MMS-1B-all ONNX — one shared base, one small pack for each of 1198 languages

ONNX export of Meta's facebook/mms-1b-all for onnx-asr. A single 1B-parameter base graph serves every language. Each language adds only a small adapter pack.

This release holds every adapter in the checkpoint: 1198 languages.

How it works

MMS is one wav2vec2 base with a small attention adapter and a CTC head per language. A merged export costs 3.6 GB for every language. Here the adapter layers and the CTC head are graph inputs, not baked-in weights:

Item Size
model.onnx + model.onnx_data (shared base, fp32) 3.85 GB, once
model.int8.onnx + model.int8.onnx_data (shared base, int8) 1.00 GB, once
adapters/<iso>.npz + vocabs/<iso>.txt about 8.4 MB per language

One session holds 3.75 GB and each extra pack adds about 7 MB. Feeding the adapter tensors costs about 0.02 ms per call, so switching language is free.

model.onnx            shared base graph
model.onnx_data       base weights (fp32)
model.int8.onnx       shared base graph, dynamic int8 weights
model.int8.onnx_data  base weights (int8)
config.json           model_type, language list, aliases
manifest.json         per-language verification record
adapters/<iso>.npz    adapter layers + CTC head + true vocab size
vocabs/<iso>.txt      character vocabulary for that language

Usage

The whole repository is about 15 GB, so onnx-asr downloads one language at a time. That needs the feat/adapter-lazy-download branch of the TigreGotico fork:

pip install "onnx-asr[cpu] @ git+https://github.com/TigreGotico/onnx-asr@feat/adapter-lazy-download"
import onnx_asr

model = onnx_asr.load_model("OpenVoiceOS/mms-1b-all-onnx")
print(len(model.asr.languages))

print(model.recognize("clip.wav", language="swh"))
print(model.recognize("clip.wav", language="sw-KE"))

The first load fetches the base graph, config.json and the pack of default_language (swh). Every other pack is fetched the first time its language is used and then cached. To pay that cost up front:

model.asr.preload("yor", "ces", "khm")

Add quantization="int8" to load_model for the int8 base.

language takes the pack name (swh), a BCP-47 tag whose primary subtag maps to a pack (sw-KE, cs), or one of the 133 aliases in config.json. Pack names with a script or dialect suffix (azj-script_latin, cak-dialect_central) must be given in full.

Verification

manifest.json records what was checked for each language.

Tier Languages What was done
A-real-clip 29 Transcription of a real recording, compared with the native transformers model (log-probability difference and token sequence).
A-plausible 68 Transcription of a real FLEURS recording through the ONNX graph, with the character error rate against the FLEURS reference.
A-native-parity 4 Native-model parity checked, but no reference recording exists for the language.
B-graph 1097 The pack runs through the shared base graph, the log-probabilities are finite and every emitted index decodes through the language vocabulary. No recording was available.

97 languages were checked on a real recording; 29 of those were also compared against the native transformers model. The remaining 1101 languages have no public recording, so they have the graph and vocabulary check only. Every pack was also checked structurally at export time: tensor names, tensor shapes and vocabulary size against the vocabulary file.

A character error rate in the table is against one FLEURS sentence. It says the model produces the right script and roughly the right words; it is not a benchmark.

Languages

All 1198 languages
Pack Language Vocabulary Verification CER
abi Abidji 56 B-graph
abk Abkhazian 46 B-graph
abp Abellen Ayta 36 B-graph
aca Achagua 38 B-graph
acd Gikyode 31 B-graph
ace Acehnese 45 B-graph
acf Saint Lucian Creole French 36 B-graph
ach Acoli 31 B-graph
acn Achang 40 B-graph
acr Achi 40 A-native-parity
acu Achuar-Shiwiar 38 B-graph
ade Adele 43 B-graph
adh Adhola 32 B-graph
adj Adioukrou 49 B-graph
adx Amdo Tibetan 61 B-graph
aeu Akeu 28 B-graph
afr Afrikaans 77 A-real-clip 0.04
agd Agarabi 33 B-graph
agg Angor 36 B-graph
agn Agutaynen 43 B-graph
agr Aguaruna 41 B-graph
agu Aguacateco 43 B-graph
agx Aghul 37 B-graph
aha Ahanta 50 B-graph
ahk Akha 33 B-graph
aia Arosi 32 B-graph
aka Akan 35 B-graph
akb Batak Angkola 35 B-graph
ake Akawaio 35 B-graph
akp Siwu 38 B-graph
alj Alangan 28 B-graph
alp Alune 33 B-graph
alt Southern Altai 49 B-graph
alz Alur 30 B-graph
ame Yanesha' 42 B-graph
amf Hamer-Banna 31 B-graph
amh Amharic 339 A-real-clip 0.03
ami Amis 29 B-graph
amk Ambai 38 B-graph
ann Obolo 43 B-graph
any Anyin 42 B-graph
aoz Uab Meto 28 B-graph
apb Sa'a 41 B-graph
apr Arop-Lokep 34 B-graph
ara Arabic 121 A-plausible 0.11
arl Arabela 37 B-graph
asa Asu 31 B-graph
asg Cishingini 35 B-graph
asm Assamese 138 A-plausible 0.01
ast Asturian 80 A-real-clip 0.06
ata Pele-Ata 36 B-graph
atb Zaiwa 53 B-graph
atg Ivbie North-Okpela-Arhe 53 B-graph
ati Attié 34 B-graph
atq Aralle-Tabulahan 31 B-graph
ava Avaric 40 B-graph
avn Avatime 52 B-graph
avu Avokaya 60 B-graph
awa Awadhi 81 B-graph
awb Awa (Papua New Guinea) 38 B-graph
ayo Ayoreo 60 B-graph
ayr Central Aymara 44 B-graph
ayz Mai Brat 43 B-graph
azb South Azerbaijani 42 B-graph
azg San Pedro Amuzgos Amuzgo 42 B-graph
azj-script_cyrillic North Azerbaijani — cyrillic 40 B-graph
azj-script_latin North Azerbaijani — latin 70 B-graph
azz Highland Puebla Nahuatl 36 B-graph
bak Bashkir 55 B-graph
bam Bambara 39 B-graph
ban Balinese 28 B-graph
bao Waimaha 48 B-graph
bas Basaa 29 B-graph
bav Vengo 43 B-graph
bba Baatonum 38 B-graph
bbb Barai 25 B-graph
bbc Batak Toba 32 B-graph
bbo Northern Bobo Madaré 38 B-graph
bcc-script_arabic Southern Balochi — arabic 34 B-graph
bcc-script_latin Southern Balochi — latin 32 B-graph
bcl Central Bikol 34 B-graph
bcw Bana 32 B-graph
bdg Bonggi 27 B-graph
bdh Baka (South Sudan) 42 B-graph
bdq Bahnar 40 B-graph
bdu Oroko 48 B-graph
bdv Bodo Parja 42 B-graph
beh Biali 34 B-graph
bel Belarusian 95 A-plausible 0.07
bem Bemba 36 A-real-clip
ben Bangla 136 A-plausible 0.05
bep Besoa 30 B-graph
bex Jur Modo 36 B-graph
bfa Bari 31 B-graph
bfo Malba Birifor 52 B-graph
bfy Bagheli 57 B-graph
bfz Mahasu Pahari 66 B-graph
bgc Haryanvi 66 B-graph
bgq Bagri 64 B-graph
bgr Bawm Chin 39 B-graph
bgt Bughotu 28 B-graph
bgw Bhatri 44 B-graph
bha Bharia 50 B-graph
bht Bhattiyali 70 B-graph
bhz Bada (Indonesia) 29 B-graph
bib Bissa 37 B-graph
bim Bimoba 34 B-graph
bis Bislama 30 B-graph
biv Southern Birifor 41 B-graph
bjr Binumarien 42 B-graph
bjv Bedjond 34 B-graph
bjw Bakwé 38 B-graph
bjz Baruga 50 B-graph
bkd Binukid 45 B-graph
bkv Bekwarra 57 B-graph
blh Kuwaa 48 B-graph
blt Tai Dam 73 B-graph
blx Mag-Indi Ayta 34 B-graph
blz Balantak 31 B-graph
bmq Bomu 51 B-graph
bmr Muinane 33 B-graph
bmu Somba-Siawari 42 B-graph
bmv Bum 43 B-graph
bng Benga 66 B-graph
bno Bantoanon 36 B-graph
bnp Bola 37 B-graph
boa Bora 48 B-graph
bod Tibetan 65 B-graph
boj Anjam 41 B-graph
bom Berom 64 B-graph
bor Borôro 52 B-graph
bos Bosnian 77 A-plausible 0.02
bov Tuwuli 40 B-graph
box Buamu 52 B-graph
bpr Koronadal Blaan 43 B-graph
bps Sarangani Blaan 33 B-graph
bqc Boko (Benin) 50 B-graph
bqi Bakhtiari 46 B-graph
bqj Bandial 40 B-graph
bqp Busa 61 B-graph
bre Breton 43 B-graph
bru Eastern Bru 51 B-graph
bsc Bassari 38 B-graph
bsq Bassa 63 B-graph
bss Akoose 62 B-graph
btd Batak Dairi 41 B-graph
bts Batak Simalungun 31 B-graph
btt Bete-Bendi 55 B-graph
btx Batak Karo 38 B-graph
bud Ntcham 54 B-graph
bul Bulgarian 96 A-real-clip 0.02
bus Bokobaru 51 B-graph
bvc Baelelea 32 B-graph
bvz Bauzi 30 B-graph
bwq Southern Bobo Madaré 34 B-graph
bwu Buli (Ghana) 30 B-graph
byr Baruya 40 B-graph
bzh Mapos Buang 44 B-graph
bzi Bisu 75 B-graph
bzj Belize Kriol English 32 B-graph
caa Chortí 48 B-graph
cab Garifuna 36 B-graph
cac-dialect_sanmateoixtatan Chuj — dialect sanmateoixtatan 48 B-graph
cac-dialect_sansebastiancoatan Chuj — dialect sansebastiancoatan 50 B-graph
cak-dialect_central Kaqchikel — dialect central 48 B-graph
cak-dialect_santamariadejesus Kaqchikel — dialect santamariadejesus 38 B-graph
cak-dialect_santodomingoxenacoj Kaqchikel — dialect santodomingoxenacoj 49 B-graph
cak-dialect_southcentral Kaqchikel — dialect southcentral 38 B-graph
cak-dialect_western Kaqchikel — dialect western 39 B-graph
cak-dialect_yepocapa Kaqchikel — dialect yepocapa 32 B-graph
cap Chipaya 47 B-graph
car Carib 30 B-graph
cas Tsimané 62 B-graph
cat Catalan 106 A-plausible 0.04
cax Chiquitano 39 B-graph
cbc Carapana 46 B-graph
cbi Chachi 50 B-graph
cbr Cashibo-Cacataibo 41 B-graph
cbs Cashinahua 49 B-graph
cbt Chayahuita 32 B-graph
cbu Candoshi-Shapra 47 B-graph
cbv Cacua 50 B-graph
cce Chopi 34 B-graph
cco Comaltepec Chinantec 50 B-graph
cdj Churahi 69 B-graph
ceb Cebuano 74 A-plausible 0.04
ceg Chamacoco 48 B-graph
cek Eastern Khumi Chin 40 B-graph
ces Czech 86 A-real-clip 0.00
cfm Falam Chin 37 B-graph
cgc Kagayanen 34 B-graph
che Chechen 39 B-graph
chf Tabasco Chontal 39 B-graph
chv Chuvash 47 B-graph
chz Ozumacín Chinantec 54 B-graph
cjo Ashéninka Pajonal 39 B-graph
cjp Cabécar 46 B-graph
cjs Shor 42 B-graph
ckb Central Kurdish 111 A-real-clip 0.15
cko Anufo 39 B-graph
ckt Chukot 42 B-graph
cla Ron 35 B-graph
cle Lealao Chinantec 47 B-graph
cly Eastern Highland Chatino 41 B-graph
cme Cerma 39 B-graph
cmn-script_simplified Mandarin Chinese — simplified 4495 B-graph
cmo-script_khmer Central Mnong — khmer 59 B-graph
cmo-script_latin Central Mnong — latin 51 B-graph
cmr Mro-Khimi Chin 38 B-graph
cnh Hakha Chin 33 B-graph
cni Asháninka 34 B-graph
cnl Lalana Chinantec 48 B-graph
cnt Tepetotutla Chinantec 48 B-graph
coe Koreguaje 45 B-graph
cof Colorado 37 B-graph
cok Santa Teresa Cora 40 B-graph
con Cofán 40 B-graph
cot Caquinte 45 B-graph
cou Wamey 40 B-graph
cpa Palantla Chinantec 45 B-graph
cpb Ucayali-Yurúa Ashéninka 49 B-graph
cpu Pichis Ashéninka 47 B-graph
crh Crimean Tatar 47 B-graph
crk-script_latin Plains Cree — latin 39 B-graph
crk-script_syllabics Plains Cree — syllabics 82 B-graph
crn El Nayar Cora 40 B-graph
crq Iyo'wujwa Chorote 50 B-graph
crs Seselwa Creole French 39 B-graph
crt Iyojwa'ja Chorote 43 B-graph
csk Jola-Kasa 37 B-graph
cso Sochiapam Chinantec 42 B-graph
ctd Tedim Chin 44 B-graph
ctg Chittagonian 62 B-graph
cto Emberá-Catío 45 B-graph
ctu Chol 40 B-graph
cuc Usila Chinantec 43 B-graph
cui Cuiba 41 B-graph
cuk San Blas Kuna 39 B-graph
cul Culina 44 B-graph
cwa Kabwa 31 B-graph
cwe Kwere 34 B-graph
cwt Kuwaataay 36 B-graph
cya Nopala Chatino 40 B-graph
cym Welsh 83 A-plausible 0.11
daa Dangaléat 34 B-graph
dah Gwahatike 39 B-graph
dan Danish 75 A-plausible 0.04
dar Dargwa 39 B-graph
dbj Ida'an 30 B-graph
dbq Daba 36 B-graph
ddn Dendi (Benin) 39 B-graph
ded Dedua 39 B-graph
des Desano 49 B-graph
deu German 194 A-plausible 0.04
dga Southern Dagaare 38 B-graph
dgi Northern Dagara 56 B-graph
dgk Dagba 49 B-graph
dgo Dogri (individual language) 67 B-graph
dgr Dogrib 47 B-graph
dhi Dhimal 59 B-graph
did Didinga 38 B-graph
dig Digo 35 B-graph
dik Southwestern Dinka 36 B-graph
dip Northeastern Dinka 32 B-graph
div Divehi 65 B-graph
djk Eastern Maroon Creole 33 B-graph
dnj-dialect_blowowest Dan — dialect blowowest 35 B-graph
dnj-dialect_gweetaawueast Dan — dialect gweetaawueast 39 B-graph
dnt Mid Grand Valley Dani 41 B-graph
dnw Western Dani 38 B-graph
dop Lukpa 38 B-graph
dos Dogosé 47 B-graph
dsh Daasanach 43 B-graph
dso Desiya 36 B-graph
dtp Central Dusun 35 B-graph
dts Toro So Dogon 31 B-graph
dug Duruma 33 B-graph
dwr Dawro 33 B-graph
dyi Djimini Senoufo 39 B-graph
dyo Jola-Fonyi 37 B-graph
dyu Dyula 35 B-graph
dzo Dzongkha 61 B-graph
eip Eipomek 41 B-graph
eka Ekajuk 32 B-graph
ell Greek 102 A-real-clip 0.00
emp Northern Emberá 60 B-graph
enb Markweeta 34 B-graph
eng English 154 A-plausible 0.01
enx Enxet 42 B-graph
epo Esperanto 51 B-graph
ese Ese Ejja 49 B-graph
ess Central Siberian Yupik 46 B-graph
est Estonian 74 A-plausible 0.04
eus Basque 34 B-graph
evn Evenki 41 B-graph
ewe Ewe 55 B-graph
eza Ezaa 48 B-graph
fal South Fali 41 B-graph
fao Faroese 40 B-graph
far Fataleka 29 B-graph
fas Persian 118 A-plausible 0.07
fij Fijian 39 B-graph
fin Finnish 71 A-real-clip 0.01
flr Fuliiru 35 B-graph
fmu Far Western Muria 53 B-graph
fon Fon 49 B-graph
fra French 314 A-plausible 0.00
frd Fordata 32 B-graph
fry Western Frisian 46 B-graph
ful Fula 85 A-plausible 0.23
gag-script_cyrillic Gagauz — cyrillic 39 B-graph
gag-script_latin Gagauz — latin 41 B-graph
gai Borei 36 B-graph
gam Kandawo 35 B-graph
gau Mudhili Gadaba 64 B-graph
gbi Galela 37 B-graph
gbk Gaddi 69 B-graph
gbm Garhwali 68 B-graph
gbo Northern Grebo 48 B-graph
gde Gude 41 B-graph
geb Kire 37 B-graph
gej Gen 48 B-graph
gil Gilbertese 28 B-graph
gjn Gonja 34 B-graph
gkn Gokana 58 B-graph
gld Nanai 37 B-graph
gle Irish 78 A-plausible 0.36
glg Galician 76 A-real-clip 0.10
glk Gilaki 42 B-graph
gmv Gamo 34 B-graph
gna Kaansa 62 B-graph
gnd Zulgo-Gemzek 38 B-graph
gng Ngangam 47 B-graph
gof-script_latin Gofa — latin 32 B-graph
gog Gogo 30 B-graph
gor Gorontalo 30 B-graph
gqr Gor 32 B-graph
grc Ancient Greek 122 B-graph
gri Ghari 33 B-graph
grn Guarani 58 B-graph
grt Garo 66 B-graph
gso Southwest Gbaya 39 B-graph
gub Guajajára 35 B-graph
guc Wayuu 48 A-native-parity
gud Yocoboué Dida 36 B-graph
guh Guahibo 48 B-graph
guj Gujarati 124 A-plausible 0.05
guk Gumuz 221 B-graph
gum Guambiano 46 B-graph
guo Guayabero 41 B-graph
guq Aché 49 B-graph
guu Yanomamö 49 B-graph
gux Gourmanchéma 30 B-graph
gvc Guanano 46 B-graph
gvl Gulay 56 B-graph
gwi Gwichʼin 49 B-graph
gwr Gwere 42 B-graph
gym Ngäbere 51 B-graph
gyr Guarayu 47 B-graph
had Hatam 30 B-graph
hag Hanga 33 B-graph
hak Hakka Chinese 46 B-graph
hap Hupla 40 B-graph
hat Haitian Creole 35 B-graph
hau Hausa 84 A-plausible 0.06
hay Haya 39 B-graph
heb Hebrew 90 A-plausible 0.27
heh Hehe 30 B-graph
hif Fiji Hindi 43 B-graph
hig Kamwe 39 B-graph
hil Hiligaynon 45 B-graph
hin Hindi 127 A-real-clip 0.07
hlb Halbi 54 B-graph
hlt Matu Chin 31 B-graph
hne Chhattisgarhi 71 B-graph
hnn Hanunoo 24 B-graph
hns Caribbean Hindustani 33 B-graph
hoc Ho 58 B-graph
hoy Holiya 64 B-graph
hrv Croatian 76 A-plausible 0.00
hsb Upper Sorbian 44 B-graph
hto Minica Huitoto 42 B-graph
hub Huambisa 38 B-graph
hui Huli 30 B-graph
hun Hungarian 76 A-plausible 0.13
hus-dialect_centralveracruz Huastec — dialect centralveracruz 33 B-graph
hus-dialect_westernpotosino Huastec — dialect westernpotosino 48 B-graph
huu Murui Huitoto 40 B-graph
huv San Mateo Del Mar Huave 40 B-graph
hvn Sabu 30 B-graph
hwc Hawai'i Creole English 41 B-graph
hye Armenian 103 A-plausible 0.03
hyw Western Armenian 44 B-graph
iba Iban 32 B-graph
ibo Igbo 89 A-real-clip 0.06
icr Islander Creole English 38 B-graph
idd Ede Idaca 43 B-graph
ifa Amganad Ifugao 32 B-graph
ifb Batad Ifugao 33 B-graph
ife Ifè 52 B-graph
ifk Tuwali Ifugao 37 B-graph
ifu Mayoyao Ifugao 33 B-graph
ify Keley-I Kallahan 33 B-graph
ign Ignaciano 46 B-graph
ikk Ika 39 B-graph
ilb Ila 31 B-graph
ilo Iloko 44 B-graph
imo Imbongu 33 B-graph
ina Interlingua 35 B-graph
inb Inga 39 B-graph
ind Indonesian 80 A-real-clip 0.00
iou Tuma-Irumu 41 B-graph
ipi Ipili 27 B-graph
iqw Ikwo 48 B-graph
iri Rigwe 46 B-graph
irk Iraqw 36 B-graph
isl Icelandic 64 A-plausible 0.05
ita Italian 183 A-plausible 0.04
itl Itelmen 51 B-graph
itv Itawit 33 B-graph
ixl-dialect_sangasparchajul Ixil — dialect sangasparchajul 36 B-graph
ixl-dialect_sanjuancotzal Ixil — dialect sanjuancotzal 45 B-graph
ixl-dialect_santamarianebaj Ixil — dialect santamarianebaj 45 B-graph
izr Izere 39 B-graph
izz Izii 51 B-graph
jac Popti' 36 B-graph
jam Jamaican Creole English 32 B-graph
jav Javanese 73 A-real-clip 0.04
jbu Jukun Takum 51 B-graph
jen Dza 39 B-graph
jic Tol 46 B-graph
jiv Shuar 29 B-graph
jmc Machame 36 B-graph
jmd Yamdena 30 B-graph
jpn Japanese 2268 A-plausible 0.15
jun Juang 57 B-graph
juy Juray 42 B-graph
jvn Caribbean Javanese 38 B-graph
kaa Kara-Kalpak 50 B-graph
kab Kabyle 65 B-graph
kac Kachin 29 B-graph
kak Kalanguya 40 B-graph
kam Kamba 68 A-plausible 0.01
kan Kannada 125 A-plausible 0.06
kao Xaasongaxango 35 B-graph
kaq Capanahua 37 B-graph
kat Georgian 93 A-real-clip 0.02
kay Kamayurá 48 B-graph
kaz Kazakh 108 A-plausible 0.06
kbo Keliko 53 B-graph
kbp Kabiyè 46 B-graph
kbq Kamano 42 B-graph
kbr Kafa 35 B-graph
kby Manga Kanuri 33 B-graph
kca Khanty 49 B-graph
kcg Tyap 37 B-graph
kdc Kutu 29 B-graph
kde Makonde 36 B-graph
kdh Tem 46 B-graph
kdi Kumam 30 B-graph
kdj Karamojong 29 B-graph
kdl Tsikimba 36 B-graph
kdn Kunda 32 B-graph
kdt Kuy 64 B-graph
kea Kabuverdianu 75 A-plausible 0.04
kek Kekchí 40 A-native-parity
ken Kenyang 54 B-graph
keo Kakwa 31 B-graph
ker Kera 55 B-graph
key Kupia 55 B-graph
kez Kukele 53 B-graph
kfb Northwestern Kolami 53 B-graph
kff-script_telugu Koya — telugu 44 B-graph
kfw Kharam Naga 45 B-graph
kfx Kullu Pahari 68 B-graph
khg Khams Tibetan 61 B-graph
khm Khmer 152 A-real-clip 0.15
khq Koyra Chiini 39 B-graph
kia Kim 49 B-graph
kij Kilivila 38 B-graph
kik Kikuyu 39 B-graph
kin Kinyarwanda 141 B-graph
kir Kyrgyz 101 A-real-clip 0.06
kjb Q'anjob'al 51 B-graph
kje Kisar 30 B-graph
kjg Khmu 37 B-graph
kjh Khakas 49 B-graph
kki Kagulu 32 B-graph
kkj Kako 44 B-graph
kle Kulung (Nepal) 65 B-graph
klu Klao 53 B-graph
klv Maskelynes 44 B-graph
klw Tado 30 B-graph
kma Konni 35 B-graph
kmd Majukayang Kalinga 40 B-graph
kml Tanudan Kalinga 35 B-graph
kmr-script_arabic Northern Kurdish — arabic 41 B-graph
kmr-script_cyrillic Northern Kurdish — cyrillic 38 B-graph
kmr-script_latin Northern Kurdish — latin 40 B-graph
kmu Kanite 24 B-graph
knb Lubuagan Kalinga 45 B-graph
kne Kankanaey 37 B-graph
knf Mankanya 35 B-graph
knj Western Kanjobal 40 B-graph
knk Kuranko 30 B-graph
kno Kono (Sierra Leone) 28 B-graph
kog Cogui 48 B-graph
kor Korean 1330 A-plausible 0.20
kpq Korupun-Sela 37 B-graph
kps Tehit 31 B-graph
kpv Komi-Zyrian 43 B-graph
kpy Koryak 42 B-graph
kpz Kupsabiny 29 B-graph
kqe Kalagan 38 B-graph
kqp Kimré 36 B-graph
kqr Kimaragang 46 B-graph
kqy Koorete 178 B-graph
krc Karachay-Balkar 40 B-graph
kri Krio 33 B-graph
krj Kinaray-a 42 B-graph
krl Karelian 34 B-graph
krr Krung 61 B-graph
krs Gbaya (Sudan) 54 B-graph
kru Kurukh 64 B-graph
ksb Shambala 34 B-graph
ksr Borong 43 B-graph
kss Southern Kisi 41 B-graph
ktb Kambaata 188 B-graph
ktj Plapo Krumen 38 B-graph
kub Kutep 48 B-graph
kue Kuman (Papua New Guinea) 39 B-graph
kum Kumyk 42 B-graph
kus Kusaal 31 B-graph
kvn Border Kuna 49 B-graph
kvw Wersing 29 B-graph
kwd Kwaio 33 B-graph
kwf Kwara'ae 36 B-graph
kwi Awa-Cuaiquer 46 B-graph
kxc Konso 147 B-graph
kxf Manumanaw Karen 41 B-graph
kxm Northern Khmer 50 B-graph
kxv Kuvi 45 B-graph
kyb Butbut Kalinga 40 B-graph
kyc Kyaka 40 B-graph
kyf Kouya 35 B-graph
kyg Keyagana 23 B-graph
kyo Kelon 32 B-graph
kyq Kenga 35 B-graph
kyu Western Kayah 42 B-graph
kyz Kayabí 41 B-graph
kzf Da'a Kaili 30 B-graph
lac Lacandon 40 B-graph
laj Lango (Uganda) 31 B-graph
lam Lamba 32 B-graph
lao Lao 123 A-plausible 0.06
las Lama (Togo) 35 B-graph
lat Latin 32 B-graph
lav Latvian 75 A-plausible 0.02
law Lauje 33 B-graph
lbj Ladakhi 60 B-graph
lbw Tolaki 28 B-graph
lcp Western Lawa 45 B-graph
lee Lyélé 67 B-graph
lef Lelemi 40 B-graph
lem Nomaande 37 B-graph
lew Ledo Kaili 37 B-graph
lex Luang 30 B-graph
lgg Lugbara 37 B-graph
lgl Wala 33 B-graph
lhu Lahu 35 B-graph
lia West-Central Limba 31 B-graph
lid Nyindrou 38 B-graph
lif Limbu 53 B-graph
lin Lingala 81 A-real-clip 0.01
lip Sekpele 47 B-graph
lis Lisu 58 B-graph
lit Lithuanian 71 A-plausible 0.07
lje Rampi 38 B-graph
ljp Lampung Api 38 B-graph
llg Lole 29 B-graph
lln Lele (Chad) 39 B-graph
lme Pévé 40 B-graph
lnd Lundayeh 39 B-graph
lns Lamnso' 51 B-graph
lob Lobi 45 B-graph
lok Loko 32 B-graph
lom Loma (Liberia) 60 B-graph
lon Malawi Lomwe 40 B-graph
loq Lobala 38 B-graph
lsi Lashi 42 B-graph
lsm Saamia 36 B-graph
ltz Luxembourgish 78 A-plausible 0.11
luc Aringa 62 B-graph
lug Ganda 79 A-plausible 0.04
luo Luo (Kenya and Tanzania) 68 A-real-clip 0.15
lwo Luwo 31 B-graph
lww Lewo 36 B-graph
lzz Laz 37 B-graph
maa-dialect_sanantonio San Jerónimo Tecóatl Mazatec — dialect sanantonio 45 B-graph
maa-dialect_sanjeronimo San Jerónimo Tecóatl Mazatec — dialect sanjeronimo 44 B-graph
mad Madurese 37 B-graph
mag Magahi 72 B-graph
mah Marshallese 41 B-graph
mai Maithili 69 B-graph
maj Jalapa De Díaz Mazatec 39 B-graph
mak Makasar 34 B-graph
mal Malayalam 136 A-plausible 0.04
mam-dialect_central Mam — dialect central 47 B-graph
mam-dialect_northern Mam — dialect northern 51 B-graph
mam-dialect_southern Mam — dialect southern 35 B-graph
mam-dialect_western Mam — dialect western 42 B-graph
maq Chiquihuitlán Mazatec 38 B-graph
mar Marathi 146 A-plausible 0.04
maw Mampruli 33 B-graph
maz Central Mazahua 48 B-graph
mbb Western Bukidnon Manobo 38 B-graph
mbc Macushi 57 B-graph
mbh Mangseng 39 B-graph
mbj Nadëb 50 B-graph
mbt Matigsalug Manobo 33 B-graph
mbu Mbula-Bwazza 64 B-graph
mbz Amoltepec Mixtec 37 B-graph
mca Maca 46 B-graph
mcb Machiguenga 36 B-graph
mcd Sharanahua 44 B-graph
mco Coatlán Mixe 46 B-graph
mcp Makaa 54 B-graph
mcq Ese 37 B-graph
mcu Cameroon Mambila 61 B-graph
mda Mada (Nigeria) 59 B-graph
mdf Moksha 39 B-graph
mdv Santa Lucía Monteverde Mixtec 41 B-graph
mdy Male (Ethiopia) 156 B-graph
med Melpa 39 B-graph
mee Mengen 28 B-graph
mej Meyah 35 B-graph
men Mende 34 B-graph
meq Merey 40 B-graph
met Mato 39 B-graph
mev Mano 53 B-graph
mfe Morisyen 34 B-graph
mfh Matal 42 B-graph
mfi Wandala 37 B-graph
mfk North Mofu 35 B-graph
mfq Moba 31 B-graph
mfy Mayo 45 B-graph
mfz Mabaan 34 B-graph
mgd Moru 43 B-graph
mge Mango 47 B-graph
mgh Makhuwa-Meetto 36 B-graph
mgo Metaʼ 54 B-graph
mhi Ma'di 32 B-graph
mhr Eastern Mari 45 B-graph
mhu Digaro-Mishmi 37 B-graph
mhx Maru 38 B-graph
mhy Ma'anyan 36 B-graph
mib Atatláhuca Mixtec 46 B-graph
mie Ocotepec Mixtec 42 B-graph
mif Mofu-Gudur 34 B-graph
mih Chayuco Mixtec 41 B-graph
mil Peñoles Mixtec 53 B-graph
mim Alacatlatzala Mixtec 40 B-graph
min Minangkabau 38 B-graph
mio Pinotepa Nacional Mixtec 38 B-graph
mip Apasco-Apoala Mixtec 43 B-graph
miq Mískito 44 B-graph
mit Southern Puebla Mixtec 54 B-graph
miy Ayutla Mixtec 44 B-graph
miz Coatzospan Mixtec 53 B-graph
mjl Mandeali 66 B-graph
mjv Mannan 57 B-graph
mkd Macedonian 97 A-plausible 0.02
mkl Mokole 51 B-graph
mkn Kupang Malay 34 B-graph
mlg Malagasy 48 B-graph
mlt Maltese 83 A-real-clip 0.11
mmg North Ambrym 35 B-graph
mnb Muna 28 B-graph
mnf Mundani 55 B-graph
mnk Mandinka 34 B-graph
mnw Mon 63 B-graph
mnx Manikion 27 B-graph
moa Mwan 35 B-graph
mog Mongondow 40 B-graph
mon Mongolian 100 A-plausible 0.10
mop Mopán Maya 47 B-graph
mor Moro 37 B-graph
mos Mossi 39 B-graph
mox Molima 39 B-graph
moz Mukulu 43 B-graph
mpg Marba 45 B-graph
mpm Yosondúa Mixtec 43 B-graph
mpp Migabac 40 B-graph
mpx Misima-Panaeati 34 B-graph
mqb Mbuko 47 B-graph
mqf Momuna 48 B-graph
mqj Mamasa 40 B-graph
mqn Moronene 34 B-graph
mri Māori 61 A-plausible 0.05
mrw Maranao 25 B-graph
msy Aruamu 41 B-graph
mtd Mualang 28 B-graph
mtj Moskona 35 B-graph
mto Totontepec Mixe 43 B-graph
muh Mündü 35 B-graph
mup Malvi 60 B-graph
mur Murle 39 B-graph
muv Muthuvan 50 B-graph
muy Muyang 51 B-graph
mvp Duri 31 B-graph
mwq Mün Chin 47 B-graph
mwv Mentawai 34 B-graph
mxb Tezoatlán Mixtec 50 B-graph
mxq Juquila Mixe 39 B-graph
mxt Jamiltepec Mixtec 40 B-graph
mxv Metlatónoc Mixtec 50 B-graph
mya Burmese 140 A-plausible 0.17
myb Mbay 43 B-graph
myk Mamara Senoufo 49 B-graph
myl Moma 31 B-graph
myv Erzya 40 B-graph
myx Masaaba 35 B-graph
myy Macuna 49 B-graph
mza Santa María Zacatepec Mixtec 53 B-graph
mzi Ixcatlán Mazatec 38 B-graph
mzj Manya 36 B-graph
mzk Nigeria Mambila 44 B-graph
mzm Mumuye 60 B-graph
mzw Deg 43 B-graph
nab Southern Nambikuára 44 B-graph
nag Naga Pidgin 40 B-graph
nan Min Nan Chinese 51 B-graph
nas Naasioi 36 B-graph
naw Nawuri 34 B-graph
nca Iyo 47 B-graph
nch Central Huasteca Nahuatl 41 B-graph
ncj Northern Puebla Nahuatl 36 B-graph
ncl Michoacán Nahuatl 38 B-graph
ncu Chumburung 34 B-graph
ndj Ndamba 30 B-graph
ndp Ndo 29 B-graph
ndv Ndut 38 B-graph
ndy Lutos 34 B-graph
ndz Ndogo 55 B-graph
neb Toura (Côte d'Ivoire) 50 B-graph
new Newari 67 B-graph
nfa Dhao 30 B-graph
nfr Nafaanra 35 B-graph
nga Ngbaka 47 B-graph
ngl Lomwe 26 B-graph
ngp Ngulu 30 B-graph
ngu Guerrero Nahuatl 39 B-graph
nhe Eastern Huasteca Nahuatl 37 B-graph
nhi Zacatlán-Ahuacatlán-Tepetzintla Nahuatl 40 B-graph
nhu Noone 48 B-graph
nhw Western Huasteca Nahuatl 40 B-graph
nhx Isthmus-Mecayapan Nahuatl 42 B-graph
nhy Northern Oaxaca Nahuatl 37 B-graph
nia Nias 37 B-graph
nij Ngaju 37 B-graph
nim Nilamba 34 B-graph
nin Ninzo 51 B-graph
nko Nkonya 39 B-graph
nlc Nalca 35 B-graph
nld Dutch 86 A-real-clip 0.04
nlg Gela 33 B-graph
nlk Ninia Yali 39 B-graph
nmz Nawdm 47 B-graph
nnb Nande 38 B-graph
nno Norwegian Nynorsk 32 B-graph
nnq Ngindo 29 B-graph
nnw Southern Nuni 57 B-graph
noa Woun Meu 51 B-graph
nob Norwegian Bokmål 75 A-plausible 0.10
nod Northern Thai 69 B-graph
nog Nogai 43 B-graph
not Nomatsiguenga 44 B-graph
npi Nepali (individual language) 124 A-real-clip 0.01
npl Southeastern Puebla Nahuatl 40 B-graph
npy Napu 29 B-graph
nso Northern Sotho 75 A-plausible 0.03
nst Tase Naga 30 B-graph
nsu Sierra Negra Nahuatl 44 B-graph
ntm Nateni 45 B-graph
ntr Delo 31 B-graph
nuj Nyole 33 B-graph
nus Nuer 37 B-graph
nuz Tlamacazapa Nahuatl 37 B-graph
nwb Nyabwa 36 B-graph
nxq Naxi 32 B-graph
nya Nyanja 74 A-real-clip 0.07
nyf Giryama 32 B-graph
nyn Nyankole 31 B-graph
nyo Nyoro 31 B-graph
nyy Nyakyusa-Ngonde 48 B-graph
nzi Nzima 34 B-graph
obo Obo Manobo 33 B-graph
oci Occitan 81 A-plausible 0.10
ojb-script_latin Northwestern Ojibwa — latin 29 B-graph
ojb-script_syllabics Northwestern Ojibwa — syllabics 159 B-graph
oku Oku 52 B-graph
old Mochi 35 B-graph
omw South Tairora 34 B-graph
onb Lingao 30 B-graph
ood Tohono O'odham 33 B-graph
orm Oromo 65 A-plausible 0.17
ory Odia (individual language) 134 A-plausible 0.08
oss Ossetic 37 B-graph
ote Mezquital Otomi 43 B-graph
otq Querétaro Otomi 40 B-graph
ozm Koonzime 64 B-graph
pab Parecís 53 B-graph
pad Paumarí 54 B-graph
pag Pangasinan 35 B-graph
pam Pampanga 36 B-graph
pan Punjabi 95 A-real-clip 0.02
pao Northern Paiute 39 B-graph
pap Papiamento 54 B-graph
pau Palauan 43 B-graph
pbb Páez 44 B-graph
pbc Patamona 45 B-graph
pbi Parkwa 39 B-graph
pce Ruching Palaung 42 B-graph
pcm Nigerian Pidgin 39 B-graph
peg Pengo 41 B-graph
pez Eastern Penan 36 B-graph
pib Yine 27 B-graph
pil Yom 43 B-graph
pir Piratapuyo 47 B-graph
pis Pijin 39 B-graph
pjt Pitjantjatjara 48 B-graph
pkb Pokomo 38 B-graph
pls San Marcos Tlacoyalco Popoloca 48 B-graph
plw Brooke's Point Palawano 34 B-graph
pmf Pamona 30 B-graph
pny Pinyin 58 B-graph
poh-dialect_eastern Poqomchi' — dialect eastern 40 B-graph
poh-dialect_western Poqomchi' — dialect western 32 B-graph
poi Highland Popoluca 42 B-graph
pol Polish 74 A-plausible 0.01
por Portuguese 82 A-plausible 0.04
poy Pogolo 30 B-graph
ppk Uma 31 B-graph
pps San Luís Temalacayuca Popoloca 49 B-graph
prf Paranan 39 B-graph
prk Parauk 35 B-graph
prt Phai 58 B-graph
pse Central Malay 27 B-graph
pss Kaulong 27 B-graph
ptu Bambam 31 B-graph
pui Puinave 43 B-graph
pus Pashto 139 A-plausible 0.43
pwg Gapapaiwa 41 B-graph
pww Pwo Northern Karen 49 B-graph
pxm Quetzaltepec Mixe 40 B-graph
qub Huallaga Huánuco Quechua 44 B-graph
quc-dialect_central Kʼicheʼ — dialect central 40 B-graph
quc-dialect_east Kʼicheʼ — dialect east 46 B-graph
quc-dialect_north Kʼicheʼ — dialect north 38 B-graph
quf Lambayeque Quechua 38 B-graph
quh South Bolivian Quechua 46 B-graph
qul North Bolivian Quechua 41 B-graph
quw Tena Lowland Quichua 47 B-graph
quy Ayacucho Quechua 39 A-native-parity
quz Cusco Quechua 40 B-graph
qvc Cajamarca Quechua 45 B-graph
qve Eastern Apurímac Quechua 43 B-graph
qvh Huamalíes-Dos de Mayo Huánuco Quechua 44 B-graph
qvm Margos-Yarowilca-Lauricocha Quechua 44 B-graph
qvn North Junín Quechua 45 B-graph
qvo Napo Lowland Quechua 39 B-graph
qvs San Martín Quechua 34 B-graph
qvw Huaylla Wanca Quechua 49 B-graph
qvz Northern Pastaza Quichua 38 B-graph
qwh Huaylas Ancash Quechua 40 B-graph
qxh Panao Huánuco Quechua 45 B-graph
qxl Salasaca Highland Quichua 41 B-graph
qxn Northern Conchucos Ancash Quechua 44 B-graph
qxo Southern Conchucos Ancash Quechua 42 B-graph
qxr Cañar Highland Quichua 39 B-graph
rah Rabha 43 B-graph
rai Ramoaaina 35 B-graph
rap Rapanui 40 B-graph
rav Sampang 59 B-graph
raw Rawang 55 B-graph
rej Rejang 36 B-graph
rel Rendille 32 B-graph
rgu Ringgou 27 B-graph
rhg Rohingya 38 B-graph
rif-script_arabic Riffian — arabic 45 B-graph
rif-script_latin Riffian — latin 44 B-graph
ril Riang Lang 30 B-graph
rim Nyaturu 33 B-graph
rjs Rajbanshi 65 B-graph
rkt Rangpuri 66 B-graph
rmc-script_cyrillic Carpathian Romani — cyrillic 40 B-graph
rmc-script_latin Carpathian Romani — latin 44 B-graph
rmo Sinte Romani 31 B-graph
rmy-script_cyrillic Vlax Romani — cyrillic 40 B-graph
rmy-script_latin Vlax Romani — latin 31 B-graph
rng Ronga 47 B-graph
rnl Ranglong 39 B-graph
roh-dialect_sursilv Romansh — dialect sursilv 40 B-graph
roh-dialect_vallader Romansh — dialect vallader 43 B-graph
rol Romblomanon 49 B-graph
ron Romanian 83 A-real-clip 0.15
rop Kriol 26 B-graph
rro Waima 35 B-graph
rub Gungu 39 B-graph
ruf Luguru 35 B-graph
rug Roviana 28 B-graph
run Rundi 32 B-graph
rus Russian 95 A-plausible 0.03
sab Buglere 40 B-graph
sag Sango 43 B-graph
sah Yakut 50 B-graph
saj Sahu 33 B-graph
saq Samburu 39 B-graph
sas Sasak 33 B-graph
sat Santali 39 B-graph
sba Ngambay 53 B-graph
sbd Southern Samo 54 B-graph
sbl Botolan Sambal 32 B-graph
sbp Sangu 30 B-graph
sch Sakachep 42 B-graph
sck Sadri 63 B-graph
sda Toraja-Sa'dan 32 B-graph
sea Semai 42 B-graph
seh Sena 32 B-graph
ses Koyraboro Senni 39 B-graph
sey Secoya 40 B-graph
sgb Mag-antsi Ayta 45 B-graph
sgj Surgujia 53 B-graph
sgw Sebat Bet Gurage 248 B-graph
shi Tachelhit 39 B-graph
shk Shilluk 50 B-graph
shn Shan 47 B-graph
sho Shanga 51 B-graph
shp Shipibo-Conibo 40 B-graph
sid Sidamo 41 B-graph
sig Paasaal 36 B-graph
sil Tumulung Sisaala 39 B-graph
sja Epena 49 B-graph
sjm Mapun 34 B-graph
sld Sissala 49 B-graph
slk Slovak 77 A-plausible 0.01
slu Selaru 30 B-graph
slv Slovenian 72 A-plausible 0.05
sml Central Sama 33 B-graph
smo Samoan 29 B-graph
sna Shona 65 A-real-clip 0.05
snd Sindhi 128 A-plausible 0.04
sne Bau Bidayuh 43 B-graph
snn Siona 44 B-graph
snp Siane 27 B-graph
snw Selee 40 B-graph
som Somali 73 A-plausible 0.25
soy Miyobe 49 B-graph
spa Spanish 243 A-plausible 0.00
spp Supyire Senoufo 54 B-graph
spy Sabaot 33 B-graph
sqi Albanian 37 B-graph
sri Siriano 50 B-graph
srm Saramaccan 40 B-graph
srn Sranan Tongo 38 B-graph
srp-script_cyrillic Serbian — cyrillic 35 B-graph
srp-script_latin Serbian — latin 96 B-graph
srx Sirmauri 67 B-graph
stn Owa 31 B-graph
stp Southeastern Tepehuan 31 B-graph
suc Western Subanon 29 B-graph
suk Sukuma 40 B-graph
sun Sundanese 41 B-graph
sur Mwaghavul 42 B-graph
sus Susu 30 B-graph
suv Puroik 36 B-graph
suz Sunwar 70 B-graph
swe Swedish 74 A-plausible 0.02
swh Swahili (individual language) 79 A-real-clip 0.12
sxb Suba 35 B-graph
sxn Sangir 44 B-graph
sya Siang 29 B-graph
syl Sylheti 35 B-graph
sza Semelai 29 B-graph
tac Lowland Tarahumara 37 B-graph
taj Eastern Tamang 66 B-graph
tam Tamil 120 A-plausible 0.04
tao Yami 29 B-graph
tap Taabwa 39 B-graph
taq Tamasheq 41 B-graph
tat Tatar 57 B-graph
tav Tatuyo 46 B-graph
tbc Takia 40 B-graph
tbg North Tairora 43 B-graph
tbk Calamian Tagbanwa 47 B-graph
tbl Tboli 39 B-graph
tby Tabaru 41 B-graph
tbz Ditammari 48 B-graph
tca Ticuna 65 B-graph
tcc Datooga 29 B-graph
tcs Torres Strait Creole 25 B-graph
tcz Thado Chin 46 B-graph
tdj Tajio 30 B-graph
ted Tepo Krumen 36 B-graph
tee Huehuetla Tepehua 37 B-graph
tel Telugu 125 A-real-clip 0.07
tem Timne 33 B-graph
teo Teso 30 B-graph
ter Tereno 42 B-graph
tes Tengger 29 B-graph
tew Tewa (USA) 51 B-graph
tex Tennet 35 B-graph
tfr Teribe 55 B-graph
tgj Tagin 37 B-graph
tgk Tajik 106 A-plausible 0.01
tgl Filipino 82 A-plausible 0.03
tgo Sudest 36 B-graph
tgp Tangoa 46 B-graph
tha Thai 133 A-plausible 0.10
thk Tharaka 31 B-graph
thl Dangaura Tharu 67 B-graph
tih Timugon Murut 35 B-graph
tik Tikar 56 B-graph
tir Tigrinya 231 B-graph
tkr Tsakhur 40 B-graph
tlb Tobelo 42 B-graph
tlj Talinga-Bwisi 33 B-graph
tly Talysh 43 B-graph
tmc Tumak 37 B-graph
tmf Toba-Maskoy 43 B-graph
tna Tacana 40 B-graph
tng Tobanga 39 B-graph
tnk Kwamera 36 B-graph
tnn North Tanna 30 B-graph
tnp Whitesands 31 B-graph
tnr Ménik 40 B-graph
tnt Tontemboan 32 B-graph
tob Toba 40 B-graph
toc Coyutla Totonac 40 B-graph
toh Gitonga 35 B-graph
tom Tombulu 31 B-graph
tos Highland Totonac 43 B-graph
tpi Tok Pisin 40 B-graph
tpm Tampulma 33 B-graph
tpp Pisaflores Tepehua 48 B-graph
tpt Tlachichilco Tepehua 44 B-graph
trc Copala Triqui 44 B-graph
tri Trió 41 B-graph
trn Trinitario 40 B-graph
trs Chicahuaxtla Triqui 56 B-graph
tso Tsonga 33 B-graph
tsz Purepecha 39 B-graph
ttc Tektiteko 40 B-graph
tte Bwanabwana 31 B-graph
ttq-script_tifinagh Tawallammat Tamajaq — tifinagh 29 B-graph
tue Tuyuca 49 B-graph
tuf Central Tunebo 40 B-graph
tuk-script_arabic Turkmen — arabic 44 B-graph
tuk-script_latin Turkmen — latin 39 B-graph
tuo Tucano 50 B-graph
tur Turkish 76 A-plausible 0.03
tvw Sedoa 32 B-graph
twb Western Tawbuid 34 B-graph
twe Tewa (Indonesia) 32 B-graph
twu Termanu 31 B-graph
txa Tombonuo 26 B-graph
txq Tii 42 B-graph
txu Kayapó 46 B-graph
tye Kyanga 51 B-graph
tzh-dialect_bachajon Tzeltal — dialect bachajon 39 B-graph
tzh-dialect_tenejapa Tzeltal — dialect tenejapa 40 B-graph
tzj-dialect_eastern Tz'utujil — dialect eastern 40 B-graph
tzj-dialect_western Tz'utujil — dialect western 40 B-graph
tzo-dialect_chamula Tzotzil — dialect chamula 39 B-graph
tzo-dialect_chenalho Tzotzil — dialect chenalho 39 B-graph
ubl Buhi'non Bikol 40 B-graph
ubu Umbu-Ungu 31 B-graph
udm Udmurt 45 B-graph
udu Uduk 37 B-graph
uig-script_arabic Uyghur — arabic 46 B-graph
uig-script_cyrillic Uyghur — cyrillic 51 B-graph
ukr Ukrainian 98 A-plausible 0.04
umb Umbundu 75 A-plausible 0.03
unr Mundari 57 B-graph
upv Uripiv-Wala-Rano-Atchin 34 B-graph
ura Urarina 29 B-graph
urb Urubú-Kaapor 48 B-graph
urd-script_arabic Urdu — arabic 127 B-graph
urd-script_devanagari Urdu — devanagari 74 B-graph
urd-script_latin Urdu — latin 50 B-graph
urk Urak Lawoi' 53 B-graph
urt Urat 42 B-graph
ury Orya 45 B-graph
usp Uspanteco 38 B-graph
uzb-script_cyrillic Uzbek — cyrillic 50 B-graph
uzb-script_latin Uzbek — latin 113 B-graph
vag Vagla 45 B-graph
vid Vidunda 29 B-graph
vie Vietnamese 137 A-plausible 0.12
vif Vili 33 B-graph
vmw Makhuwa 32 B-graph
vmy Ayautla Mazatec 38 B-graph
vot Votic 35 B-graph
vun Vunjo 33 B-graph
vut Vute 54 B-graph
wal-script_ethiopic Wolaytta — ethiopic 181 B-graph
wal-script_latin Wolaytta — latin 33 B-graph
wap Wapishana 46 B-graph
war Waray 45 B-graph
waw Waiwai 37 B-graph
way Wayana 32 B-graph
wba Warao 40 B-graph
wlo Wolio 31 B-graph
wlx Wali (Ghana) 37 B-graph
wmw Mwani 44 B-graph
wob Wè Northern 34 B-graph
wol Wolof 87 A-plausible 0.13
wsg Adilabad Gondi 45 B-graph
wwa Waama 39 B-graph
xal Kalmyk 52 B-graph
xdy Malayic Dayak 30 B-graph
xed Hdi 33 B-graph
xer Xerénte 57 B-graph
xho Xhosa 76 A-plausible 0.03
xmm Manado Malay 36 B-graph
xnj Ngoni (Tanzania) 29 B-graph
xnr Kangri 64 B-graph
xog Soga 29 B-graph
xon Konkomba 32 B-graph
xrb Eastern Karaboro 37 B-graph
xsb Sambal 45 B-graph
xsm Kasem 38 B-graph
xsr Sherpa 60 B-graph
xsu Sanumá 54 B-graph
xta Alcozauca Mixtec 45 B-graph
xtd Diuxi-Tilantongo Mixtec 42 B-graph
xte Ketengban 39 B-graph
xtm Magdalena Peñasco Mixtec 44 B-graph
xtn Northern Tlaxiaco Mixtec 38 B-graph
xua Alu Kurumba 49 B-graph
xuo Kuo 54 B-graph
yaa Yaminahua 40 B-graph
yad Yagua 33 B-graph
yal Yalunka 32 B-graph
yam Yamba 44 B-graph
yao Yao 31 B-graph
yas Nugunu (Cameroon) 34 B-graph
yat Yambeta 38 B-graph
yaz Lokaa 38 B-graph
yba Yala 39 B-graph
ybb Yemba 49 B-graph
ycl Lolopo 41 B-graph
ycn Yucuna 44 B-graph
yea Ravula 50 B-graph
yka Yakan 35 B-graph
yli Angguruk Yali 30 B-graph
yor Yoruba 94 A-real-clip 0.18
yre Yaouré 35 B-graph
yua Yucateco 38 B-graph
yue-script_traditional Cantonese — traditional 2299 B-graph
yuz Yuracare 52 B-graph
yva Yawa 31 B-graph
zaa Sierra de Juárez Zapotec 51 B-graph
zab Western Tlacolula Valley Zapotec 40 B-graph
zac Ocotlán Zapotec 38 B-graph
zad Cajonos Zapotec 43 B-graph
zae Yareni Zapotec 40 B-graph
zai Isthmus Zapotec 40 B-graph
zam Miahuatlán Zapotec 44 B-graph
zao Ozolotepec Zapotec 38 B-graph
zaq Aloápam Zapotec 51 B-graph
zar Rincón Zapotec 43 B-graph
zas Santo Domingo Albarradas Zapotec 41 B-graph
zav Yatzachi Zapotec 42 B-graph
zaw Mitla Zapotec 47 B-graph
zca Coatecas Altas Zapotec 43 B-graph
zga Kinga 32 B-graph
zim Mesme 45 B-graph
ziw Zigula 29 B-graph
zlm Malay (individual language) 74 A-plausible 0.00
zmz Mbandja 61 B-graph
zne Zande (individual language) 41 B-graph
zos Francisco León Zoque 41 B-graph
zpc Choapan Zapotec 42 B-graph
zpg Guevea De Humboldt Zapotec 49 B-graph
zpi Santa María Quiegolani Zapotec 40 B-graph
zpl Lachixío Zapotec 38 B-graph
zpm Mixtepec Zapotec 44 B-graph
zpo Amatlán Zapotec 50 B-graph
zpt San Vicente Coatlán Zapotec 41 B-graph
zpu Yalálag Zapotec 40 B-graph
zpz Texmelucan Zapotec 40 B-graph
ztq Quioquitani-Quierí Zapotec 39 B-graph
zty Yatee Zapotec 42 B-graph
zul Zulu 75 A-plausible 0.05
zyb Yongbei Zhuang 34 B-graph
zyp Zyphe Chin 44 B-graph
zza Zaza 38 B-graph

Caveats — read before you use this

  • This is a community fallback. A dedicated ASR fine-tune for your language always beats MMS. Use this only when nothing else exists.
  • MMS quality varies a lot by language, and its training data skews to narrow domains, largely religious-text recordings.
  • Output is character-level: no punctuation, no casing.
  • A B-graph language is untested on speech. It runs; nobody checked what it says.
  • If a dedicated model appears for your language, prefer it.

License and attribution

cc-by-nc-4.0, inherited from facebook/mms-1b-all. Non-commercial use only.

Meta AI, MMS project — Scaling Speech Technology to 1000+ Languages, arXiv:2305.13516.

Downloads last month
206
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for OpenVoiceOS/mms-1b-all-onnx

Quantized
(5)
this model

Collections including OpenVoiceOS/mms-1b-all-onnx

Paper for OpenVoiceOS/mms-1b-all-onnx