Many-to-English: Data v2 and Statistics

Due to license and copyright issues, we are unable to distribute the v2 data. However, you may freshly download all data using mtdata:

pip install mtdata==0.3.4
wget https://github.com/thammegowda/016-many-eng-v2/blob/2bf3e75ce/data/mtdata.recipes.yml
mtdata get-recipe -ri mul-eng-v2 -o mul-eng-v2

For dataset preparation, checkout instructions and scripts at github.com/thammegowda/016-many-eng-v2/tree/main/data

Figure 1. V2 Statistics (Get PDF)

Table 1. Many-English V2 training data statistics (Get TSV)
#	ISO 639-3	Name	Sentences	Source Toks	English Toks
		Total	2,314,289,643	36,842,400,917	37,303,550,534
1	spa	Spanish	253,668,574	5,279,377,335	4,919,556,610
2	deu	German	177,975,226	3,001,483,404	3,237,466,426
3	fra	French	162,248,222	3,884,645,161	3,429,824,104
4	ita	Italian	118,596,082	1,895,905,711	1,861,669,411
5	por	Portuguese	116,723,887	1,634,277,485	1,660,940,634
6	rus	Russian	80,564,317	1,247,584,821	1,355,254,223
7	ara	Arabic	79,055,464	1,235,068,770	1,411,260,178
8	pol	Polish	78,923,932	908,381,377	1,050,278,687
9	ces	Czech	72,609,894	852,935,694	980,963,507
10	nld	Dutch	69,859,259	1,055,952,154	1,092,597,326
11	zho	Chinese	64,117,920	1,663,029,087	1,058,219,295
12	tur	Turkish	62,206,228	561,304,806	704,879,879
13	ron	Romanian	61,195,111	762,376,580	766,302,572
14	ell	Modern Greek (1453-)	60,037,778	802,595,601	867,222,424
15	hun	Hungarian	58,950,748	637,739,268	750,176,749
16	fin	Finnish	53,789,771	577,815,600	805,043,805
17	bul	Bulgarian	53,463,643	620,500,266	672,212,878
18	swe	Swedish	49,398,648	698,791,704	791,782,502
19	dan	Danish	45,130,723	736,882,597	791,521,162
20	hrv	Croatian	39,188,893	413,531,244	487,807,222
21	heb	Hebrew	32,441,143	314,082,673	385,611,770
22	srp	Serbian	31,636,021	301,614,880	363,921,637
23	slv	Slovenian	29,339,686	388,623,228	451,821,921
24	jpn	Japanese	28,981,617	432,653,502	363,742,586
25	ind	Indonesian	25,971,252	289,945,425	307,157,909
26	est	Estonian	25,959,843	346,264,437	448,536,310
27	slk	Slovak	25,275,005	400,090,625	449,674,253
28	nor	Norwegian	24,622,569	393,029,377	425,300,573
29	hin	Hindi	19,565,950	380,660,603	352,369,524
30	vie	Vietnamese	19,154,811	345,867,441	275,251,843
31	kor	Korean	18,082,581	412,593,911	225,083,933
32	lit	Lithuanian	18,056,267	316,056,829	374,533,537
33	fas	Persian	17,264,264	215,055,984	211,627,357
34	lav	Latvian	16,002,864	298,928,041	350,828,193
35	tha	Thai	14,828,467	254,248,107	227,551,101
36	ukr	Ukrainian	13,731,503	211,778,190	235,265,464
37	ben	Bengali	12,966,849	169,193,764	183,512,421
38	bos	Bosnian	12,641,559	110,530,611	134,779,963
39	cat	Catalan	9,326,671	186,856,073	170,483,544
40	mal	Malayalam	8,364,447	87,317,212	129,515,625
41	tgl	Tagalog	7,768,323	80,270,568	74,870,808
42	msa	Malay	7,310,950	101,226,403	103,678,883
43	tam	Tamil	7,207,971	81,504,209	106,044,491
44	tel	Telugu	7,130,362	82,243,282	108,460,238
45	mlt	Maltese	6,237,081	201,765,258	158,648,210
46	mkd	Macedonian	6,057,790	80,214,670	85,781,252
47	sqi	Albanian	5,256,915	77,999,548	75,990,908
48	isl	Icelandic	5,082,666	80,124,119	88,677,794
49	pan	Panjabi	4,994,289	108,362,544	102,168,503
50	guj	Gujarati	4,939,763	74,080,744	83,828,300
51	mar	Marathi	4,906,647	58,968,852	69,396,973
