UNICEF WCARO NLP Landscape

West and Central Africa Language Technology
Last updated: 2026-04-23
Work in progress. Some data may contain inaccuracies. Contribute on GitHub

Sango

sag / sg

🌍 General Information

sag
sg
sango
sang1328
Creole
Latin script
620,000
5500000 (10⁶+)
safe
Central African Republic, Chad, Democratic Republic of Congo
Sangho, Sanngo

🗺️ Language Use

Data from CLEAR Global's Language Use Data Platform.

🤖 NLP & Tech Resources

✓ AfroLID
✓ NLLB-200
✓ MADLAD-400 Docs: 2100 MAD-Docs
✓ MADLAD-400 Sentences: 117900 MAD-Sents
✓ Fineweb2: 💬
✓ CMU Wilderness
✓ MMS-ASR
✓ MMS-TTS
✓ MMS-LID
✓ Omnilingual ASR
✓ SimbaBench

Benchmarks

MT (Machine Translation)

FLORES+ 10-sample

FLORES-200

LLM (Large Language Models)

SIB-200 10-sample

ModelClassification Acc.Source
amazon/nova-pro-v1100.0reported
openai/gpt-4o100.0reported
openai/gpt-5100.0reported

MMLU Synthetic 10-sample

MGSM Synthetic 10-sample

ARC Synthetic 10-sample

TRANSLATION

Kreyòl-MT (bible-based)

ModelBLEU (sag→eng)BLEU (eng→sag)BLEU (sag→fra)BLEU (fra→sag)Source
jhu-clsp/kreyol-mt39377290reported

📝 Notes

Observations

  • National lingua franca of the Central African Republic
  • Sole widely-spoken local language for CAR coverage
  • Kreyol-MT models are not tagged with "Translation" task so it doesn't show up on Hugging Face queries

ASR Models (17)

ModelSizeDownloadsLikes
MahmoudAshraf/mms-300m-1130-forced-aligner 0.3B 4.0M 83
facebook/mms-1b-all 1.0B 2.0M 195
facebook/mms-1b-fl102 1.0B 8.7K 29
UBC-NLP/Simba-S 2B 2.2K 4
facebook/mms-1b-l1107 1.0B 280 12
espnet/xeus 60 146
UBC-NLP/Simba-W 2B 44 0
UBC-NLP/Simba-M 33 0
bc7ec356/heep-universal 0.8B 31 0
onnx-community/mms-300m-1130-forced-aligner-ONNX 25 0
johntsi/ZeroSwot-Medium_asr-cv_en-to-200 0.4B 17 0
johntsi/ZeroSwot-Large_asr-cv_en-to-200 0.4B 16 1
johntsi/ZeroSwot-Medium_asr-mustc_en-to-200 0.4B 14 0
johntsi/ZeroSwot-Large_asr-mustc_en-to-200 0.4B 12 0
UBC-NLP/Simba-H 5 0
romara-labs/mms-300m-1130-forced-aligner-ONNX 4 0
UBC-NLP/Simba-X 3 0

View on HuggingFace: sg: 16 | sag: 1

TTS Models (1)

ModelDownloadsLikes
Dapor/Dapson 0 4

View on HuggingFace: sg: 1

MT Models (31)

ModelSizeDownloadsLikes
facebook/nllb-200-distilled-600M 1.1M 880
google/madlad400-3b-mt 3B 329.0K 192
facebook/nllb-200-distilled-1.3B 147.0K 181
facebook/nllb-200-3.3B 81.6K 443
Helsinki-NLP/opus-mt-mul-en 61.6K 89
facebook/nllb-200-1.3B 31.4K 71
Xenova/nllb-200-distilled-600M 4.4K 50
Helsinki-NLP/opus-mt-en-mul 3.3K 28
JustFrederik/nllb-200-distilled-600M-ct2-int8 925 1
facebook/nllb-moe-54b 557 123
JustFrederik/nllb-200-1.3B-ct2-int8 200 0
JustFrederik/nllb-200-distilled-1.3B-ct2-int8 116 2
Helsinki-NLP/opus-mt-fi-sg 47 0
Helsinki-NLP/opus-mt-en-nic 42 0
Helsinki-NLP/opus-mt-fr-sg 42 0
Helsinki-NLP/opus-mt-sg-sv 42 0
Helsinki-NLP/opus-mt-nic-en 41 0
Helsinki-NLP/opus-mt-es-sg 39 0
vonjack/opus-mt-mul-en-big 0.3B 39 4
Helsinki-NLP/opus-mt-sg-en 38 0

View on HuggingFace: sg: 30 | sag: 1

LLM Models (12)

ModelSizeDownloadsLikes
google/madlad400-8b-lm 9B 183 11
jbochi/madlad400-8b-lm 9B 14 8
Kolyadual/Newton-bot-3-text-mini-8B 8B 7 1
goldfish-models/sag_latn_5mb 7 0
AAU-NLP/CreoleVal-CreoleM2M 0.6B 6 0
goldfish-models/sag_latn_10mb 4 0
goldfish-models/sag_latn_full 2 0
misterlakaz/Ceramic-Base-856b 0 6
misterlakaz/Midas-1922b 0 8
GlemVNT/VNT-3.5F-16K 0 0
wikilangs/sg 0 0
LumieraLM/Lumiera_v2 0 0

View on HuggingFace: sg: 8 | sag: 4

Datasets

ASR Datasets (8)

DatasetRowsDownloadsLikes
sarulab-speech/yodas2_sidon 1.5M 6.0K 60
suryatmodulus/yodas2_sidon 1.1K 0
UBC-NLP/SimbaBench_dataset 748.0K 975 0
WueNLP/sib-fleurs 94.4K 260 11
YuRiVeRTi/V1Q 186.0K 201 3
french-datasets/espnet_yodas2 16 0
dijihax/Dataset 8 2
french-datasets/espnet_yodas 5 0

View on HuggingFace: sg: 5 | sag: 3

TTS Datasets (6)

DatasetRowsDownloadsLikes
sarulab-speech/yodas2_sidon 1.5M 6.0K 60
suryatmodulus/yodas2_sidon 1.1K 0
UBC-NLP/SimbaBench_dataset 748.0K 975 0
WueNLP/sib-fleurs 94.4K 260 11
YuRiVeRTi/V1Q 186.0K 201 3
dijihax/Dataset 8 2

View on HuggingFace: sg: 5 | sag: 1

Translation Datasets (29)

DatasetRowsDownloadsLikes
facebook/flores 43.4K 97
openlanguagedata/flores_plus 893.0K 15.8K 124
gtak1/panlex-meanings 64.1M 6.3K 0
google/smol 798.0K 2.8K 94
Muennighoff/flores200 1.6K 20
jhu-clsp/kreyol-mt 1.9M 1.2K 9
Helsinki-NLP/tatoeba 866 56
mteb/FloresBitextMining 2.0K 303 1
visheratin/laion-coco-nllb 894.0K 255 44
cointegrated/panlex-meanings 157.0M 255 13
YuRiVeRTi/V1Q 186.0K 201 3
ymoslem/Tatoeba-Translations 8.6M 192 5
slone/nllb-200-10M-sample 10.0M 168 13
community-datasets/udhr 123 2
Helsinki-NLP/qed_amara 114 5
mteb/flores 2.0K 96 0
MEYNG/sango-vocabulary 1.2K 67 0
cis-lmu/GlotStoryBook 80.1K 67 7
FrancophonIA/gatitos 61 4
vpermilp/nllb-200-distilled-600M-rust 51 1

View on HuggingFace: sg: 17 | sag: 12