Mooré - UNICEF WCARO NLP

🌍 General Information

ISO 639-3mos

ISO 639-1—

French Namemoré

Glottocodemoss1236

Language FamilyNiger–Congo

Writing SystemLatin ( Mooré alphabet ) Minim Dag Noore [ 2 ]

L1 Speakers12 million

L2 Speakers—

Population7600000 (10⁶+)

Endangermentsafe

CountriesBenin, Burkina Faso, Cote d'Ivoire, Ghana, Mali, Togo

Also Known AsMole, Moose, More, Moré, Moshi, Mossi

WikipediaMooré on Wikipedia

🗺️ Language Use

Data from CLEAR Global's Language Use Data Platform.

👥 Actors (2)

BurkimbIA (Ngo)

Non-profit community of Burkinabe engineers, researchers, students, and professionals building open-source AI models for the Moore (Mossi) language. M...

GO AI Corp (Startup)

GO AI Corp is a Burkinabè technology startup providing AI solutions, web/mobile development, cybersecurity, and cloud services. They co-developed NLP ...

🤖 NLP & Tech Resources

✓ AfroLID

✓ NLLB-200

✓ Mozilla Common Voice: ☑️

✓ Fineweb2: 💬

✓ CMU Wilderness

✓ MAFAND

✓ MMS-ASR

✓ MMS-TTS

✓ MMS-LID

✓ Omnilingual ASR

✓ SimbaBench

Benchmarks

ASR (Speech-to-Text)

GoAI

Model	WER	CER	Source
facebook/omniASR-LLM-3B	37.66	14.81	evaluated
facebook/omniASR-LLM-7B	29.51	10.56	evaluated
facebook/mms-1b-all	43.75	14.62	evaluated
UBC-NLP/Simba-S	114.58	75.04	evaluated

MT (Machine Translation)

MAFAND-MT

Model	spBLEU	chrF++	direction	BLEU	Source
facebook/nllb-200-3.3B	5.4	27.6	fra→mos	—	reported
facebook/nllb-200-3.3B	6.1	23.5	mos→fra	—	reported
masakhane/m2m100_418M_fr_mos_rel_news_ft	—	16.8	fra→mos	2.2	reported
masakhane/m2m100_418M_mos_fr_rel_news_ft	—	18.8	mos→fra	4.1	reported

BOUQuET

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

FLORES+ 10-sample

Model	direction	SpBLEU	ChrF	Source
anthropic/claude-opus-4.5	eng→mos	6.4	32.5	reported
anthropic/claude-opus-4.5	mos→eng	6.9	29.4	reported
anthropic/claude-opus-4.6	mos→eng	9.2	30.3	reported
anthropic/claude-opus-4.6	eng→mos	3.8	32.8	reported
anthropic/claude-sonnet-4.5	mos→eng	14.9	31.3	reported
anthropic/claude-sonnet-4.5	eng→mos	5.1	24.0	reported
baidu/ernie-4.5-300b-a47b	eng→mos	5.4	30.8	reported
baidu/ernie-4.5-300b-a47b	mos→eng	9.1	27.9	reported
google/gemini-3-pro-preview	mos→eng	15.2	38.7	reported
google/gemini-3-pro-preview	eng→mos	5.8	30.3	reported

FLORES-200

Model	direction	BLEU	chrF	Source
google/madlad400-3b-mt	mos→eng	3.4	23	reported
google/madlad400-3b-mt	eng→mos	0.9	2.3	reported
google/madlad400-7.2b-mt	mos→eng	3.4	22.4	reported
google/madlad400-7.2b-mt	eng→mos	1.2	16.6	reported
google/madlad400-10.7b-mt	mos→eng	3.7	24.1	reported
google/madlad400-10.7b-mt	eng→mos	0.8	2.2	reported
google/madlad400-8b-lm	mos→eng	1.6	17.5	reported
google/madlad400-8b-lm	eng→mos	0	3.5	reported

LLM (Large Language Models)

FLORES-200

Model	Log-perplexity	Source
goldfish-models/mos_latn_full	187.64	reported

SIB-200 10-sample

Model	Classification Acc.	Source
amazon/nova-pro-v1	100.0	reported
anthropic/claude-opus-4.5	100.0	reported
anthropic/claude-sonnet-4.6	100.0	reported

