Iranian languages

The Iranian languages include Iranian Persian, Dari, Tajik (three varieties of Modern Persian), Pashto, Balochi, Kurdish, Ossetian, Tat, and several dozen other languages.

The master plan involves generating independent finite-state transducers for each language, and then making individual dictionaries and transfer rules for every pair. The current status of these goals is listed below.

Status

The ultimate goal is to have multi-purposable transducers for a variety of Iranian languages. These can then be paired for X→Y translation with the addition of a CG for language X and transfer rules / dictionary for the pair X→Y. Below is listed development progress for each language's transducers and dictionary pairs.

Transducers

Once a transducer has ~80% coverage on a range of medium-large corpora we can say it is "working". Over 90% and it can be considered to be "production".

name	Language	ISO 639		formalism	state	stems	coverage	location	primary authors
		-2	-3
apertium-pes	Iranian Persian (Farsi)	—	pes	lttoolbox	development			apertium-pes (incubator)
apertium-tgk	Tajik	tg	tgk	lttoolbox	development
apertium-glk	Gilaki	—	glk	lttoolbox	development			apertium-glk (incubator)	ronl, Fran
apertium-oss	Ossetian	os	oss	lttoolbox	development			apertium-oss (incubator)

name	Language	ISO 639		formalism	state	stems	paradigms	coverage	location	primary authors
		-2	-3
apertium-kmr	Kurdish (Kurmanji)	ku	kmr	lttoolbox	development	17,771	157	[[Apertium-kmr#Current_State|~Apertium-kmr/stats/average%]]	apertium-kmr (languages)	Fran, Memduh
apertium-pes	Iranian Persian (Farsi)	fa	pes	lttoolbox	development	13,167	113	[[Apertium-pes#Current_State|~Apertium-pes/stats/average%]]	apertium-pes (languages)	Fran, ...
apertium-tgk	Tajik	tg	tgk	lttoolbox	development	2,784	79	[[Apertium-tgk#Current_State|~Apertium-tgk/stats/average%]]	apertium-tgk (languages)	Fran, ...
apertium-oss	Ossetian	os	oss	lttoolbox	prototype	111		~17%	apertium-oss (languages)	Fran, ...
apertium-glk	Gilaki		glk	lttoolbox	prototype	4	28	[[Apertium-oss#Current_State|~Apertium-glk/stats/average%]]	apertium-glk (languages)	Fran, ronl
apertium-ckb	Central Kurdish (Sorani)		ckb	lttoolbox	prototype	2		[[Apertium-kmr#Current_State|~Apertium-ckb/stats/average%]]	apertium-ckb (languages)	Fran, Memduh

Table of Existing Pairs

Text in italics denotes language pairs in the incubator. Regular text denotes a developing language pair in nursery, while text in bold denotes a stable well-working language pair in trunk and text in bold and italics denotes a pair in staging. Bidix stems as counted with dixcounter are displayed below.

	pes	tgk	glk	oss	fas
pes	-	tgk-pes 504	pes-glk 8
tgk	tgk-pes 504	-
glk	pes-glk 8		-
oss				-
fas					-
eng		tg-en ?
epo					eo-fa ?
urd					ur-fa ?

Language Codes

Note that fas(/per) and fa are macrocodes for Persian, which includes Farsi (Iranian Persian - pes), Dari (Afghan Persian - prs), and Tajik (tgk).

Samples

Article 1 of the Universal Declaration of Human Rights:

All human beings are born free and equal in dignity and rights. They are endowed with reason and conscience and should act towards one another in a spirit of brotherhood.

