Model reference · open weights

wav2vec2-large-xlsr-53-arabic

wav2vec2-large-xlsr-53-arabic is an open-weight audio or speech model from elgeish, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Audio elgeish 1 variants 732k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What wav2vec2-large-xlsr-53-arabic is

Wav2Vec2-Large-XLSR-53-Arabic Fine-tuned facebook/wav2vec2-large-xlsr-53 on Arabic using the train splits of Common Voice and Arabic Speech Corpus. When using this model, make sure that your speech input is sampled at 16kHz. Usage The model can be used directly (without a language model) as follows: Here's the output: Evaluation The model can be evaluated as follows on the Arabic test data of Common Voice: Test Result: 26.55% Training For more details, see Fine-Tuning with Arabic Speech Corpus. This model represents Arabic in a format called Buckwalter transliteration. The Buckwalter format only includes ASCII characters, some of which are non-alpha (e.g., "" maps to "أ"). The lang-trans package is used to convert (transliterate) Arabic abjad. This script was used to first fine-tune facebook/wav2vec2-large-xlsr-53 on the train split of the Arabic Speech Corpus dataset; the test split was used for model selection; the resulting model at this point is saved as elgeish/wav2vec2-large-xlsr-53-levantine-arabic. Training was then resumed using the train split of the Common Voice dataset; the validation split was used for model selection; training was stopped to meet the deadline of Fine-Tune-XLSR Week: this model is the checkpoint at 100k steps and a validation WER of 23.39%. It's worth noting that validation WER is trending down, indicating the potential of further training (resuming the decaying learning rate at 7e-6). Future Work One area to explore is using attentionmask in model input, which is recommended here. Also, exploring data augmentation using datasets used to train models listed here.

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makerelgeish
TypeAudio & music
Variants1
Runs withtransformers
Released2022-03-02
Popularity732k downloads / month
Likes18
LicenceOpen weights

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
wav2vec2-large-xlsr-53-arabicBF16Weights ↗

Benchmarks

Reported results

As published on the model card — the maker's own numbers, not measured by AxForge.

TaskDatasetMetricScore
Automatic Speech RecognitionCommon Voice 6.1 (Arabic)Test WER26.55
Automatic Speech RecognitionCommon Voice 6.1 (Arabic)Validation WER23.39

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys elgeish-wav2vec2-large-xlsr-53-arabic for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (elgeish-wav2vec2-large-xlsr-53-arabic below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="elgeish-wav2vec2-large-xlsr-53-arabic" -F file=@audio.mp3

Details

Languages, data & research

Languages

ar

Trained / evaluated on

arabic_speech_corpus mozilla-foundation/common_voice_6_1

Tags

transformers pytorch jax wav2vec2 automatic-speech-recognition audio speech xlsr-fine-tuning-week hf-asr-leaderboard ar dataset:arabic_speech_corpus dataset:mozilla-foundation/common_voice_6_1 model-index endpoints_compatible

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want wav2vec2-large-xlsr-53-arabic on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More audio & music

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms