Wolof

wol / wo

🌍 General Information

ISO 639-3wol

ISO 639-1wo

French Namewolof

Glottocodenucl1347

Language FamilyNiger–Congo

Writing SystemLatin (Wolof alphabet) Arabic ( Wolofal ) Garay script

L1 Speakers8.2 million

L2 Speakers9.5 million

Population5500000 (10⁶+)

Endangermentsafe

CountriesGambia, Mauritania, Senegal

Also Known AsOuolof, Volof, Walaf, Waro-Waro, Yallof

WikipediaWolof on Wikipedia

🗺️ Language Use

Data from CLEAR Global's Language Use Data Platform.

👥 Actors (10)

Baamtu (Startup)

Digital transformation and AI consulting firm. Develops custom AI solutions for clients including government and financial institutions. Has TTS and c...

CONCREE (Startup)

Senegalese social enterprise originally focused on entrepreneurship support (virtual incubation, business training). Has expanded into AI/NLP for Wolo...

Digital Umuganda (Startup)

Rwandan AI and open data company building voice infrastructure for African languages. "Umuganda" is the Rwandan tradition of community service -- Digi...

Farmerline / Darli AI (Startup)

Ghanaian agritech company building technology solutions for smallholder farmers. Core platform Mergdata is a cloud-based farm management system used b...

GalsenAI (Research Community)

Community of young Senegalese AI/data science enthusiasts. Runs training, meetups, hackathons, and collaborative projects. Strong focus on Wolof NLP w...

Jokalante (Startup)

Senegalese social enterprise ("jokalante" = "facilitate dialogue" in Wolof) providing digital solutions for rural and underserved populations. Core pl...

LAfricaMobile (Startup)

Communication platform serving 300+ companies across Africa. Provides messaging (SMS, WhatsApp Business API, Voice), USSD, and AI-powered Text-to-Spee...

Masakhane (Research Community And Foundation)

Masakhane ("We build together" in isiZulu) is a grassroots NLP organization dedicated to strengthening natural language processing research in African...

UBC Deep Learning & NLP Lab (University)

Research lab at the University of British Columbia led by Muhammad Abdul-Mageed, focused on deep representation learning and natural language socio-pr...

YUX Design / Kitala AI (Startup)

African design and innovation firm with offices in Dakar, Accra, Lagos, Abuja, Brazzaville, Kigali, and Nairobi. ~50 staff including ML engineers and ...

🤖 NLP & Tech Resources

✓ AfroLID

✓ Google Translate: 2024

✓ NLLB-200

✓ M2M-100

✓ Mozilla Common Voice: ☑️

✓ MADLAD-400 Docs: 871 MAD-Docs

✓ MADLAD-400 Sentences: 25400 MAD-Sents

✓ Fineweb2: 💬

✓ FLEURS

✓ MAFAND

✓ AfriNLLB

✓ MMS-ASR

✓ MMS-LID

✓ Omnilingual ASR

✓ SimbaBench

✓ WaxalNLP

Benchmarks

ASR (Speech-to-Text)

FLEURS-102 test

Model	CER	Source
facebook/mms-1b-fl102	11.5	reported

FLEURS-102 dev

Model	CER	Source
facebook/mms-1b-fl102	11.2	reported

PazaBench (aggregated)

