--- library_name: nemo license: cc-by-4.0 language: - ar - arz - apc - ary - afb pipeline_tag: automatic-speech-recognition metrics: - wer tags: - automatic-speech-recognition - speech-recognition - speech-to-text - stt - transcription - speech - audio - asr - arabic - arabic-asr - arabic-speech - dialectal-arabic - msa - modern-standard-arabic - gulf-arabic - egyptian-arabic - levantine-arabic - maghrebi-arabic - multi-dialect - nemo - nemo-toolkit - nvidia - fastconformer - fastconformer-ctc - conformer - ctc - efficient - lightweight - compact - on-device - edge - cpu-inference - real-time - low-latency - low-resource model-index: - name: lemura-arabic-asr-lite results: - task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: name: Open Universal Arabic ASR Leaderboard (average of 6 sets) type: open-universal-arabic-asr metrics: - type: wer value: 25.08 name: Average WER - task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: name: MASC (clean) type: masc-clean metrics: - type: wer value: 7.27 name: WER - task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: name: Common Voice 18 (Arabic) type: common-voice-18-ar metrics: - type: wer value: 9.74 name: WER - task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: name: MGB-2 type: mgb-2 metrics: - type: wer value: 14.33 name: WER - task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: name: MASC (noisy) type: masc-noisy metrics: - type: wer value: 23.65 name: WER - task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: name: SADA type: sada metrics: - type: wer value: 37.28 name: WER - task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: name: Casablanca type: casablanca metrics: - type: wer value: 58.24 name: WER ---
# lemura-arabic-asr-lite ![Format](https://img.shields.io/badge/Format-NeMo-0b7285?style=flat) ![Task](https://img.shields.io/badge/Task-Speech%20Recognition-5f3dc4?style=flat) ![Type](https://img.shields.io/badge/Type-ASR-862e9c?style=flat) ![License](https://img.shields.io/badge/License-cc--by--4.0-6c757d?style=flat) **A compact, dialect-aware Arabic speech-recognition model — leaderboard-tier accuracy at ~18× fewer parameters.** ![Task](https://img.shields.io/badge/task-ASR-blue?style=flat) ![Params](https://img.shields.io/badge/params-~115M-f59e0b?style=flat) ![Architecture](https://img.shields.io/badge/arch-FastConformer--CTC-6f42c1?style=flat) ![Dialects](https://img.shields.io/badge/dialects-MSA%20%2B%204%20groups-brightgreen?style=flat) ![Runtime](https://img.shields.io/badge/runtime-CPU%20%C2%B7%20GPU%20%C2%B7%20real--time-blue?style=flat) [ Overview](#-overview) · [ Model Details](#-model-details) · [ Benchmarks](#-benchmarks) · [ Efficiency](#-efficiency) · [ Usage](#-usage) · [ Live Demo](https://huggingface.co/spaces/lemuralabs/lemura-arabic-asr-demo)
--- ## 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