Kanuri - UNICEF WCARO NLP

🌍 General Information

ISO 639-3kau

ISO 639-1kr

French Namekanouri

Glottocodekanu1279

Language FamilyNilo-Saharan

Writing SystemLatin Arabic ( Ajami ) [ 2 ]

L1 Speakers10.6 million

L2 Speakers—

Population9600000 (10⁶+)

Endangerment—

CountriesCameroon, Chad, Niger, Nigeria

Also Known AsAga, Borno, Bornouan, Bornouans, Bornu, Central Kanuri, Kanouri, Kanoury, Kanuri, Yerwa

WikipediaKanuri on Wikipedia

🗺️ Language Use

Data from CLEAR Global's Language Use Data Platform.

👥 Actors (1)

CLEAR Global (Ngo)

CLEAR Global's mission is to help people get information and be heard, whatever language they speak. Evolved from Translators without Borders (TWB), w...

🤖 NLP & Tech Resources

Lanfrica

OLAC

Benchmarks

ASR (Speech-to-Text)

TWB Voice 1.0

Model	WER	CER	Source
whisper-small-clearglobal-kanuri-asr-1.0.0	10.16	3.72	reported
w2v-bert-2.0-clearglobal-kanuri-asr-1.0.0	11.31	3.05	reported

TTS (Text-to-Speech)

TWB Voice 1.0

Model	Pronunciation accuracy	Naturalness	Source
TWB-Voice-Kanuri-TTS-1.0	2.8/5	2.76/5	reported

LLM (Large Language Models)

FLORES-200

Model	Log-perplexity	Source
goldfish-models/knc_arab_full	181.38	reported
goldfish-models/knc_latn_full	170.17	reported

📝 Notes

Observations

Major language in the Lake Chad Basin (Nigeria, Niger, Chad, Cameroon)

ASR Models (23)

Model	Size	Downloads	Likes
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
facebook/mms-1b-l1107	1.0B	280	12
eesungkim/stt_kr_conformer_transducer_large	—	56	10
bc7ec356/heep-universal	0.8B	31	0
onnx-community/mms-300m-1130-forced-aligner-ONNX	—	25	0
CLEAR-Global/whisper-small-clearglobal-kanuri-asr-1.0.0	0.2B	23	1
ypluit/stt_kr_citrinet1024_PublicCallCenter_1000H_0.22	—	11	0
CLEAR-Global/w2v-bert-2.0-clearglobal-kanuri-asr-1.0.0	0.6B	9	0
hyyoka/wav2vec2-xlsr-korean-senior	—	8	0
espnet/Yushi_Ueda_ksponspeech_asr_train_asr_conformer8_n_fft512_hop_length256-truncated-eb42e5	—	7	1
ypluit/stt_kr_citrinet1024_PublicCallCenter_1000H_0.26	—	6	0
Jungwonchang/whisper_finetune_ksponspeech_partial_40epoch	—	5	0
Jungwonchang/whisper_finetune_ksponspeech_2000steps	—	4	0
romara-labs/mms-300m-1130-forced-aligner-ONNX	—	4	0
Jungwonchang/whisper_finetune_ksponspeech_partial	—	3	0
doongsae/whisper_finetuning	72.6M	3	0
byungkyu/sc_onnx	—	3	0
ypluit/stt_kr_citrinet1024_PublicCallCenter_1000H	—	2	0

View on HuggingFace: kr: 21 | kau: 2

TTS Models (3)

Model	Downloads	Likes
Dapor/Dapson	0	4
CLEAR-Global/TWB-Voice-Kanuri-TTS-1.0	0	0

View on HuggingFace: kr: 2 | kau: 1

MT Models (11)