Language	Text
Ossetian	Адӕймӕгтӕ се¢ ппӕт дӕр райгуырынц сӕрибарӕй ӕмӕ ӕмхуызонӕй сӕ барты. Уыдон ӕххӕст сты зонд ӕмӕ намысӕй, ӕмӕ кӕрӕдзийӕн хъуамӕ уой ӕфсымӕрты хуызӕн.
Pashto, Northern	د بشر ټول افراد آزاد نړۍ ته راځی او د حيثيت او حقوقو له پلوه سره برابر دی. ټول د عقل او وجدان خاوندان دی او يو له بل سره د ورورۍ په روحيې سره بايد چلند کړی.
Kurdish, Northern	Hemû mirov azad û di weqar û mafan de wekhev tên dinyayê. Ew xwedî hiş û şuûr in û divê li hember hev bi zihniyeteke bratiyê bilivin.
Tajik	Тамоми одамон озод ва аз лиҳози шарафу ҳуқуқ ба ҳам баробар ба дунё меоянд. Онҳо соҳиби ақлу виҷдонанд ва бояд бо якдигар муносибати бародарона дошта бошанд.
Iranian Persian	تمام افراد بشر آزاد بدنیا میایند و از لحاظ حیثیت و حقوق با هم برابرند. همه دارای عقل و وجدان میباشند و باید نسبت بیکدیگر با روح برادری رفتار کنند.
Dari	تمام افراد بشر آزاد به دنیا می‌آیند و از لحاظ حیثیت و حقوق با هم برابرند. همه دارای عقل و وجدان هستند و باید نسبت به یکدیگر با روح برادری رفتار کنند.

Vulnerability

This table summarizes the vulnerability of various Iranian languages. Data is derived from the ‘Atlas of the World’s Languages in Danger, © UNESCO, http://www.unesco.org/culture/languages-atlas’ and Ethnologue.

