Upload processor

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|tp|>": 1130
+}

merges.txt

@@ -0,0 +1,768 @@
+#version: 0.2
+Ġ l
+n a
+Ġl i
+Ġ t
+Ġ p
+Ġ s
+Ġ m
+a n
+Ġ e
+Ġ k
+l i
+o na
+e n
+w a
+a l
+n i
+s i
+Ġ ni
+al a
+Ġl a
+Ġt a
+Ġp i
+o n
+j an
+Ġm i
+k i
+m a
+Ġs i
+Ġta wa
+t e
+m i
+Ġl on
+Ġ w
+Ġ ala
+Ġt o
+i l
+a ma
+Ġp ona
+Ġm u
+Ġ o
+Ġ jan
+Ġp a
+k e
+k a
+Ġsi na
+Ġl u
+li n
+Ġk ama
+s o
+Ġ ona
+p o
+Ġto ki
+il e
+Ġ na
+en po
+Ġs u
+Ġw ile
+Ġs e
+Ġ i
+Ġmu te
+p a
+si na
+Ġ a
+Ġk en
+l o
+p e
+ki n
+m e
+Ġ an
+j o
+m o
+Ġs ona
+Ġt an
+Ġlu kin
+s a
+Ġpi lin
+k en
+al e
+t a
+e lo
+Ġi ke
+Ġto mo
+k u
+Ġ ale
+il o
+w i
+Ġm o
+p u
+Ġk u
+e li
+Ġse me
+si n
+Ġli li
+Ġt enpo
+Ġk i
+Ġsu li
+Ġ wa
+Ġk e
+pe ken
+Ġpa li
+Ġke peken
+j a
+t enpo
+Ġm a
+Ġpa na
+p i
+Ġ jo
+w en
+w eli
+Ġt u
+Ġta so
+u n
+Ġan te
+Ġmo ku
+e ka
+l en
+Ġp o
+Ġw eka
+k ala
+Ġw an
+Ġlu ka
+Ġna sin
+Ġsi n
+Ġo lin
+k o
+n pa
+Ġmu si
+Ġwa wa
+Ġs ama
+Ġk ala
+n o
+Ġt elo
+l u
+Ġa wen
+Ġni mi
+j e
+Ġna npa
+Ġ K
+te len
+Ġ T
+Ġla wa
+Ġ ilo
+Ġs o
+Ġli pu
+Ġpa kala
+t u
+Ġpi ni
+Ġsi telen
+u ta
+Ġsu no
+Ġso weli
+Ġse wi
+Ġna sa
+ĠT u
+Ġe n
+ta so
+t o
+j elo
+Ġki n
+Ġpo ka
+lu pu
+tu li
+Ġi jo
+un tuli
+ĠK untuli
+l e
+Ġla pe
+Ġku te
+Ġk a
+so weli
+Ġan u
+Ġl en
+Ġkala ma
+Ġm on
+Ġsi ke
+Ġmo li
+Ġka si
+p en
+Ġala sa
+Ġsu wi
+Ġan pa
+Ġku le
+ke si
+n sa
+Ġo pen
+Ġ ja
+Ġk on
+Ġku lupu
+Ġ S
+Ġ u
+Ġi nsa
+o je
+Ġ "
+Ġl oje
+Ġse li
+Ġki li
+t ala
+l a
+Ġa li
+s un
+na sin
+pi n
+Ġu tala
+an i
+Ġpo ki
+e na
+s uta
+Ġsi jelo
+Ġ n
+Ġja ki
+Ġ A
+Ġ P
+Ġl e
+Ġp an
+Ġm ani
+Ġk o
+me ja
+Ġ uta
+Ġp u
+Ġpi meja
+to ki
+Ġmon suta
+Ġn ena
+Ġli n
+ni mi
+Ġmi je
+Ġmu n
+Ġlu pa
+Ġ L
+Ġm ama
+ma ko
+Ġna mako
+Ġsin pin
+t an
+Ġm eli
+Ġsu pa
+Ġwa so
+to mo
+si ke
+Ġa kesi
+no ka
+l on
+ka si
+Ġlin ja
+m u
+Ġ noka
+Ġwa lo
+a kesi
+Ġ M
+Ġ un
+ku lupu
+Ġki wen
+pi si
+ĠA n
+i jo
+s e
+s an
+w e
+Ġ jelo
+Ġe sun
+Ġla so
+Ġpa ke
+Ġki pisi
+p an
+li pu
+te lo
+Ġmon si
+Ġle te
+Ġun pa
+al u
+ke wi
+kala ma
+sike ke
+ĠAn kewi
+j u
+si la
+Ġpali sa
+k alu
+Ġ E
+si telen
+te san
+Ġse lo
+ta kalu
+je tesan
+jetesan takalu
+wa so
+Ġmi sikeke
+pi pi
+Ġpo we
+ko sila
+sun o
+Ġ I
+on si
+pa li
+me li
+mu si
+" .