52	kan	Kannada	4,575,413	40,771,254	54,676,162
53	swa	Swahili	3,205,843	42,560,576	45,279,169
54	afr	Afrikaans	2,809,410	53,573,711	51,376,322
55	urd	Urdu	2,720,004	67,312,118	56,632,409
56	eus	Basque	2,242,400	26,372,037	33,074,627
57	kat	Georgian	1,999,450	27,458,248	35,491,982
58	aze	Azerbaijani	1,883,613	26,100,570	30,740,334
59	sin	Sinhala	1,793,201	22,108,819	27,173,749
60	nob	Norwegian Bokmål	1,726,761	31,583,907	35,794,508
61	jav	Javanese	1,587,444	8,848,159	9,072,046
62	bel	Belarusian	1,479,649	25,891,752	28,618,056
63	hbs	Serbo-Croatian	1,454,703	27,548,866	31,028,525
64	glg	Galician	1,437,243	26,686,128	26,336,449
65	hye	Armenian	1,419,203	23,287,198	26,485,597
66	epo	Esperanto	1,388,826	22,067,450	23,058,245
67	mlg	Malagasy	1,231,046	25,930,950	23,469,140
68	ceb	Cebuano	1,218,273	24,245,069	21,771,595
69	xho	Xhosa	1,201,422	15,897,253	20,904,940
70	pus	Pushto	1,196,081	16,856,328	15,727,700
71	zul	Zulu	1,115,794	16,024,047	20,707,959
72	ori	Oriya	1,092,528	13,064,193	15,012,212
73	amh	Amharic	1,027,344	15,494,687	20,578,235
74	cym	Welsh	1,000,739	15,843,410	15,172,492
75	nep	Nepali	995,864	13,341,958	16,474,036
76	kaz	Kazakh	944,584	11,747,980	14,094,209
77	nya	Nyanja	925,583	15,384,350	17,441,340
78	ilo	Iloko	919,162	18,277,002	17,202,744
79	mya	Burmese	900,544	25,948,094	18,772,742
80	tsn	Tswana	866,529	20,811,868	15,368,526
81	sna	Shona	863,878	13,153,931	17,144,608
82	hil	Hiligaynon	825,933	17,910,874	15,622,829
83	tso	Tsonga	778,008	17,769,145	14,732,648
84	mon	Mongolian	765,300	9,272,762	10,680,787
85	hat	Haitian	759,321	14,435,753	12,916,497
86	iku	Inuktitut	746,626	8,449,431	17,190,991
87	hau	Hausa	663,084	11,648,689	10,824,093
88	ewe	Ewe	599,479	13,025,825	11,330,365
89	yor	Yoruba	596,112	16,637,961	11,174,615
90	khm	Khmer	593,391	13,924,064	10,119,979
91	nso	Pedi	587,885	14,141,122	10,830,977
92	ibo	Igbo	579,217	13,518,003	10,722,100
93	lin	Lingala	569,608	11,208,047	10,481,908
94	tgk	Tajik	561,689	8,382,627	9,265,848
95	tah	Tahitian	559,201	16,938,664	10,752,789
96	srn	Sranan Tongo	556,794	14,271,952	10,838,516
97	twi	Twi	545,891	11,491,836	10,266,119
98	kir	Kirghiz	528,368	7,405,988	9,203,721
99	som	Somali	526,424	7,487,392	8,650,726
100	kin	Kinyarwanda	516,672	8,987,376	9,695,846
101	sun	Sundanese	504,253	6,283,228	6,573,601
102	bis	Bislama	486,314	12,213,952	9,135,441
103	gle	Irish	471,263	10,281,209	9,558,910
104	bcl	Central Bikol	469,102	10,344,866	9,067,112
105	loz	Lozi	419,140	9,650,373	7,949,230
106	gaa	Ga	415,709	9,417,753	7,928,833
107	tat	Tatar	393,396	6,333,739	7,675,820
108	tpi	Tok Pisin	389,302	9,260,948	7,207,274
109	bem	Bemba (Zambia)	387,645	6,618,150	7,222,344
110	pap	Papiamento	387,566	8,266,408	7,260,620
111	smo	Samoan	369,918	9,419,838	6,998,244
112	run	Rundi	367,844	6,604,320	6,874,435
113	fij	Fijian	363,957	7,971,843	6,780,823
114	nds	Low German	349,920	4,421,714	4,909,613
115	tir	Tigrinya	337,989	5,341,594	6,603,145
116	efi	Efik	336,539	7,394,238	6,333,038
117	ton	Tonga (Tonga Islands)	329,618	11,312,726	6,161,139
118	kur	Kurdish	323,271	7,380,867	7,139,218
119	lue	Luvale	321,193	4,775,044	6,062,455
120	asm	Assamese	298,723	3,693,735	4,398,208
121	toi	Tonga (Zambia)	296,174	4,411,522	5,502,863
122	lua	Luba-Lulua	295,047	5,558,950	5,556,044