Model	CER	WER	Source
facebook/omniASR-LLM-7B	4.0	13.0	reported
facebook/omniASR-LLM-7B-ZS	6.0	22.0	reported
facebook/omniASR-LLM-1B	4.0	14.0	reported
facebook/omniASR-LLM-3B	4.0	13.0	reported
facebook/omniASR-LLM-300M	5.0	16.0	reported
facebook/omniASR-CTC-7B	5.0	20.0	reported
facebook/omniASR-CTC-1B	8.0	32.0	reported
facebook/omniASR-CTC-3B	7.0	25.0	reported
facebook/omniASR-CTC-300M	10.0	40.0	reported
microsoft/paza-mms-1b-all	25.0	75.0	reported
facebook/mms-1b-all	16.0	59.0	reported
facebook/mms-1b-fl102	17.0	61.0	reported
microsoft/paza-Phi-4-multimodal-instruct	46.0	97.0	reported
nvidia/parakeet-tdt-0.6b-v3	61.0	98.0	reported
facebook/wav2vec2-conformer-rel-pos-large-960h-ft	41.0	100.0	reported
facebook/data2vec-audio-large-960h	44.0	98.0	reported
facebook/wav2vec2-conformer-rope-large-960h-ft	43.0	99.0	reported
facebook/hubert-large-ls960-ft	41.0	96.0	reported
facebook/hubert-xlarge-ls960-ft	42.0	97.0	reported
microsoft/paza-whisper-large-v3-turbo	54.0	98.0	reported
facebook/wav2vec2-large-960h-lv60-self	44.0	97.0	reported
facebook/data2vec-audio-base-960h	46.0	100.0	reported
facebook/wav2vec2-large-robust-ft-libri-960h	44.0	99.0	reported
nvidia/canary-qwen-2.5b	53.0	107.0	reported
facebook/wav2vec2-large-960h	50.0	99.0	reported
ibm/granite-speech-3.3-2b	49.0	100.0	reported
facebook/wav2vec2-base-960h	54.0	100.0	reported
openai/whisper-large-v3-turbo	76.0	99.0	reported
efficient-speech/lite-whisper-large-v3-turbo-acc	65.0	98.0	reported
distil-whisper/distil-large-v3	65.0	98.0	reported
ibm/granite-speech-3.3-8b	54.0	105.0	reported
openai/whisper-large	68.0	98.0	reported
distil-whisper/distil-medium.en	65.0	99.0	reported
openai/whisper-large-v3	81.0	99.0	reported
distil-whisper/distil-large-v2	68.0	99.0	reported
Qwen/Qwen2-Audio-7B-Instruct	63.0	102.0	reported
efficient-speech/lite-whisper-large-v3-acc	78.0	99.0	reported
openai/whisper-large-v2	78.0	99.0	reported
kyutai/stt-2.6b-en	62.0	106.0	reported
openai/whisper-medium.en	70.0	99.0	reported
openai/whisper-small.en	73.0	99.0	reported
efficient-speech/lite-whisper-large-v3	66.0	98.0	reported
openai/whisper-base.en	72.0	99.0	reported
efficient-speech/lite-whisper-large-v3-turbo	70.0	99.0	reported
efficient-speech/lite-whisper-large-v3-fast	68.0	99.0	reported
microsoft/Phi-4-multimodal-instruct	65.0	110.0	reported
openai/whisper-tiny.en	76.0	99.0	reported
nvidia/canary-1b-v2	60.0	113.0	reported
efficient-speech/lite-whisper-large-v3-turbo-fast	84.0	100.0	reported
usefulsensors/moonshine-base	71.0	110.0	reported
Qwen/Qwen2-Audio-7B	151.0	178.0	reported
usefulsensors/moonshine-tiny	84.0	134.0	reported

SimbaBench (Kallaama)

Model	WER	CER	Source
facebook/mms-1b-all	66.85	39.72	reported
openai/whisper-large-v3	427.88	356.73	reported
openai/whisper-large-v3-turbo	192.2	151.51	reported
facebook/seamless-m4t-v2-large	171.84	162.56	reported
UBC-NLP/Simba-S	58.07	43.05	reported
UBC-NLP/Simba-M	58.57	34.37	reported
UBC-NLP/omniASR_LLM_7B_v2	58.34	57.11	reported
UBC-NLP/omniASR_LLM_1B_v2	71.21	76.68	reported
UBC-NLP/omniASR_LLM_300M_v2	61.77	61.41	reported
UBC-NLP/omniASR_CTC_7B_v2	49.91	39.0	reported
UBC-NLP/omniASR_CTC_3B_v2	49.26	38.19	reported
UBC-NLP/omniASR_CTC_1B_v2	55.11	40.18	reported

MT (Machine Translation)

FLORES-200

Model	direction	chrF	BLEU	Source
AfriqueQwen-14B	eng→wol	8.41	—	reported
AfriqueQwen-14B	wol→eng	24.15	—	reported
Qwen3-14B	eng→wol	10.23	—	reported
Qwen3-14B	wol→eng	24.99	—	reported
AfriqueGemma-12B	eng→wol	7.11	—	reported
AfriqueGemma-12B	wol→eng	22.53	—	reported
Gemma3-12B	eng→wol	7.6	—	reported
Gemma3-12B	wol→eng	12.38	—	reported
AfriqueLlama-8B	eng→wol	8.93	—	reported
AfriqueLlama-8B	wol→eng	22.37	—	reported
AfriNLLB 548M (Pruned Iterative FT)	eng→wol	28.63	6.97	reported
AfriNLLB 548M (Pruned Iterative FT)	wol→eng	39.58	17.11	reported
AfriNLLB 548M (Pruned Iterative FT)	fra→wol	25.45	4.52	reported
AfriNLLB 548M (Pruned Iterative FT)	wol→fra	37.03	14.97	reported
NLLB-600M	eng→wol	28.63	6.97	reported
NLLB-600M	wol→eng	39.58	17.11	reported
NLLB-600M	fra→wol	21.84	3.73	reported
NLLB-600M	wol→fra	34.59	12.96	reported
google/madlad400-3b-mt	wol→eng	28.4	6.6	reported
google/madlad400-3b-mt	eng→wol	13.2	1.2	reported
google/madlad400-7.2b-mt	wol→eng	29.3	6.7	reported
google/madlad400-7.2b-mt	eng→wol	12.6	1	reported
google/madlad400-10.7b-mt	wol→eng	29.8	7.1	reported
google/madlad400-10.7b-mt	eng→wol	15.4	1.4	reported
google/madlad400-8b-lm	wol→eng	19.7	3.2	reported
google/madlad400-8b-lm	eng→wol	3.5	0	reported