SAHARA

Model	Lang. Avg.	spBLEU fra→mos	NER F1	Source
gemini-3-pro-preview	34.37	3.88	64.86	reported
gemini-2.5-pro	27.46	2.53	52.38	reported
gpt-5-2025-08-07	22.05	1.25	42.86	reported
gpt-5.1-2025-11-13	13.91	1.14	26.67	reported
gemini-2.5-flash	15.45	0.13	30.77	reported
claude-sonnet-4-5@20250929	15.48	0.97	30.0	reported
claude-4-sonnet-20250514	12.77	1.14	24.39	reported
gpt-4.1	16.83	1.09	32.56	reported
CohereForAI/c4ai-command-a-03-2025	8.17	0.96	15.38	reported
meta-llama/Llama-4-Scout-17B-16E-Instruct	4.21	1.01	7.41	reported
meta-llama/Llama-3.3-70B-Instruct	5.7	0.58	10.81	reported
google/gemma-3-27b-it	5.36	0.72	10.0	reported
google/gemma-2-27b-it	14.58	0.59	28.57	reported
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B	3.5	0.33	6.67	reported
meta-llama/Llama-3.1-70B-Instruct	4.94	0.79	9.09	reported
Qwen/Qwen3-30B-Instruct-2507	8.1	0.19	16.0	reported
deepseek-ai/DeepSeek-R1-Distill-Llama-70B	5.06	0.6	9.52	reported
Tower-Babel/Babel-9B-Chat	0.15	0.31	0.0	reported
Tower-Babel/Babel-83B-Chat	4.15	0.61	7.69	reported
Qwen/Qwen3-4B-Instruct-2507	0.07	0.15	0.0	reported
google/gemma-2-9b-it	0.12	0.24	0.0	reported
google/gemma-3-12b-it	3.32	0.59	6.06	reported
meta-llama/Llama-3.1-8B-Instruct	0.07	0.14	0.0	reported
CohereForAI/aya-23-35B	0.07	0.13	0.0	reported
CohereForAI/c4ai-command-r-plus-08-2024	4.85	0.18	9.52	reported
CohereForAI/c4ai-command-r7b-12-2024	0.1	0.19	0.0	reported
microsoft/Phi-4-mini-instruct	0.18	0.37	0.0	reported
meta-llama/Llama-3.2-1B-Instruct	0.34	0.68	0.0	reported
microsoft/Phi-3.5-mini-instruct	0.17	0.34	0.0	reported
google/gemma-2-2b-it	0.09	0.18	0.0	reported
CohereForAI/aya-23-8B	0.1	0.19	0.0	reported
google/gemma-3-4b-it	0.17	0.34	0.0	reported
meta-llama/Llama-3.2-3B-Instruct	0.04	0.08	0.0	reported

📝 Notes

Observations

Survey Focus 1 for Burkina Faso (2026 UNICEF WCAR Local Languages Survey)
Also in Use Cases Document: Burkina Faso Moore language integration with GoAI (STT, TTS, French-Moore translation deployed in UYouth/U-Report via RapidPro)

ASR Models (14)

Model	Size	Downloads	Likes
UBC-NLP/Simba-S	2B	2.2K	4
burkimbia/BIA-WHISPER-LARGE-SACHI_V2	2B	77	0
espnet/xeus	—	60	146
UBC-NLP/Simba-W	2B	44	0
UBC-NLP/Simba-M	—	33	0
goaicorp/mos-whisper-small	0.2B	19	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
burkimbia/BIA-WHISPER-LARGE-SACHI_V3	2B	14	0
johntsi/ZeroSwot-Large_asr-mustc_en-to-200	0.4B	12	0
UBC-NLP/Simba-H	—	5	0
goaicorp/mos-whisper-large-v3-turbo	0.8B	3	0
UBC-NLP/Simba-X	—	3	0

View on HuggingFace: mos: 14

TTS Models (3)