123	guw	Gun	290,144	6,721,034	5,454,034
124	pag	Pangasinan	285,597	5,672,775	5,371,723
125	war	Waray (Philippines)	285,349	6,311,807	5,374,533
126	bre	Breton	273,188	2,735,231	2,447,672
127	pis	Pijin	266,652	5,374,116	5,030,924
128	sag	Sango	252,755	6,621,876	4,802,606
129	lug	Ganda	248,562	3,992,062	4,492,236
130	bsb	Brunei Bisaya	241,086	3,583,360	3,113,443
131	mah	Marshallese	236,556	5,814,572	4,474,163
132	tum	Tumbuka	233,890	3,645,348	4,356,059
133	hmo	Hiri Motu	232,428	4,847,883	4,342,356
134	oss	Ossetian	229,483	3,868,514	4,430,070
135	tll	Tetela	224,060	4,258,478	4,194,454
136	kqn	Kaonde	221,670	3,756,335	4,111,752
137	pon	Pohnpeian	220,925	4,440,396	4,202,464
138	niu	Niuean	217,182	5,476,212	4,017,789
139	iso	Isoko	216,873	4,945,777	4,051,792
140	lat	Latin	216,432	3,110,815	4,429,358
141	yap	Yapese	215,210	6,304,624	4,108,322
142	umb	Umbundu	213,522	4,010,262	3,945,677
143	chk	Chuukese	210,398	4,416,540	4,055,497
144	kon	Kongo	210,169	4,457,644	3,902,525
145	kal	Kalaallisut	209,623	2,402,283	3,936,525
146	ven	Venda	206,815	4,579,633	3,815,390
147	gil	Gilbertese	205,404	4,801,402	3,901,907
148	oci	Occitan (Post 1500)	205,314	4,004,337	3,929,607
149	lub	Luba-Katanga	199,037	3,563,612	3,749,988
150	mri	Maori	195,178	4,711,991	3,990,738
151	fry	Western Frisian	195,005	2,995,668	3,658,550
152	zne	Zande (Individual)	191,586	4,426,708	3,609,304
153	crs	Seselwa Creole French	191,197	3,885,810	3,543,049
154	lus	Lushai	189,473	4,329,926	3,547,696
155	mos	Mossi	188,023	4,740,841	3,523,787
156	nno	Norwegian Nynorsk	187,835	1,668,127	1,690,134
157	tiv	Tiv	185,919	4,840,223	3,481,715
158	mfe	Morisyen	183,172	4,103,579	3,377,373
159	orm	Oromo	181,306	2,838,514	3,040,872
160	lao	Lao	179,072	3,181,292	3,138,522
161	tvl	Tuvalu	174,065	5,030,740	3,314,644
162	kwy	San Salvador Kongo	171,939	2,989,433	3,133,212
163	yua	Yucateco	169,246	3,537,319	3,303,093
164	uzb	Uzbek	165,034	2,609,380	2,820,005
165	wls	Wallisian	155,683	4,014,401	2,877,923
166	zai	Isthmus Zapotec	147,137	2,739,592	2,737,032
167	gug	Paraguayan Guaraní	144,878	2,159,687	2,752,993
168	aym	Aymara	143,522	1,980,996	2,743,295
169	bci	Baoulé	143,225	3,706,794	2,600,991
170	tzo	Tzotzil	140,931	3,005,279	2,679,131
171	ssw	Swati	138,797	1,826,677	2,377,984
172	luo	Luo (Kenya And Tanzania)	137,861	2,619,113	2,505,480
173	lun	Lunda	135,471	1,866,210	2,483,887
174	que	Quechua	134,477	1,742,305	2,547,859
175	rnd	Ruund	134,093	2,453,057	2,446,620
176	quz	Cusco Quechua	128,347	1,657,901	2,460,850
177	tuk	Turkmen	125,910	1,771,066	2,278,843
178	wal	Wolaytta	121,889	1,889,023	2,322,586
179	nyk	Nyaneka	116,786	1,757,830	2,134,339
180	quy	Ayacucho Quechua	114,510	1,410,901	2,173,084
181	tdt	Tetun Dili	112,319	2,387,269	2,103,986
182	bzs	Brazilian Sign Language	111,833	2,058,578	2,068,712
183	ltz	Luxembourgish	109,923	1,582,213	1,947,571
184	kwn	Kwangali	107,197	1,715,529	1,938,333
185	wol	Wolof	102,164	1,012,345	939,929
186	swc	Congo Swahili	101,811	1,769,704	1,844,561
187	kua	Kuanyama	101,249	1,947,962	1,843,253
188	ndo	Ndonga	98,863	1,857,396	1,797,795
189	bak	Bashkir	96,353	1,337,669	1,733,722
190	kik	Kikuyu	94,649	1,719,465	1,733,973
191	snd	Sindhi	94,473	2,827,926	2,805,957
192	uig	Uighur	93,302	2,267,564	2,450,089