BOUQuET

Model	direction	chrF++	Source
OMT-LLaMA 8B	eng→wol	?	reported
OMT-LLaMA 8B	wol→eng	?	reported

FLORES+ 10-sample

Model	direction	SpBLEU	ChrF	Source
google/gemini-2.5-flash	wol→eng	18.1	45.3	reported
google/gemini-2.5-flash	eng→wol	10.4	33.6	reported
google/gemini-2.5-pro	wol→eng	21.3	45.4	reported
google/gemini-2.5-pro	eng→wol	11.4	34.6	reported
google/gemini-3-pro-preview	wol→eng	32.3	55.7	reported
google/gemini-3-pro-preview	eng→wol	13.5	38.1	reported
openai/gpt-5.2	eng→wol	11.7	35.0	reported
openai/gpt-5.2	wol→eng	12.0	37.5	reported

NTREX

Model	direction	BLEU	chrF	Source
google/madlad400-3b-mt	wol→eng	2.1	18.4	reported
google/madlad400-3b-mt	eng→wol	0.4	9.8	reported
google/madlad400-7.2b-mt	wol→eng	2.4	19.3	reported
google/madlad400-7.2b-mt	eng→wol	0.5	10	reported
google/madlad400-10.7b-mt	wol→eng	2.8	19.4	reported
google/madlad400-10.7b-mt	eng→wol	0.5	12.1	reported
google/madlad400-8b-lm	wol→eng	2.2	20.2	reported
google/madlad400-8b-lm	eng→wol	0	5.3	reported

LLM (Large Language Models)

FLORES-200

Model	Log-perplexity	Source
goldfish-models/wol_latn_full	141.12	reported

AfroBench

Model	Intent	Topic	Source
AfriqueQwen-14B	31.1	58.13	reported
Qwen3-14B	32.82	58.13	reported
AfriqueGemma-12B	29.31	48.49	reported
Gemma3-12B	36.24	58.8	reported
AfriqueLlama-8B	19.81	38.75	reported

AfroBench-Lite

Model	Avg Score	Source
CohereForAI/aya-101	29.2	reported
google/gemma-1.1-7b-it	22.7	reported
meta-llama/Llama-2-7b	16.7	reported
meta-llama/Meta-Llama-3-8B	16.0	reported
meta-llama/Meta-Llama-3.1-8B	17.2	reported
MaLA-LM/LLaMAX3-8B	16.6	reported
google/gemma-2-9b	26.2	reported
google/gemma-2-27b	26.9	reported
meta-llama/Meta-Llama-3.1-70B	25.1	reported
AfroLLaMa 8B	14.2	reported
Gemini 1.5 Pro	29.7	reported
GPT-4o	43.5	reported
google/gemma-3-27b-it	30.9	reported
Gemini 2.0 Flash	63.7	reported
GPT-4.1	49.0	reported
Claude 4.0 Sonnet	39.7	reported
Claude 3.7 Sonnet	46.4	reported
Claude 4.5 Sonnet	43.9	reported
Gemini 2.5 Flash	57.8	reported
Gemini 2.5 Pro	66.9	reported
GPT-5	63.4	reported
Gemini 3 Pro	68.9	reported

AfriMGSM(Math)

Model	Accuracy	Source
Aya-101	1.2	reported
Gemma 2 27B	5.6	reported
LLaMa 3.1 70B	3.2	reported
GPT-4o	28.0	reported

AfriXNLI

Model	Accuracy	Source
Aya-101	36.7	reported
Gemma 2 27B	36.7	reported
LLaMa 3.1 70B	34.7	reported
GPT-4o	52.7	reported

