 7, 2025
- Updated
- Dec 7, 2025
- SHA
- dd48de7d
Model card
From the Hugging Face model README
Arabic EOU Model – Saudi Dialect (raghad23/arabic-eou-model90)
High-performance End-of-Utterance (EOU) detection model for real-time Arabic voice agents (LiveKit, etc.).
Task
Binary classification:
LABEL_0→ Speaker continuesLABEL_1→ End of turn (EOU)
Performance (Test Set)
| Metric | Score |
|---|---|
| Accuracy | 90.68% |
| Weighted F1 | 93.40% |
| Precision (EOU) | 99.83% |
| Recall (EOU) | 87.75% |
| Eval Loss | 0.1964 |
Excellent real-time performance — detects end-of-utterance accurately in Saudi Arabic dialect.
Dataset
414k Saudi dialect samples
https://huggingface.co/datasets/raghad23/arabic_eou_sada_dataset
Base Model
aubmindlab/bert-base-arabertv02
Latency
< 80ms → perfect for LiveKit deployment
Usage
from transformers import pipeline
pipe = pipeline("text-classification", model="raghad23/arabic-eou-model90")
pipe("تمام الحمدلله وشلونك") # → LABEL_1 = EOU
- Type
- bert
- Languages
- ar
- Created
- Dec 7, 2025
- Updated
- Dec 7, 2025