+k on
+o lin
+s u
+â Ģ
+Ġ N
+Ġt onsi
+wa wa
+Ġpi pi
+ma ma
+Ġo ko
+mo ku
+Ġle ko
+Ġko kosila
+s ona
+se me
+ju na
+e so
+Ġm eso
+lin ja
+Ġma juna
+lu kin
+ĠS on
+ĠI n
+s elo
+w ile
+Ġl an
+si ma
+ki li
+pi lin
+lu ka
+ĠK a
+ĠT e
+ĠL i
+ĠM e
+ĠIn li
+Ġlan pan
+. .
+i ke
+s eli
+t on
+w an
+si jelo
+ki jetesantakalu
+Ġa pe
+pe si
+ku le
+pi ku
+Ġso ko
+Ġja sima
+ĠP i
+ĠSon ja
+Ġape ja
+Ġ J
+na npa
+sin pin
+Ġki jetesantakalu
+lu pa
+la wa
+a li
+n ton
+Ġ âĢ
+Ġt e
+ki wen
+pa kala
+wi nton
+lu wi
+Ġlin luwi
+ĠL o
+ĠE winton
+âĢ Ŀ
+ĠN i
+ĠâĢ ľ
+l an
+n tu
+o ko
+Ġ W
+Ġm elo
+Ġe piku
+mi je
+pi ni
+ĠK i
+ĠT o
+Ġka pesi
+ĠS a
+ĠS u
+ĠS an
+ĠS en
+ĠP a
+ĠP e
+ĠL a
+pali sa
+ĠTe len
+ĠLi sa
+Ġmelo me
+a wen
+m on
+m un
+p ona
+Ġ O
+na ta
+li ja
+po ki
+sa wi
+Ġku ntu
+ja ki
+Ġpu wa
+ĠM i
+se wi
+su pa
+ĠKa nata
+ĠMe wi
+.. .
+ĠJ u
+ĠSen i
+mon suta
+e piku
+o pen
+an te
+si ja
+Ġmi jo
+mi sikeke
+ama na
+po ka
+sa li
+ĠK u
+ĠK en
+ĠT a
+ĠS i
+ĠS amana
+Ġu sawi
+la pe
+la pi
+ĠP o
+mu te
+pan po
+ĠE lo
+ĠKa pesi
+ĠKi n
+ĠSu panpo
+ĠSan ta
+ĠLa sina
+ĠMewi ka
+Ġmijo mi
+e ko
+e sun
+i mi
+i nsa
+j uta
+k ama
+m ala
+n ena
+u tala
+y u
+¼ ģ
+ï ¼ģ
+Ġ U
+na sa
+Ġs an
+Ġe te
+Ġk an
+wa la
+si pin
+ala ta
+ala sija
+on ken
+Ġpa sila
+ke ke
+pa na
+pe lan
+Ġki ki
+ko kosila
+ĠK an
+ĠK eli
+ĠT imi
+Ġka mala
+ĠS o
+ĠA si
+ĠP u
+ĠP an
+ĠP ona
+ĠP alata
+ĠL e
+ĠM a
+ĠM alasija
+Ġun u
+ĠE ko
+ĠE pelan
+ĠI ta
+ĠN e
+ĠN u
+ĠSon ko
+ĠLi n
+ĠMe keke
+ĠPi ta
+ĠJ onken
+ĠLo la
+âĢĿ .
+ĠW a
+ĠTo si
+ĠTo ki
+ĠSu san
+ĠPe pu
+ĠMi sali
+ĠSi ko
+lapi su
+ĠElo pa
+ĠKin kili
+Ġkamala wala
+ĠEpelan to
+! "
+" ,
+" ?
+. "
+? !