193	nzi	Nzima	93,246	1,805,503	1,683,130
194	div	Dhivehi	93,076	2,588,152	2,498,051
195	arg	Aragonese	91,536	1,806,009	1,691,482
196	kmb	Kimbundu	90,755	1,968,384	1,618,168
197	top	Papantla Totonac	87,046	1,346,132	1,619,234
198	tsc	Tswa	84,521	1,915,560	1,531,811
199	jsl	Japanese Sign Language	84,021	2,230,725	1,519,410
200	fao	Faroese	80,766	1,278,203	1,631,708
201	ise	Italian Sign Language	80,621	1,507,107	1,526,663
202	gym	Ngäbere	78,833	1,622,106	1,455,179
203	ach	Acoli	73,276	1,500,241	1,322,044
204	zlm	Malay (Individual)	72,869	1,142,624	1,368,006
205	vmw	Makhuwa	72,868	1,182,779	1,325,331
206	ful	Fulah	71,335	864,835	634,180
207	hne	Chhattisgarhi	70,961	444,623	372,650
208	chv	Chuvash	68,987	1,038,292	1,300,512
209	rar	Rarotongan	67,802	1,641,489	1,179,057
210	tog	Tonga (Nyasa)	67,217	1,054,854	1,227,043
211	bar	Bavarian	66,713	925,275	1,048,612
212	mco	Coatlán Mixe	66,159	1,098,536	1,259,613
213	pes	Iranian Persian	65,551	1,586,213	1,792,204
214	kek	Kekchí	63,382	2,237,930	1,839,837
215	ada	Adangme	63,016	1,668,455	1,128,094
216	aed	Argentine Sign Language	62,993	1,198,716	1,212,898
217	ckb	Central Kurdish	62,727	805,937	876,164
218	pck	Paite Chin	61,172	1,773,658	1,800,544
219	dje	Zarma	60,992	1,948,721	1,780,545
220	plt	Plateau Malagasy	60,812	1,844,608	1,790,381
221	dhv	Dehu	59,304	1,516,299	1,081,402
222	arz	Egyptian Arabic	59,273	1,040,607	1,217,443
223	ncj	Northern Puebla Nahuatl	58,561	956,551	1,079,883
224	cab	Garifuna	58,494	1,007,492	1,085,354
225	mam	Mam	57,127	1,423,370	1,168,787
226	wln	Walloon	56,623	429,679	305,452
227	guc	Wayuu	53,685	829,204	981,093
228	djk	Eastern Maroon Creole	53,221	1,500,873	1,039,928
229	seh	Sena	52,346	857,567	942,338
230	ido	Ido	51,442	847,598	925,707
231	kam	Kamba (Kenya)	51,134	959,544	929,605
232	sop	Songe	50,760	935,482	921,385
233	nyn	Nyankole	50,320	808,018	908,313
234	qvi	Imbabura Highland Quichua	50,226	667,059	917,189
235	sid	Sidamo	46,475	685,282	840,289
236	cak	Kaqchikel	46,242	1,296,149	961,305
237	wuu	Wu Chinese	44,979	1,401,488	981,672
238	rsl	Russian Sign Language	44,580	704,592	851,505
239	mgr	Mambwe-Lungu	43,613	729,826	779,743
240	yao	Yao	43,430	675,600	786,686
241	lmo	Lombard	43,257	956,126	916,365
242	ast	Asturian	43,053	323,110	285,999
243	cmn	Mandarin Chinese	42,771	480,846	364,575
244	kri	Krio	42,355	1,001,068	750,234
245	hmn	Hmong	41,767	908,683	728,027
246	kab	Kabyle	41,472	639,490	583,828
247	ngl	Lomwe	39,344	599,003	692,267
248	fil	Filipino	38,927	595,383	564,897
249	kss	Southern Kisi	37,713	776,337	653,867
250	ncx	Central Puebla Nahuatl	36,281	521,485	651,884
251	koo	Konzo	36,215	576,098	638,761
252	cjk	Chokwe	35,889	603,308	626,882
253	bbc	Batak Toba	35,299	576,883	619,703
254	srm	Saramaccan	34,820	852,215	596,927
255	iba	Iban	34,587	616,831	589,527
256	tcf	Malinaltepec Me’Phaa	34,575	848,660	624,296
257	nia	Nias	34,220	583,584	603,116
258	mwl	Mirandese	33,736	798,507	803,673
259	toj	Tojolabal	33,682	666,366	603,392
260	fon	Fon	31,182	866,652	549,296
261	nch	Central Huasteca Nahuatl	30,372	470,473	549,024
262	ndc	Ndau	30,339	489,579	526,630
263	ibg	Ibanag	30,297	572,127	534,006
264	ngu	Guerrero Nahuatl	29,640	461,702	532,754
265	urh	Urhobo	29,213	593,239	526,979
266	kbp	Kabiyè	28,909	615,867	518,354