Model	Size	Downloads	Likes
Helsinki-NLP/opus-mt-tc-bible-big-mul-mul	0.2B	442	10
Helsinki-NLP/opus-mt-tc-bible-big-deu_eng_fra_por_spa-mul	0.2B	88	1
Helsinki-NLP/opus-mt-tc-bible-big-mul-deu_eng_nld	0.2B	54	2
Helsinki-NLP/opus-mt-tc-bible-big-mul-deu_eng_fra_por_spa	0.2B	54	2
vonjack/opus-mt-mul-en-big	0.3B	39	4
slone/nllb-pruned-6L-512d-finetuned	—	2	6
masakhane/africomet-stl-1.1	—	0	5
masakhane/africomet-qe-stl-1.1	—	0	5
McGill-NLP/ssa-comet-mtl	—	0	3
McGill-NLP/ssa-comet-stl	—	0	1
McGill-NLP/ssa-comet-qe	—	0	1

View on HuggingFace: kr: 10 | kau: 1

LLM Models (19)

Model	Size	Downloads	Likes
UBC-NLP/toucan-base	0.6B	2.5K	5
UBC-NLP/toucan-1.2B	1B	1.9K	1
SEOKDONG/gpt-oss-safeguard-20b-kor-enterprise-gptq-4bit	21B	72	3
UBC-NLP/cheetah-1.2B	—	33	4
SEOKDONG/gpt-oss-safeguard-20b-kor-enterprise	21B	19	4
ZeppelinCorp/Charm_15	—	18	0
goldfish-models/knc_arab_5mb	—	12	0
goldfish-models/knc_latn_10mb	—	9	0
goldfish-models/knc_latn_5mb	—	9	0
Kolyadual/Newton-bot-3-text-mini-8B	8B	7	1
goldfish-models/knc_arab_100mb	—	4	0
goldfish-models/knc_arab_10mb	—	4	0
goldfish-models/knc_arab_full	—	3	0
goldfish-models/knc_latn_full	—	1	0
Xois/BuuClientPublicV1-MD-BOT	—	0	0
misterlakaz/Ceramic-Base-856b	—	0	6
misterlakaz/Midas-1922b	—	0	8
GlemVNT/VNT-3.5F-16K	—	0	0
LumieraLM/Lumiera_v2	—	0	0

View on HuggingFace: kau: 10 | kr: 9

Datasets

ASR Datasets (4)

Dataset	Rows	Downloads	Likes
YuRiVeRTi/V1Q	186.0K	201	3
CLEAR-Global/TWB-Voice-1.0	72.6K	39	0
lenoxaugo254/LenoxAI	—	10	1
dijihax/Dataset	—	8	2

View on HuggingFace: kr: 4

TTS Datasets (5)

Dataset	Rows	Downloads	Likes
YuRiVeRTi/V1Q	186.0K	201	3
CLEAR-Global/TWB-voice-TTS-Kanuri-1.0-sampleset	605	24	0
lenoxaugo254/LenoxAI	—	10	1
dijihax/Dataset	—	8	2

View on HuggingFace: kr: 4 | kau: 1

Translation Datasets (19)

Dataset	Rows	Downloads	Likes
CohereLabs/aya_collection	514.0M	12.6K	234
google/smol	798.0K	2.8K	94
Helsinki-NLP/opus_gnome	59.5K	635	1
ayymen/Weblate-Translations	11.7M	383	18
YuRiVeRTi/V1Q	186.0K	201	3
slone/nllb-200-10M-sample	10.0M	168	13
community-datasets/udhr	—	123	2
Helsinki-NLP/qed_amara	—	114	5
cis-lmu/GlotStoryBook	80.1K	67	7
qianstats/multimodal_low-resource_language_translation	—	63	0
FrancophonIA/gatitos	—	61	4
CLEAR-Global/Gamayun-kits	623.0K	54	2
janavivekariya/aya_collection	514.0M	43	0
kargaranamir/GlotStoryBook-backup	80.1K	21	0
Bretagne/PolyWrite_clean	155	11	0
lenoxaugo254/LenoxAI	—	10	1
dijihax/Dataset	—	8	2
FrancophonIA/DiLAF	—	5	0
Himanshu9636/Weblate-Translations	—	0	0

View on HuggingFace: kr: 13 | kau: 6