+E ko
+a sin
+e si
+e ta
+e lon
+e sija
+i je
+i sipin
+j al
+j on
+j ama
+k an
+l ani
+m an
+m ani
+n u
+o mi
+o se
+p on
+p il
+p ani
+p alu
+s on
+s ama
+t onsi
+u pi
+w ani
+Ġ yu
+na wi
+na ja
+Ġp eta
+an u
+an ka
+an pa
+an tan
+li a
+li sa
+li ku
+li lan
+wa si
+wa wi
+ni ja
+si ko
+ala sa
+Ġta ki
+on yu
+Ġmi sa
+ki ni
+ki jo
+ki ko
+ki mu
+ki pisi
+ki san
+ma juna
+te lan
+mi le
+il a
+Ġmu lapisu
+Ġo we
+Ġo juta
+ke peken
+ke naja
+ka so
+ka ton
+ka wan
+so ko
+po lo
+po we
+Ġi sipin
+pa jal
+pa kawan
+lo je
+pe ta
+pe ko
+me so
+me su
+jo le
+jo ju
+mo si
+mo mo
+mo to
+sa lin
+ta wa
+ta wan
+ta sali
+ku kan
+wi to
+pu si
+pu wani
+Ġwa le
+Ġke se
+ja sima
+pi li
+pi meja
+Ġtu li
+un eko
+ko wa
+no kijo
+je sa
+je kenaja
+ĠK ena
+ĠK ijo
+ĠK elon
+ĠK omi
+ĠK ila
+ĠT en
+ĠT onyu
+Ġso to
+le te
+le ko
+Ġkon we
+ĠS uneko
+Ġu mesu
+la so
+la sin
+ĠA li
+ĠA wi
+ĠA lapi
+ĠA man
+ĠA wawi
+ĠA polo
+ĠA tawan
+ĠA lasin
+ĠP uta
+ĠL uta
+ĠL upi
+ĠL antan
+mu lapisu
+ĠM ena
+ĠM ose
+ĠM anka
+ĠAn se
+ĠAn son
+ĠAn kowa
+ijo sa
+alu to
+ju si
+ju wan
+ju kini
+ĠE ki
+ĠE lisa
+ĠI lan
+su li
+su ka
+su wi
+su pan
+ĠN asin
+ĠN aluto
+ĠIn ton
+ĠKa pil
+ĠKa jesa
+ĠTe po
+ĠTe ja
+ĠTe wen
+ĠTe pani
+ĠLi lija
+ĠLi lilan
+ĠMe lani
+ĠMe siko
+ĠMe kiko
+seli ja
+ĠPi wi
+ĠPi sin
+ĠPi ju
+ĠPi nija
+ĠPi kaso
+ĠPi nokijo
+ĠJ an
+Ġte je
+ĠLo pin
+ĠLo wasi
+ĠLo katon
+ĠLo supan
+ĠNi ki
+ĠNi mu
+ĠNi jon
+ĠNi pon
+ĠNi mile
+ĠW eko
+ĠW ije
+ĠW ijosa
+ĠKi ta
+ĠKi liku
+ĠTo to
+ĠSa ku
+ĠSa salin
+ĠSa jusi
+ĠSen tu
+ĠPa si
+ĠPa kala
+ĠPa kisan
+ĠPa puwani
+ĠPe we
+ĠPe kimu
+ĠPe joju
+ĠLa jo
+ĠLa wito
+ĠO sin
+ĠO we
+ĠO juta
+ĠO selija
+ĠMi moku
+ĠMi jama
+ĠJu li
+ĠJu ke
+ĠJu tu
+ĠJu lija
+ĠKu pa
+ĠKu lija
+ĠKu kukan
+ĠTa wi
+ĠTa pajal
+ĠTa juwan
+ĠPo ta
+ĠPo moto
+ĠPo suka
+ĠU tu
+ĠU sawi
+ĠKan se
+ĠKan pusi
+ĠSo momo
+ĠPu tu
+ĠPu nawi
+ĠPan to
+ĠPan tasali
+ĠLe wi
+ĠLe mosi
+ĠMa ku
+ĠMa su
+ĠIta lija
+ĠIta lia
+ĠNe palu
+ĠNe telan
+ĠNu ken
+ĠNu wan
+ĠLin ta
+ĠLin ja
+ĠWa jole
+ĠWa pili
+esi po
+Ġyu peko
+Ġwale ja
+ĠKena jekenaja
+ĠKijo to
+ĠKomi nu
+ĠAnse tan
+ĠElisa pe
+ĠNasin esipo
+ĠInton esija
+ĠKapil u
+ĠKiliku ntu
+ĠPapuwani jukini
+ĠTapajal o
+ĠPomoto lo
+ĠPantasali pakawan
+Ġyupeko si

special_tokens_map.json

@@ -0,0 +1,788 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|startoftranscript|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|en|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|zh|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|de|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|es|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|ru|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|ko|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|fr|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|ja|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|pt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|tr|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|pl|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|ca|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|nl|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|ar|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|sv|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|it|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|hi|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|fi|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|vi|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|he|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|uk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|el|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|ms|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|cs|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|ro|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|da|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|hu|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|ta|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|no|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|th|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|ur|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|hr|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|bg|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|lt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|la|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|mi|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|ml|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|cy|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|sk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|te|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|fa|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|lv|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|bn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|sr|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|az|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|sl|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|kn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|et|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|mk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|br|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|eu|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|is|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|hy|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|ne|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|mn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|bs|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|kk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|sq|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|sw|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|gl|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|mr|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|pa|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|si|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|km|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|sn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|yo|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|so|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|af|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|oc|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|ka|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|be|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|tg|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|sd|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|gu|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|am|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|yi|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|lo|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|uz|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|fo|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|ht|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|ps|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|tk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|nn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|mt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|sa|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|lb|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|my|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|bo|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|tl|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|mg|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|as|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|tt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|haw|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|ln|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|ha|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|ba|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|jw|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|su|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|translate|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|transcribe|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|startoflm|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|startofprev|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|nocaptions|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|notimestamps|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|tp|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,2993 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "<|startoftranscript|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "<|en|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "<|zh|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 4,