267	wes	Cameroon Pidgin	28,041	641,415	496,515
268	bum	Bulu (Cameroon)	27,873	622,714	490,542
269	cnh	Hakha Chin	27,858	557,128	477,930
270	bas	Basa (Cameroon)	27,629	613,848	493,245
271	mau	Huautla Mazatec	27,411	493,893	496,940
272	btx	Batak Karo	27,274	437,937	469,368
273	abk	Abkhazian	27,222	351,408	483,397
274	nba	Nyemba	27,215	553,775	468,908
275	ksw	S’Gaw Karen	27,094	1,329,003	554,643
276	ctu	Chol	26,360	544,787	475,801
277	mai	Maithili	25,399	162,714	126,990
278	sme	Northern Sami	24,617	140,379	150,190
279	nyu	Nyungwe	24,475	419,949	426,977
280	csn	Colombian Sign Language	23,906	472,341	465,894
281	csb	Kashubian	23,816	153,784	157,725
282	oke	Okpe (Southwestern Edo)	22,381	456,587	398,402
283	bhw	Biak	22,290	367,652	380,779
284	tzh	Tzeltal	22,285	523,994	405,145
285	pcm	Nigerian Pidgin	21,983	463,475	392,393
286	fse	Finnish Sign Language	21,607	298,087	396,825
287	pso	Polish Sign Language	20,382	311,955	377,371
288	qug	Chimborazo Highland Quichua	20,233	247,132	350,124
289	chw	Chuwabu	17,991	253,364	299,537
290	cce	Chopi	17,957	346,849	303,040
291	csl	Chinese Sign Language	17,606	491,553	342,313
292	ina	Interlingua (International Auxiliary Language Association)	16,773	152,801	148,929
293	arn	Mapudungun	16,718	275,184	296,072
294	ttj	Tooro	16,429	253,796	280,735
295	gsg	German Sign Language	16,306	267,549	295,339
296	rom	Romany	16,068	422,606	412,229
297	chr	Cherokee	15,778	288,472	417,310
298	syr	Syriac	15,772	217,809	416,361
299	dop	Lukpa	15,715	558,921	416,550
300	cop	Coptic	15,711	256,406	416,573
301	cjp	Cabécar	15,708	648,168	401,094
302	quw	Tena Lowland Quichua	15,673	292,826	415,605
303	shi	Tachelhit	15,665	573,846	404,703
304	quc	K’Iche'	15,593	618,467	412,776
305	usp	Uspanteco	15,581	500,231	413,073
306	amu	Guerrero Amuzgo	15,541	567,453	411,629
307	jak	Jakun	15,521	565,010	411,376
308	nhg	Tetelcingo Nahuatl	15,454	408,450	409,284
309	hsb	Upper Sorbian	15,448	91,685	96,679
310	chq	Quiotepec Chinantec	15,395	1,064,331	408,551
311	cni	Asháninka	15,294	330,584	405,727
312	dua	Duala	15,277	442,302	267,263
313	gbi	Galela	14,988	623,655	398,070
314	kmr	Northern Kurdish	14,802	272,115	259,235
315	lam	Lamba	14,757	240,079	269,942
316	dyu	Dyula	14,730	318,841	255,835
317	ppk	Uma	14,675	672,340	387,644
318	nav	Navajo	14,664	230,522	248,549
319	cha	Chamorro	14,550	317,039	350,357
320	rmn	Balkan Romani	14,450	256,958	239,481
321	bts	Batak Simalungun	14,234	234,221	237,953
322	tlh	Klingon	13,897	102,819	114,576
323	hsh	Hungarian Sign Language	13,796	214,525	254,586
324	glv	Manx	13,490	285,583	252,235
325	fcs	Quebec Sign Language	13,430	268,170	238,533
326	agr	Aguaruna	13,326	325,087	338,679
327	ojb	Northwestern Ojibwa	13,320	290,069	354,097
328	dik	Southwestern Dinka	13,320	383,809	354,111
329	nij	Ngaju	13,169	213,858	222,235
330	ake	Akawaio	13,058	544,402	327,197
331	tyv	Tuvinian	12,990	199,681	243,947
332	jiv	Shuar	12,901	271,591	342,865
333	acu	Achuar-Shiwiar	12,762	373,501	327,361
334	xmf	Mingrelian	12,690	167,843	259,004
335	bsn	Barasana-Eduria	12,411	683,801	332,654
336	tss	Taiwan Sign Language	12,162	356,465	236,036
337	jbo	Lojban	11,985	91,618	85,242
338	cse	Czech Sign Language	11,607	178,242	208,581
339	bin	Bini	11,580	259,899	206,848
340	sxn	Sangir	11,563	227,808	193,551