Language	ISO639-3	Location	Speakers	Status
				Ethnologue	UNESCO
Avestan	ave	Iran	0	10 (Extinct)	-
Pahlavani	phv	Afghanistan	0	9 (Dormant)	-
Koroshi	ktl	Iran	180	8b (Nearly extinct)	4 (Critically endangered)
Kumzari	zum	Oman	2,300	8a (Moribund)	3 (Severely endangered)
Parachi	prc	Afghanistan	3,500	7 (Shifting)	2 (Definitely endangered)
Bashkardi	bsg	Iran	7,030	7 (Shifting)	2 (Definitely endangered)
Gazi	gzi	Iran	7,030	7 (Shifting)	2 (Definitely endangered)
Sivandi	siy	Iran	7,030	7 (Shifting)	-
Fars, Northwestern	faz	Iran	7,500	7 (Shifting)	-
Dari, Zoroastrian	gbz	Iran	8,000	7 (Shifting)	2 (Definitely endangered)
Shabak	sdb	Iraq	15,000	7 (Shifting)	-
Karingani	kgn	Iran	17,600	7 (Shifting)	-
Vafsi	vaf	Iran	18,000	7 (Shifting)	2 (Definitely endangered)
Bajelani	bjm	Iraq	20,000	7 (Shifting)	-
Ashtiani	atn	Iran	21,100	7 (Shifting)	2 (Definitely endangered)
Khunsari	kfm	Iran	21,100	7 (Shifting)	2 (Definitely endangered)
Tat, Muslim	ttt	Azerbaijan	28,010	7 (Shifting)	3 (Severely endangered)
Harzani	hrz	Iran	28,100	7 (Shifting)	-
Dzhidi	jpr	Israel & Iran	60,000	7 (Shifting)	2 (Definitely endangered)
Fars, Southwestern	fay	Iran	100,000	7 (Shifting)	-
Bukharic	bhh	Israel & Uzbekistan	110,000	7 (Shifting)	2 (Definitely endangered)
Gurani	hac	Iraq	200,000	7 (Shifting)	-
Takestani	tks	Iran	220,000	7 (Shifting)	-
Mazanderani	mzn	Iran	3,270,000	7 (Shifting)	-
Alviri-Vidari	avd	Iran	?	7 (Shifting)	-
Eshtehardi	esh	Iran	?	7 (Shifting)	-
Gozarkhani	goz	Iran	?	7 (Shifting)	-
Kabatei	xkp	Iran	?	7 (Shifting)	-
Kajali	xkj	Iran	?	7 (Shifting)	-
Kho’ini	xkc	Iran	?	7 (Shifting)	-
Koresh-e Rostam	okh	Iran	?	7 (Shifting)	-
Maraghei	vmh	Iran	?	7 (Shifting)	-
Razajerdi	rat	Iran	?	7 (Shifting)	-
Rudbari	rdb	Iran	?	7 (Shifting)	-
Shahrudi	shm	Iran	?	7 (Shifting)	-
Taromi, Upper	tov	Iran	?	7 (Shifting)	-
Sarli	sdf	Iraq	Fewer than 20,000.	7 (Shifting)	-
Ishkashimi	isk	Afghanistan	3,000	6b (Threatened)	-
Yidgha	ydg	Pakistan	6,150	6b (Threatened)	2 (Definitely endangered)
Yazgulyam	yah	Tajikistan	9,000	6b (Threatened)	3 (Severely endangered)
Yagnobi	yai	Tajikistan	12,000	6b (Threatened)	2 (Definitely endangered)
Sarikoli	srh	China	16,000	6b (Threatened)	2 (Definitely endangered)
Lasgerdi	lsa	Iran	1,000	6a (Vigorous)	-
Sanglechi	sgy	Afghanistan	2,200	6a (Vigorous)	-
Munji	mnj	Afghanistan	5,300	6a (Vigorous)	3 (Severely endangered)
Ormuri	oru	Pakistan, Afghanistan	6,050	6a (Vigorous)	2 (Definitely endangered)
Natanzi	ntz	Iran	7,030	6a (Vigorous)	3 (Severely endangered)
Nayini	nyq	Iran	7,030	6a (Vigorous)	3 (Severely endangered)
Soi	soj	Iran	7,030	6a (Vigorous)	-
Sorkhei	sqo	Iran	10,000	6a (Vigorous)	-
Dehwari	deh	Pakistan	13,000	6a (Vigorous)	-
Sangisari	sgr	Iran	36,000	6a (Vigorous)	-
Wakhi	wbl	China, Pakistan, Tajikistan, Afghanistan	47,100	6a (Vigorous)	2 (Definitely endangered)
Semnani	smy	Iran	60,000	6a (Vigorous)	-
Shughni	sgh	Tajikistan	80,000	6a (Vigorous)	3 (Severely endangered)
Lari	lrl	Iran	80,000,	6a (Vigorous)	-
Waneci	wne	Pakistan	95,000	6a (Vigorous)	-
Parsi	prp	India	326,000	6a (Vigorous)	-
Parsi-Dari	prd	Iran	350,000	6a (Vigorous)	-
Aimaq	aiq	Afghanistan	650,000	6a (Vigorous)	-
Luri, Southern	luz	Iran	875,000	6a (Vigorous)	-
Laki	lki	Iran	1,000,000	6a (Vigorous)	-
Bakhtiâri	bqi	Iran	1,000,000	6a (Vigorous)	-
Luri, Northern	lrc	Iran	1,500,000	6a (Vigorous)	-
Kurdish, Southern	sdh	Iran	3,000,000	6a (Vigorous)	-
Pashto, Central	pst	Pakistan	7,920,000	6a (Vigorous)	-
Shahmirzadi	srz	Iran	?	6a (Vigorous)	-
Dezfuli	def	Iran	?	6a (Vigorous)	-
Khalaj	kjf	Azerbaijan	42,100	5 (Developing)	-
Ossetic	oss	Georgia, Russian Federation	577,450	5 (Developing)	1 (Vulnerable)
Hazaragi	haz	Afghanistan	2,210,000	5 (Developing)	-
Judeo-Tat	jdt	Azerbaijan, Russian Federation	2,010	4 (Educational)	2 (Definitely endangered)
Zazaki, Northern	kiu	Turkey	140,000	4 (Educational)	-
Talysh	tly	Azerbaijan, Iran	915,400	4 (Educational)	1 (Vulnerable)
Zazaki, Southern	diq	Turkey	1,500,000	4 (Educational)	-
Balochi, Western	bgn	Pakistan	1,799,840	4 (Educational)	-
Balochi, Eastern	bgp	Pakistan	1,800,800	4 (Educational)	-
Gilaki	glk	Iran	3,270,000	4 (Educational)	-
Balochi, Southern	bcc	Pakistan	3,405,000	4 (Educational)	-
Pashto, Northern	pbu	Pakistan	11,430,000	4 (Educational)	-
Kurdish, Northern	kmr	Turkey	20,210,872	3 (Wider communication)	-
Kurdish, Central	ckb	Iraq	6,750,000	2 (Provincial)	-
Tajiki	tgk	Tajikistan	4,479,650	1 (National)	-
Pashto, Southern	pbt	Afghanistan	7,590,100	1 (National)	-
Dari	prs	Afghanistan	9,600,000	1 (National)	-
Persian, Iranian	pes	Iran	47,045,100	1 (National)	-

Classification

• Southwestern: Iranian Persian, Tajik
• Northwestern: Kurdish (Kurmanji, Sorani)
• Southeastern: Pashto
• Northeastern: Ossetian