MODELHugging Face

5/5

UBC-NLP/toucan-base

Afar(aar)MTmT5Encoder-Decoder

View Source

Model Info

Language

Afar (aar)

Architecture

Encoder-Decoder

Institution

Elmadany, Abdelrahim; Adebara, Ife; Abdul-Mageed, Muhammad (UBC-NLP)

Last Updated

11 May 2026

Intended Use Cases

MT for 150+ African language pairs including aar

License & Access

SPDX identifierUnknown (contact info required)

Restricted — review the source terms before use.

Provenance

Source URL

https://huggingface.co/UBC-NLP/toucan-base

Fetch Timestamp

11 May 2026

Submitter

Elmadany, Abdelrahim; Adebara, Ife; Abdul-Mageed, Muhammad (UBC-NLP)

Full Record

21 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 (17/18)

iso code: aar
Model Name: UBC-NLP/toucan-base
Where is it hosted: HuggingFace
Link: https://huggingface.co/UBC-NLP/toucan-base
Year: 2024
Creator/Author(s): Elmadany, Abdelrahim; Adebara, Ife; Abdul-Mageed, Muhammad (UBC-NLP)
Paper Reference: Elmadany et al. (2024) — Toucan: Many-to-Many Translation for 150 African Language Pairs. ACL 2024 Findings pp.13189-13206
NLP Task: MT
Architecture: Encoder-Decoder
Base Model: mT5
Fine-tuned?: No
License: Unknown (contact info required)
Open Access: Restricted
Has Model Card: Yes
SOTA Tasks: MT for 150+ African language pairs including aar
Verified By: Not stated
Date Indexed: 2026-05-11
Comment: 0.6B-parameter Afrocentric MT model. Supports Afar (aar) among 46 languages in 150+ pairs. Fine-tuned versions: toucan-1.2B and toucan-3.7B also available. Trai…

Readiness (LRS) (4/7)

model id: ubc-nlp-toucan-base-aar
Model Type: LLM
Training Data Sources: AfroLingu-MT; multilingual African corpora
Benchmark Used: Not stated
Benchmark Score: Not stated
Benchmark Date: Not stated
Status: Activederivedupdated within 3 years

Readiness Score Breakdown

5/5

Data Coverage100%

Model Availability100%

Benchmarks100%

Documentation80%

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.

model

toucan-base

text-generation model · T5ForConditionalGeneration · UBC-NLP

42 languagesAcholi(ach)T5ForConditionalGenerationtext-generation

HUHugging Face

Restricted27 Oct 2026

model

toucan-base

text-generation model · T5ForConditionalGeneration · UBC-NLP

42 languagesAfrikaans(afr)T5ForConditionalGenerationtext-generation

HUHugging Face

Restricted27 Oct 2026

model

toucan-base

text-generation model · T5ForConditionalGeneration · UBC-NLP

42 languagesAmharic(amh)T5ForConditionalGenerationtext-generation

HUHugging Face

Restricted27 Oct 2026

model

toucan-base

text-generation model · T5ForConditionalGeneration · UBC-NLP

42 languagesArabic(ara)T5ForConditionalGenerationtext-generation

HUHugging Face

Restricted27 Oct 2026

model

toucan-base

text-generation model · T5ForConditionalGeneration · UBC-NLP

42 languagesBambara(bam)T5ForConditionalGenerationtext-generation

HUHugging Face

Restricted27 Oct 2026

model

toucan-base

text-generation model · T5ForConditionalGeneration · UBC-NLP

42 languagesBasaa(bas)T5ForConditionalGenerationtext-generation

HUHugging Face

Restricted27 Oct 2026

model

toucan-base

text-generation model · T5ForConditionalGeneration · UBC-NLP

42 languagesBemba(bem)T5ForConditionalGenerationtext-generation

HUHugging Face

Restricted27 Oct 2026

model

toucan-base

text-generation model · T5ForConditionalGeneration · UBC-NLP

42 languagesBété, Gagnoa(btg)T5ForConditionalGenerationtext-generation

HUHugging Face

Restricted27 Oct 2026

model

toucan-base

text-generation model · T5ForConditionalGeneration · UBC-NLP

42 languagesEwe(ewe)T5ForConditionalGenerationtext-generation

HUHugging Face

Restricted27 Oct 2026

model

toucan-base

text-generation model · T5ForConditionalGeneration · UBC-NLP

42 languagesFang(fan)T5ForConditionalGenerationtext-generation

HUHugging Face

Restricted27 Oct 2026

model

toucan-base

text-generation model · T5ForConditionalGeneration · UBC-NLP

42 languagesFon(fon)T5ForConditionalGenerationtext-generation

HUHugging Face

Restricted27 Oct 2026

model

toucan-base

text-generation model · T5ForConditionalGeneration · UBC-NLP

42 languagesGeʽez(gez)T5ForConditionalGenerationtext-generation

HUHugging Face

Restricted27 Oct 2026

model

toucan-base

text-generation model · T5ForConditionalGeneration · UBC-NLP

42 languagesHausa(hau)T5ForConditionalGenerationtext-generation

HUHugging Face

Restricted27 Oct 2026

model