MODELHugging Face

5/5

AfriBERTa – Pan-African Language Model (Cross River coverage)

Andoni(ann)LM/ClassificationXLM-R (adapted)XLMRobertaForMaskedLM

Model Info

Language

Andoni (ann)

Architecture

XLMRobertaForMaskedLM

Institution

David Ifeoluwa Adelani et al. (Castorini group)

Last Updated

22 May 2026

Intended Use Cases

Cross-lingual transfer for African NLP; Obolo not in training set but closest covered language is Efik/Ibibio

License & Access

SPDX identifierApache-2.0

Open — attribution required; commercial use allowed.

Provenance

Source URL

https://huggingface.co/castorini/afriberta_large

Fetch Timestamp

22 May 2026

Submitter

David Ifeoluwa Adelani et al. (Castorini group)

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: ann
Model Name: AfriBERTa – Pan-African Language Model (Cross River coverage)
Where is it hosted: HuggingFace
Link: https://huggingface.co/castorini/afriberta_large
Year: 2022
Creator/Author(s): David Ifeoluwa Adelani et al. (Castorini group)
Paper Reference: arXiv:2111.11772
NLP Task: LM/Classification
Architecture: XLMRobertaForMaskedLMderivedHugging Face config: architectures / model_type
Base Model: XLM-R (adapted)
Fine-tuned?: No
License: Apache-2.0
Open Access: Open
Has Model Card: Yes
SOTA Tasks: Cross-lingual transfer for African NLP; Obolo not in training set but closest covered language is Efik/Ibibio
Verified By: Not stated
Date Indexed: 2026-05-22
Comment: Not stated

Readiness (LRS) (3/7)

model id: afriberta-pan-african-language-model-cross-river-coverage-ann
Model Type: LLMderivedHugging Face card: pipeline_tag
Training Data Sources: Multilingual African text incl. 11 languages
Benchmark Used: Not stated
Benchmark Score: Not stated
Benchmark Date: Not stated
Status: Not stated

Readiness Score Breakdown

5/5

Data Coverage95%

Model Availability100%

Benchmarks100%

Documentation83%

Recency100%

Representativeness

Gender Balance

Regional Distribution

Dialect Coverage

Inclusivity

Relations Explorer link

Also Available In

This is the same multilingual corpus, sliced for other languages the platform indexes it under.

AfriBERTa-Large (Afrikaans covered indirectly via XLM-R base)

Afrikaans not in AfriBERTa training set; note for accuracy

13 languagesAfrikaans(afr)Trained from scratchLM / Encoder (RoBERTa)

Open12 May 2026

afriberta_large

fill-mask model · XLMRobertaForMaskedLM · castorini

13 languagesAmharic(amh)XLMRobertaForMaskedLMfill-mask

Open27 Oct 2026

afriberta_large

fill-mask model · XLMRobertaForMaskedLM · castorini

13 languagesHausa(hau)XLMRobertaForMaskedLMfill-mask

Open27 Oct 2026

afriberta_large

fill-mask model · XLMRobertaForMaskedLM · castorini

13 languagesIgbo(ibo)XLMRobertaForMaskedLMfill-mask

Open27 Oct 2026

afriberta_large

fill-mask model · XLMRobertaForMaskedLM · castorini

13 languagesKinyarwanda(kin)XLMRobertaForMaskedLMfill-mask

Open27 Oct 2026

afriberta_large

fill-mask model · XLMRobertaForMaskedLM · castorini

13 languagesOromo(orm)XLMRobertaForMaskedLMfill-mask

Open27 Oct 2026

afriberta_large

fill-mask model · XLMRobertaForMaskedLM · castorini

13 languagesNigerian Pidgin(pcm)XLMRobertaForMaskedLMfill-mask

Open27 Oct 2026

afriberta_large

fill-mask model · XLMRobertaForMaskedLM · castorini

13 languagesKirundi(run)XLMRobertaForMaskedLMfill-mask

Open27 Oct 2026

afriberta_large

fill-mask model · XLMRobertaForMaskedLM · castorini

13 languagesSomali(som)XLMRobertaForMaskedLMfill-mask

Open27 Oct 2026

afriberta_large

fill-mask model · XLMRobertaForMaskedLM · castorini

13 languagesSwahili(swa)XLMRobertaForMaskedLMfill-mask

Open27 Oct 2026

afriberta_large

fill-mask model · XLMRobertaForMaskedLM · castorini

13 languagesTigrinya(tir)XLMRobertaForMaskedLMfill-mask

Open27 Oct 2026

afriberta_large

fill-mask model · XLMRobertaForMaskedLM · castorini

13 languagesYoruba(yor)XLMRobertaForMaskedLMfill-mask

Open27 Oct 2026

Related Models

xeus

automatic-speech-recognition model · espnet · espnet

1,424 languagesAndoni(ann)espnetautomatic-speech-recognition

Restricted27 Oct 2026

hubert-base-mmsulab

HubertModel · coml

1,416 languagesAndoni(ann)HubertModel

Restricted27 Oct 2026

spidr-mmsulab

coml

1,416 languagesAndoni(ann)

Restricted27 Oct 2026