Model	Size	Downloads	Likes
mradermacher/orpheus-tts-mos-GGUF	3B	32	0
burkimbia/BIA-XTTSv2-moore-v0	—	0	0
burkimbia/BIA-XTTSv2-moore-v1	—	0	1

View on HuggingFace: mos: 3

MT Models (30)

Model	Downloads	Likes
facebook/nllb-200-distilled-600M	1.1M	880
facebook/nllb-200-distilled-1.3B	147.0K	181
facebook/nllb-200-3.3B	81.6K	443
facebook/nllb-200-1.3B	31.4K	71
Xenova/nllb-200-distilled-600M	4.4K	50
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-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
JustFrederik/nllb-200-3.3B-ct2-float16	52	3
Helsinki-NLP/opus-mt-sv-mos	49	0
Helsinki-NLP/opus-mt-fr-mos	47	1
michaelfeil/ct2fast-nllb-200-distilled-1.3B	47	1
michaelfeil/ct2fast-nllb-200-3.3B	43	14
Helsinki-NLP/opus-mt-fi-mos	41	0
Helsinki-NLP/opus-mt-mos-en	41	0
ychenNLP/nllb-200-3.3B-easyproject	36	8

View on HuggingFace: mos: 30

LLM Models (4)

Model	Downloads	Likes
goldfish-models/mos_latn_5mb	6	0
goldfish-models/mos_latn_full	2	0
goldfish-models/mos_latn_10mb	2	0
wikilangs/mos	0	0

View on HuggingFace: mos: 4

Datasets

ASR Datasets (11)

Dataset	Rows	Downloads	Likes
UBC-NLP/SimbaBench_dataset	748.0K	975	0
WueNLP/sib-fleurs	94.4K	260	11
goaicorp/GOAI-MooreSpeechCorpora	11.1K	161	3
goaicorp/goai-moore-speech-proverbes	2.3K	15	1
goaicorp/goai-moore-speech-devinettes	611	15	1
goaicorp/goai-moore-speech-contes	6.0K	15	1
anyantudre/moore-speech-contes	11.9K	13	1
anyantudre/moore-speech-devinettes	611	7	1
anyantudre/moore-speech-proverbes	2.3K	6	1
anyantudre/MooreSpeechCorpora	5.5K	4	3
Minervus00/moore_audio_data	27.1K	4	1

View on HuggingFace: mos: 11

TTS Datasets (12)

Dataset	Rows	Downloads	Likes
UBC-NLP/SimbaBench_dataset	748.0K	975	0
WueNLP/sib-fleurs	94.4K	260	11
goaicorp/GOAI-MooreSpeechCorpora	11.1K	161	3
goaicorp/goai-moore-speech-proverbes	2.3K	15	1
goaicorp/goai-moore-speech-devinettes	611	15	1
goaicorp/goai-moore-speech-contes	6.0K	15	1
anyantudre/moore-speech-contes	11.9K	13	1
anyantudre/moore-speech-devinettes	611	7	1
anyantudre/moore-speech-proverbes	2.3K	6	1
anyantudre/MooreSpeechCorpora	5.5K	4	3
Minervus00/moore_audio_data	27.1K	4	1
sawadogosalif/MooreFRCollections	61.9K	2	4

View on HuggingFace: mos: 12

Translation Datasets (25)

Dataset	Rows	Downloads	Likes
facebook/flores	—	43.4K	97
openlanguagedata/flores_plus	893.0K	15.8K	124
google/smol	798.0K	2.8K	94
Muennighoff/flores200	—	1.6K	20
facebook/bouquet	5.6M	1.6K	33
aiana94/polynews-parallel	5.4M	1.4K	13
masakhane/mafand	143.0K	463	15
sbmaruf/forai_ml_masakhane_mafand	136.0K	365	2
mteb/FloresBitextMining	2.0K	303	1
visheratin/laion-coco-nllb	894.0K	255	44
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
FrancophonIA/gatitos	—	61	4
vpermilp/nllb-200-distilled-600M-rust	—	51	1
robinhad/long_flores	—	49	0
madoss/nllb-mos-raw	2.2M	36	0
Svngoku/xP3x-Kongo	1.2M	30	4
neulab/PangeaBench-flores	—	17	0

View on HuggingFace: mos: 25