Omnilingual ASR models trained/fine-tuned on Omnilingual ASR Corpus

Hejazi Arabic(acw)ASRSpeech Recognition / Encoder

View Source

Model Info

Language

Hejazi Arabic (acw)

Architecture

Speech Recognition / Encoder

Institution

Meta / Facebook AI

Last Updated

11 May 2026

Intended Use Cases

Multilingual ASR

License & Access

SPDX identifierVaries

Licensed under Varies. Review the source terms before use.

Provenance

Source URL

https://huggingface.co/datasets/facebook/omnilingual-asr-corpus#models-trained-or-fine-tuned-on-facebookomnilingual-asr-corpus

Fetch Timestamp

11 May 2026

Submitter

Meta / Facebook AI

Full Record

19 of 25 fields stated

Every column the registry tracks. Values marked derivedwere filled by a rule or read from the source's text rather than stated in its metadata; the rule or the quoted sentence is shown under the value.

Registry columns (16/18)

iso code: acw
Model Name: Omnilingual ASR models trained/fine-tuned on Omnilingual ASR Corpus
Where is it hosted: HuggingFace
Link: https://huggingface.co/datasets/facebook/omnilingual-asr-corpus#models-trained-or-fine-tuned-on-facebookomnilingual-asr-corpus
Year: 2025
Creator/Author(s): Meta / Facebook AI
Paper Reference: https://arxiv.org/abs/2511.09690derivedHugging Face card: arXiv tag
NLP Task: ASR
Architecture: Speech Recognition / Encoder
Base Model: Not stated
Fine-tuned?: Yes
License: Varies
Open Access: Open
Has Model Card: Yes
SOTA Tasks: Multilingual ASR
Verified By: Not stated
Date Indexed: 2026-05-11
Comment: Relevant because Hejazi Arabic acw_Arab appears in the Omnilingual ASR Corpus. Model availability depends on models linked from the corpus card; treat as corpus…

Readiness (LRS) (3/7)

model id: omnilingual-asr-models-trained-fine-tuned-on-omnilingual-asr-corpus-acw
Model Type: Not stated
Training Data Sources: Omnilingual ASR Corpus; includes acw_Arab subset for Hejazi Arabic
Benchmark Used: Not stated
Benchmark Score: Not stated
Benchmark Date: Not stated
Status: Activederivedupdated within 3 years