AfriMMLU

Model	AfriMMLU-ElemMath	AfriMMLU-GlobalFacts	AfriMMLU-Geography	AfriMMLU-MicroEcon	AfriMMLU-IntLaw	Source
GPT-4o	61.0	36.0	27.0	19.0	38.0	reported

SIB-200 10-sample

Model	Classification Acc.	Source
baidu/ernie-4.5-300b-a47b	100.0	reported
deepseek/deepseek-v3.2-exp	100.0	reported
openai/gpt-4.1	100.0	reported

📝 Notes

Observations

Dominant language of Senegal, major regional lingua franca
Senegal not in survey but important WCA country (summit host)

ASR Models (31)

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/seamless-m4t-v2-large	2B	66.9K	968
facebook/mms-1b-fl102	1.0B	8.7K	29
CAYTU/whosper-large	—	380	3
facebook/mms-1b-l1107	1.0B	280	12
M9and2M/whisper-small-wolof	0.2B	60	4
espnet/xeus	—	60	146
kingabzpro/wav2vec2-large-xlsr-53-wolof	0.3B	29	3
abdouaziiz/wav2vec2-xls-r-300m-wolof-lm	—	22	5
johntsi/ZeroSwot-Medium_asr-cv_en-to-200	0.4B	17	0
cibfaye/whisper-wolof	0.2B	16	1
johntsi/ZeroSwot-Large_asr-cv_en-to-200	0.4B	16	1
johntsi/ZeroSwot-Medium_asr-mustc_en-to-200	0.4B	14	0
EuriskoMobility/seamless-m4t-v2-large	2B	12	0
johntsi/ZeroSwot-Large_asr-mustc_en-to-200	0.4B	12	0
speechbrain/asr-wav2vec2-dvoice-wolof	—	11	4
aioxlabs/dvoice-wolof	—	8	0
ngia/whisper-small-wolof	0.2B	5	0
osanseviero/seamless-copy	2B	3	0

View on HuggingFace: wo: 30 | wol: 1

TTS Models (31)

Model	Size	Downloads	Likes
k2-fsa/OmniVoice	—	606.0K	577
drbaph/OmniVoice-bf16	—	4.7K	13
WueNLP/seamless-m4t-v2-large-speech-encoder	—	1.7K	9
splendor1811/omnivoice-vietnamese	0.6B	672	2
gluschenko/omnivoice-onnx	—	397	4
CONCREE/Adia_TTS	0.9B	300	11
edwixx/OmniVoice	—	163	0
bilalfaye/speecht5_tts-wolof	0.1B	89	1
bilalfaye/speecht5_tts-wolof-v0.2	0.1B	63	1
AYI-TEKK/tts-wo	0.1B	30	0
WANJIAX2197/OmniVoice	—	30	0
AYI-TEKK/tts-v2	0.1B	28	0
AYI-TEKK/Adia_TTS	0.9B	27	0
Bgeorge/OmniVoice	—	25	1
rnjema-unima/mms-tts-wol-baseline	36.3M	21	0
Manish993135/OmniVoice	—	16	0
bilalRHCH/Arabic-text-to-speech	—	14	0
gubernac/OmniVoice	—	13	1
EBINSHAJI1999/OmniVoice	—	12	0
Citrus-777/OmniVoice	—	12	0

View on HuggingFace: wo: 30 | wol: 1

MT Models (38)

Model	Size	Downloads	Likes
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
alirezamsh/small100	0.3B	3.9K	104
Helsinki-NLP/opus-mt-en-mul	—	3.3K	28
mradermacher/OmniTranslate-1.0-GGUF	0.6B	1.1K	3
mradermacher/OmniTranslate-1.1-GGUF	0.6B	1.1K	2
JustFrederik/nllb-200-distilled-600M-ct2-int8	—	925	1
facebook/nllb-moe-54b	—	557	123
MihaiPopa-1/OmniTranslate-1.1	0.6B	393	0
MihaiPopa-1/OmniTranslate-1.0	0.6B	374	0
JustFrederik/nllb-200-1.3B-ct2-int8	—	200	0
JustFrederik/nllb-200-distilled-600M-ct2-float16	—	157	0
winstxnhdw/nllb-200-distilled-1.3B-ct2-int8	—	141	6
JustFrederik/nllb-200-distilled-1.3B-ct2-int8	—	116	2
JustFrederik/nllb-200-distilled-600M-ct2	—	65	2

View on HuggingFace: wo: 30 | wol: 8

LLM Models (36)

