---
library_name: nemo
license: cc-by-4.0
language:
- ar
pipeline_tag: automatic-speech-recognition
tags:
- automatic-speech-recognition
- asr
- arabic
- arabic-asr
- dialectal-arabic
- gulf-arabic
- fastconformer
- ctc
- efficient
---

<div align="center">

<img src="https://cdn-avatars.huggingface.co/v1/production/uploads/6a43eaa1e610ba5400625802/fct9hOhOa2VVlgBjj4uA8.png" width="180"/>

# lemura-arabic-asr

**A compact, dialect-aware Arabic speech-recognition model — leaderboard-tier accuracy at ~18× fewer parameters.**

![Task](https://img.shields.io/badge/task-ASR-blue)
![Params](https://img.shields.io/badge/params-~115M-f59e0b)
![Architecture](https://img.shields.io/badge/arch-FastConformer--CTC-6f42c1)
![Dialects](https://img.shields.io/badge/dialects-MSA%20%2B%204%20groups-brightgreen)
![Runtime](https://img.shields.io/badge/runtime-CPU%20%C2%B7%20GPU%20%C2%B7%20real--time-blue)

[🧭 Overview](#-overview) · [📋 Model Details](#-model-details) · [📊 Benchmarks](#-benchmarks) · [⚡ Efficiency](#-efficiency) · [💻 Usage](#-usage) · [🎙️ Live Demo](https://huggingface.co/spaces/lemuralabs/lemura-arabic-asr-demo)

</div>

---

## 🧭 Overview

**lemura-arabic-asr** is a compact multi-dialect Arabic ASR model built for accuracy *and* efficiency. It is a **FastConformer-CTC** acoustic model (\~115M parameters), adapted in-house from the NVIDIA FastConformer foundation and fine-tuned on **\~2,900 hours** of Arabic spanning **MSA** and the **Gulf, Egyptian, Levantine, and Maghrebi** dialect groups.

**Highlights**

- 🪶 **Small & fast** — ~115M parameters; runs comfortably on **CPU** and in **real time**, no GPU required.
- 🗣️ **Dialect-aware** — trained across five Arabic dialect groups, not MSA-only.
- 🎧 **Robust on real audio** — strongest on broadcast, conversational, and Gulf/MSA speech.
- 🔓 **Open & simple** — a single `.nemo` file, loadable in a few lines with NVIDIA NeMo.

## 📋 Model Details

| | |
|---|---|
| **Model** | lemura-arabic-asr — compact multi-dialect Arabic ASR |
| **Task** | Automatic speech recognition (audio → text) |
| **Architecture** | FastConformer encoder + CTC decoder |
| **Parameters** | ~115M |
| **Foundation** | Adapted from NVIDIA FastConformer; ~2,900 h Arabic fine-tuning |
| **Audio input** | 16 kHz mono (auto-resampled) |
| **Languages** | Arabic — MSA + Gulf / Egyptian / Levantine / Maghrebi |
| **Runtime** | NVIDIA NeMo — CPU · GPU · real-time |
| **License** | CC-BY-4.0 |

## 📊 Benchmarks

Evaluated on all six **Open Universal Arabic ASR Leaderboard** test sets using the [official leaderboard code](https://github.com/Natural-Language-Processing-Elm/open_universal_arabic_asr_leaderboard) (same normalizer, same WER metric).

### Per-set WER (%)

| SADA | Common Voice 18 | MASC-clean | MASC-noisy | MGB-2 | Casablanca | **Average** |
|---:|---:|---:|---:|---:|---:|---:|
| 37.28 | 9.74 | 7.27 | 23.65 | 14.33 | 58.24 | **25.08** |

### In context (Average WER %, lower is better)

| Model | Params | Avg WER |
|---|---:|---:|
| cohere-transcribe-arabic-07-2026 | ~2.0B | 25.87 |
| **lemura-arabic-asr** | **~0.12B** | **25.08\*** |
| omniASR_LLM_7B | 7B | 28.32 |
| Qwen3-Omni-30B-A3B | 30B | 30.71 |
| nvidia-conformer-ctc-large-arabic (lm) | 0.6B | 32.91 |
| Qwen3-ASR-1.7B | 1.7B | 33.36 |

## ⚡ Efficiency

The top leaderboard systems are large generative audio-LLMs (2–30B parameters) that need GPUs. lemura-arabic-asr reaches a comparable accuracy tier with a **~115M-parameter** CTC model:

| | lemura-arabic-asr | Typical top systems |
|---|---|---|
| Parameters | **~115M** | 2B – 30B |
| Hardware | **CPU or GPU** | GPU |
| Latency | **Real-time** | Seconds / clip |
| Footprint | **~0.4 GB** | 4 – 60 GB |

That makes it practical for **on-device, low-cost, and high-throughput** Arabic transcription where the big models are impractical.

## 💻 Usage

```python
import nemo.collections.asr as nemo_asr

model = nemo_asr.models.ASRModel.restore_from("asr_final.nemo")
print(model.transcribe(["audio.wav"]))   # 16 kHz mono
```

Try it live — no install: **[🎙️ lemura-arabic-asr demo](https://huggingface.co/spaces/lemuralabs/lemura-arabic-asr-demo)**

## 🙏 Credits

- Acoustic foundation: **NVIDIA FastConformer**
- Evaluation: the **[Open Universal Arabic ASR Leaderboard](https://github.com/Natural-Language-Processing-Elm/open_universal_arabic_asr_leaderboard)** official code