341	gla	Scottish Gaelic	11,187	146,904	119,438
342	mfs	Mexican Sign Language	11,030	231,366	231,452
343	kac	Kachin	10,933	270,566	184,602
344	kbh	Camsá	10,703	412,791	272,268
345	rms	Romanian Sign Language	10,355	196,803	191,630
346	svk	Slovakian Sign Language	10,024	158,006	180,593
347	udm	Udmurt	9,322	147,306	171,878
348	yid	Yiddish	9,110	132,320	112,423
349	ami	Amis	9,054	184,171	174,073
350	crh	Crimean Tatar	8,742	48,790	50,680
351	fur	Friulian	8,535	70,721	63,476
352	her	Herero	8,078	143,109	139,975
353	kvk	Korean Sign Language	7,811	280,446	159,540
354	alz	Alur	7,541	154,056	132,728
355	gss	Greek Sign Language	7,018	135,730	138,708
356	srd	Sardinian	6,912	73,336	65,457
357	bzj	Belize Kriol English	6,885	135,908	119,338
358	yue	Yue Chinese	6,704	152,857	113,146
359	lfn	Lingua Franca Nova	6,388	49,392	46,787
360	aar	Afar	6,336	60,314	62,572
361	lim	Limburgan	6,203	39,173	38,816
362	pdt	Plautdietsch	5,838	111,653	101,001
363	mni	Manipuri	5,670	101,067	127,542
364	mxv	Metlatónoc Mixtec	5,651	175,449	103,511
365	sco	Scots	5,561	160,697	165,958
366	cor	Cornish	5,548	40,280	41,655
367	tmh	Tamashek	5,466	158,901	152,889
368	ish	Esan	5,201	112,505	90,930
369	kea	Kabuverdianu	5,193	101,895	89,956
370	tsz	Purepecha	4,886	78,179	89,106
371	mhr	Eastern Mari	4,149	24,079	23,788
372	pot	Potawatomi	4,113	108,987	110,373
373	aka	Akan	4,096	106,463	107,922
374	dzo	Dzongkha	4,064	76,550	26,060
375	prs	Dari	4,028	105,220	96,334
376	toh	Gitonga	3,890	78,105	65,257
377	alt	Southern Altai	3,886	53,347	70,793
378	ile	Interlingue	3,850	27,427	29,741
379	psr	Portuguese Sign Language	3,619	69,442	68,455
380	kau	Kanuri	3,367	91,841	84,933
381	ang	Old English (Ca. 450-1100)	3,243	14,717	14,129
382	ssp	Spanish Sign Language	3,192	62,120	62,281
383	fuv	Nigerian Fulfulde	3,088	83,338	83,391
384	nus	Nuer	3,073	120,476	83,366
385	din	Dinka	3,067	101,158	83,486
386	bod	Tibetan	2,981	87,624	35,072
387	arq	Algerian Arabic	2,933	41,376	45,002
388	fsl	French Sign Language	2,919	61,263	55,624
389	vol	Volapük	2,737	15,010	18,884
390	cbk	Chavacano	2,428	17,380	17,029
391	dtp	Kadazan Dusun	1,845	13,012	13,023
392	csg	Chilean Sign Language	1,687	27,143	27,960
393	men	Mende (Sierra Leone)	1,660	36,528	28,466
394	gom	Goan Konkani	1,601	41,639	46,209
395	pam	Pampanga	1,516	10,362	12,016
396	ava	Avaric	1,325	11,624	11,913
397	bug	Buginese	1,324	12,377	13,193
398	mnw	Mon	1,282	90,294	69,035
399	kha	Khasi	1,277	9,156	8,623
400	bam	Bambara	1,273	11,180	13,552
401	zsm	Standard Malay	1,270	10,317	11,410
402	gos	Gronings	1,171	5,902	6,188
403	san	Sanskrit	1,151	5,674	7,544
404	min	Minangkabau	1,143	28,717	30,987
405	ase	American Sign Language	1,128	16,016	16,570
406	sot	Southern Sotho	1,120	26,838	24,722
407	kas	Kashmiri	890	5,629	6,387
408	tet	Tetum	889	26,037	24,904
409	psp	Philippine Sign Language	880	22,876	22,876
410	vsl	Venezuelan Sign Language	837	19,100	17,757
411	csf	Cuba Sign Language	792	13,283	14,052
412	nst	Tase Naga	766	5,756	4,777
413	lad	Ladino	762	4,523	4,769
414	roh	Romansh	695	7,022	7,516
415	ota	Ottoman Turkish (1500-1928)	688	4,032	4,573
416	hoc	Ho	622	3,014	3,473
417	zza	Zaza	596	3,479	3,767
418	grc	Ancient Greek (To 1453)	593	3,925	5,024
419	szl	Silesian	588	3,850	4,554
420	prl	Peruvian Sign Language	581	9,375	10,363
421	frp	Arpitan	573	2,675	2,394
422	wae	Walser	556	2,862	3,022
423	ace	Achinese	491	3,822	3,588
424	grn	Guarani	477	5,242	7,043
425	bfi	British Sign Language	442	7,664	9,020
426	cos	Corsican	438	12,566	11,985
427	inh	Ingush	418	6,656	7,065
428	bvl	Bolivian Sign Language	403	6,824	7,286
429	nan	Min Nan Chinese	403	14,601	11,491
430	swh	Swahili (Individual)	371	1,851	2,542
431	rup	Macedo-Romanian	362	6,375	6,164
432	gor	Gorontalo	358	10,126	11,615
433	zpa	Lachiguiri Zapotec	356	6,320	6,431
434	vec	Venetian	355	3,559	3,172
435	azb	South Azerbaijani	343	9,296	12,112
436	zib	Zimbabwe Sign Language	312	9,002	8,503
437	orv	Old Russian	309	1,737	2,124
438	lzh	Literary Chinese	303	5,381	3,886
439	pms	Piemontese	302	3,360	2,646
440	inl	Indonesian Sign Language	287	4,294	4,995
441	xal	Kalmyk	285	1,659	2,070
442	max	North Moluccan Malay	273	2,006	1,880
443	diq	Dimli (Individual)	265	6,451	10,707
444	gsw	Swiss German	258	2,462	2,693
445	awa	Awadhi	252	1,323	1,336
446	got	Gothic	244	8,491	3,273
447	mzy	Mozambican Sign Language	242	4,337	4,413
448	ary	Moroccan Arabic	240	6,929	9,113
449	ltg	Latgalian	219	2,343	2,759
450	nov	Novial	218	1,451	1,470
451	hrx	Hunsrik	214	1,307	1,253
452	asf	Auslan	213	3,125	3,149
453	prg	Prussian	213	1,526	1,717
454	sat	Santali	209	9,092	9,473
455	tzl	Talossan	205	1,050	1,007
456	jam	Jamaican Creole English	201	7,542	7,713
457	frr	Northern Frisian	197	1,337	1,461
458	shn	Shan	193	4,072	1,174
459	avk	Kotava	170	991	1,285
460	pli	Pali	163	1,278	1,912
461	esn	Salvadoran Sign Language	154	2,909	3,093
462	haw	Hawaiian	153	2,872	2,709
463	krl	Karelian	136	664	694
464	che	Chechen	128	596	621
465	chu	Church Slavic	128	1,323	1,669
466	mad	Madurese	126	4,428	5,203
467	new	Newari	122	4,047	4,169
468	lld	Ladin	120	972	826
469	hds	Honduras Sign Language	120	2,355	2,406
470	cho	Choctaw	119	740	785
471	sah	Yakut	117	2,115	3,110
472	zam	Miahuatlán Zapotec	115	1,432	1,871
473	rue	Rusyn	113	480	683
474	qya	Quenya	109	476	649
475	dsb	Lower Sorbian	107	1,414	1,879
476	bzt	Brithenig	106	642	591
477	ldn	Láadan	105	646	616
478	npi	Nepali (Individual)	102	404	489
479	hai	Haida	101	841	1,193
480	gcf	Guadeloupean Creole French	100	593	586
481	pih	Pitcairn-Norfolk	98	2,439	2,229
482	bho	Bhojpuri	95	2,342	2,267
483	pnb	Western Panjabi	95	3,629	3,227
484	lij	Ligurian	93	815	734
485	bxr	Russia Buriat	90	3,112	3,986
486	tpw	Tupí	87	520	518
487	ksh	Kölsch	86	1,893	1,669
488	pys	Paraguayan Sign Language	84	913	1,073
489	hif	Fiji Hindi	83	1,256	1,650
490	nog	Nogai	82	336	475
491	mzn	Mazanderani	81	2,732	3,507
492	egl	Emilian	80	493	450
493	lut	Lushootseed	79	427	449
494	mus	Creek	75	700	662
495	mww	Hmong Daw	74	499	413
496	gsm	Guatemalan Sign Language	71	1,293	1,419
497	tcy	Tulu	68	2,359	2,707
498	afb	Gulf Arabic	64	292	360
499	bal	Baluchi	62	345	326
500	myv	Erzya	61	1,617	1,970
501	ext	Extremaduran	61	580	620
502	sgs	Samogitian	59	540	785
503	enm	Middle English (1100-1500)	59	374	381
504	miq	Mískito	58	151	128
505	zsl	Zambian Sign Language	55	1,588	1,292
506	moh	Mohawk	54	479	372
507	pdc	Pennsylvania German	54	495	517
508	fkv	Kven Finnish	54	525	614
509	ipk	Inupiaq	52	552	600
510	sjn	Sindarin	49	229	282
511	ins	Indian Sign Language	48	441	511
512	rif	Tarifit	46	209	239
513	dty	Dotyali	46	1,596	1,426
514	cre	Cree	46	779	1,620
515	ike	Eastern Canadian Inuktitut	44	140	247
516	sux	Sumerian	43	246	217
517	sma	Southern Sami	43	175	214
518	tly	Talysh	42	145	202
519	shs	Shuswap	40	240	207
520	pmy	Papuan Malay	39	157	167
521	brx	Bodo (India)	37	138	168
522	nbl	South Ndebele	34	267	260
523	swg	Swabian	34	272	268
524	ecs	Ecuadorian Sign Language	34	279	338
525	tmr	Jewish Babylonian Aramaic (Ca. 200-1200 Ce)	34	252	452
526	gbm	Garhwali	33	155	138
527	mgm	Mambae	33	282	307
528	nap	Neapolitan	31	301	262
529	hup	Hupa	31	417	345
530	pnt	Pontic	29	598	588
531	liv	Liv	29	150	176
532	atj	Atikamekw	29	865	805
533	ppl	Pipil	29	163	208
534	glk	Gilaki	28	1,391	1,572
535	zgh	Standard Moroccan Tamazight	27	392	332
536	lkt	Lakota	27	164	179
537	ain	Ainu (Japan)	26	117	154
538	aln	Gheg Albanian	25	133	134
539	pau	Palauan	25	121	119
540	csr	Costa Rican Sign Language	25	237	239
541	ood	Tohono O’Odham	24	198	149
542	bvy	Baybayanon	23	158	165
543	vls	Vlaams	21	627	579
544	rap	Rapanui	21	130	99
545	rmy	Vlax Romani	20	837	774
546	frm	Middle French (Ca. 1400-1600)	18	209	222
547	scn	Sicilian	16	200	266
548	apc	North Levantine Arabic	16	75	110
549	nqo	N’Ko	16	983	479
550	nau	Nauru	16	74	104
551	wkd	Wakde	16	125	123
552	zha	Zhuang	15	497	519
553	kjh	Khakas	15	60	75
554	shy	Tachawit	15	65	86
555	koi	Komi-Permyak	14	68	85
556	ave	Avestan	14	122	159
557	nlv	Orizaba Nahuatl	14	137	154
558	ngt	Kriang	14	86	92
559	bua	Buriat	14	61	77
560	non	Old Norse	13	134	136
561	trv	Taroko	12	98	86
562	sfs	South African Sign Language	12	290	338
563	akl	Aklanon	12	53	48
564	acm	Mesopotamian Arabic	11	63	88
565	aoz	Uab Meto	11	51	55
566	kpv	Komi-Zyrian	11	32	40
567	phn	Phoenician	11	172	89
568	afh	Afrihili	10	46	54
569	mdf	Moksha	9	89	97
570	laa	Southern Subanen	9	153	150
571	dws	Dutton World Speedwords	9	37	48
572	hbo	Ancient Hebrew	8	74	126
573	kum	Kumyk	8	33	51
574	ady	Adyghe	8	53	102
575	stq	Saterfriesisch	8	56	58
576	vro	Võro	8	75	92
577	cjy	Jinyu Chinese	8	70	52
578	mvv	Tagal Murut	8	33	40
579	mic	Mi’Kmaq	7	23	33
580	drt	Drents	6	48	52
581	oar	Old Aramaic (Up To 700 Bce)	6	61	71
582	sml	Central Sama	6	21	15
583	dng	Dungan	6	27	32
584	fuc	Pulaar	6	21	26
585	luy	Luyia	5	62	92
586	jpa	Jewish Palestinian Aramaic	5	26	50
587	izh	Ingrian	5	18	19
588	lsp	Panamanian Sign Language	5	38	53
589	hyw	Western Armenian	5	491	584
590	zea	Zeeuws	5	323	304
591	pfl	Pfaelzisch	5	168	191
592	tmw	Temuan	5	23	34
593	hak	Hakka Chinese	4	25	20
594	osp	Old Spanish	4	26	26
595	kom	Komi	4	143	123
596	lez	Lezghian	4	108	75
597	pal	Pahlavi	4	42	51
598	hnj	Hmong Njua	3	20	15
599	gan	Gan Chinese	3	26	18
600	sdh	Southern Kurdish	2	11	14
601	ofs	Old Frisian	2	16	15
602	jdt	Judeo-Tat	2	6	9
603	byn	Bilin	2	3	3
604	ncs	Nicaraguan Sign Language	2	10	10
605	bpy	Bishnupriya	2	55	57
606	hsn	Xiang Chinese	2	14	10
607	aeb	Tunisian Arabic	2	10	16
608	tkl	Tokelau	1	7	6
609	cku	Koasati	1	20	48
610	chy	Cheyenne	1	59	54
611	tts	Northeastern Thai	1	3	5
612	tig	Tigre	1	3	4
613	gag	Gagauz	1	5	5
614	nhn	Central Nahuatl	1	3	3
615	mrj	Western Mari	1	64	60
616	lbe	Lak	1	56	55
617	lrc	Northern Luri	1	42	54
618	arc	Official Aramaic (700-300 Bce)	1	2	2
619	chn	Chinook Jargon	1	7	6
620	iii	Sichuan Yi	1	2	4
621	ckt	Chukot	1	3	5

Many-to-English: Data v2 and Statistics

Acknowledgements