Model	Size	Downloads	Likes
bigscience/bloomz-560m	0.6B	1.0M	137
bigscience/bloom-560m	0.6B	164.0K	371
bigscience/bloom-1b7	2B	49.4K	122
CohereLabs/tiny-aya-global	3B	39.9K	148
bigscience/bloom-3b	3B	14.1K	94
bigscience/bloomz-3b	3B	13.3K	81
bigscience/bloom-7b1	7B	10.4K	202
bigscience/bloom-1b1	1B	7.0K	66
bigscience/bloom	176B	5.9K	5.0K
bigscience/bloomz-7b1	7B	4.2K	147
bigscience/bloomz-7b1-mt	7B	4.1K	144
bigscience/bloom-7b1-intermediate	7B	3.7K	0
bigscience/bloomz-7b1-p3	7B	3.5K	6
bigscience/bloomz	176B	3.5K	513
bigscience/bloom-1b1-intermediate	1B	3.4K	0
bigscience/bloomz-mt	176B	3.3K	32
bigscience/bloomz-1b1	1B	2.9K	33
bigscience/bloomz-1b7	2B	2.8K	23
UBC-NLP/toucan-base	0.6B	2.5K	5
bigscience/bloom-1b7-intermediate	2B	2.4K	0

View on HuggingFace: wo: 30 | wol: 6

Datasets

ASR Datasets (34)

Dataset	Rows	Downloads	Likes
google/fleurs	—	46.3K	392
sarulab-speech/yodas2_sidon	1.5M	6.0K	60
google/xtreme_s	—	3.2K	70
BolajiJsAI/WaxalNLP	2.6M	2.5K	1
suryatmodulus/yodas2_sidon	—	1.1K	0
UBC-NLP/SimbaBench_dataset	748.0K	975	0
WueNLP/belebele-fleurs	65.1K	799	9
satwikguptha/xtreme_s	—	364	0
nanexxx/fleurs	—	313	0
WueNLP/sib-fleurs	94.4K	260	11
YuRiVeRTi/V1Q	186.0K	201	3
soynade-research/Wolof-ASR-Data	86.5K	189	2
facebook/2M-Belebele	59.1K	183	12
cahya/fleurs	—	169	1
galsenai/wolof-audio-data	35.1K	96	2
serge-wilson/wolof-french-asr	47.9K	69	0
vonewman/wolof-audio-data	35.1K	50	1
OlameMend/soreva	—	40	7
developeranalyser/new_train_data	—	32	3
serge-wilson/wolof_speech_transcription	14.8K	31	3

View on HuggingFace: wo: 18 | wol: 16

TTS Datasets (10)

Dataset	Rows	Downloads	Likes
sarulab-speech/yodas2_sidon	1.5M	6.0K	60
BolajiJsAI/WaxalNLP	2.6M	2.5K	1
suryatmodulus/yodas2_sidon	—	1.1K	0
UBC-NLP/SimbaBench_dataset	748.0K	975	0
WueNLP/belebele-fleurs	65.1K	799	9
WueNLP/sib-fleurs	94.4K	260	11
galsenai/wolof_tts	40.0K	225	10
YuRiVeRTi/V1Q	186.0K	201	3
galsenai/anta_women_tts	19.9K	182	9
OlameMend/soreva	—	40	7

View on HuggingFace: wo: 7 | wol: 3

Translation Datasets (60)

Dataset	Rows	Downloads	Likes
HuggingFaceFW/finetranslations	—	75.8K	283
facebook/flores	—	43.4K	97
openlanguagedata/flores_plus	893.0K	15.8K	124
CohereLabs/aya_collection	514.0M	12.6K	234
yhavinga/ccmatrix	—	4.0K	26
google/smol	798.0K	2.8K	94
Muennighoff/flores200	—	1.6K	20
gsarti/flores_101	207.0K	1.6K	32
facebook/bouquet	5.6M	1.6K	33
aiana94/polynews-parallel	5.4M	1.4K	13
ayymen/Pontoon-Translations	3.6M	1.1K	18
Helsinki-NLP/tatoeba	—	866	56
masakhane/mafand	143.0K	463	15
ayymen/Weblate-Translations	11.7M	383	18
sbmaruf/forai_ml_masakhane_mafand	136.0K	365	2
Helsinki-NLP/opus_ubuntu	37.4K	354	4
mteb/NTREXBitextMining	2.0K	309	1
mteb/FloresBitextMining	2.0K	303	1
visheratin/laion-coco-nllb	894.0K	255	44
cointegrated/panlex-meanings	157.0M	255	13

View on HuggingFace: wo: 30 | wol: 30