+      "content": "<|de|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 5,
+      "content": "<|es|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 6,
+      "content": "<|ru|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 7,
+      "content": "<|ko|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 8,
+      "content": "<|fr|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 9,
+      "content": "<|ja|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 10,
+      "content": "<|pt|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 11,
+      "content": "<|tr|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 12,
+      "content": "<|pl|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 13,
+      "content": "<|ca|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 14,
+      "content": "<|nl|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 15,
+      "content": "<|ar|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 16,
+      "content": "<|sv|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 17,
+      "content": "<|it|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 18,
+      "content": "<|id|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 19,
+      "content": "<|hi|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 20,
+      "content": "<|fi|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 21,
+      "content": "<|vi|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 22,
+      "content": "<|he|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 23,
+      "content": "<|uk|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 24,
+      "content": "<|el|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 25,
+      "content": "<|ms|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 26,
+      "content": "<|cs|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 27,
+      "content": "<|ro|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 28,
+      "content": "<|da|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 29,
+      "content": "<|hu|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 30,
+      "content": "<|ta|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 31,
+      "content": "<|no|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32,
+      "content": "<|th|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 33,
+      "content": "<|ur|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 34,
+      "content": "<|hr|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 35,
+      "content": "<|bg|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 36,
+      "content": "<|lt|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 37,
+      "content": "<|la|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 38,
+      "content": "<|mi|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 39,
+      "content": "<|ml|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 40,
+      "content": "<|cy|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 41,
+      "content": "<|sk|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 42,
+      "content": "<|te|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 43,
+      "content": "<|fa|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 44,
+      "content": "<|lv|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 45,
+      "content": "<|bn|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 46,
+      "content": "<|sr|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 47,
+      "content": "<|az|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 48,
+      "content": "<|sl|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 49,
+      "content": "<|kn|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 50,
+      "content": "<|et|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 51,
+      "content": "<|mk|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 52,
+      "content": "<|br|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 53,
+      "content": "<|eu|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 54,
+      "content": "<|is|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 55,
+      "content": "<|hy|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 56,
+      "content": "<|ne|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 57,
+      "content": "<|mn|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 58,
+      "content": "<|bs|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 59,
+      "content": "<|kk|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 60,
+      "content": "<|sq|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 61,
+      "content": "<|sw|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 62,
+      "content": "<|gl|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 63,
+      "content": "<|mr|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 64,
+      "content": "<|pa|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 65,
+      "content": "<|si|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 66,
+      "content": "<|km|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 67,
+      "content": "<|sn|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 68,
+      "content": "<|yo|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 69,
+      "content": "<|so|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 70,
+      "content": "<|af|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 71,
+      "content": "<|oc|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 72,
+      "content": "<|ka|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 73,
+      "content": "<|be|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 74,
+      "content": "<|tg|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 75,
+      "content": "<|sd|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 76,
+      "content": "<|gu|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 77,
+      "content": "<|am|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 78,
+      "content": "<|yi|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 79,
+      "content": "<|lo|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 80,
+      "content": "<|uz|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 81,
+      "content": "<|fo|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 82,
+      "content": "<|ht|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 83,
+      "content": "<|ps|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 84,
+      "content": "<|tk|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 85,
+      "content": "<|nn|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 86,
+      "content": "<|mt|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 87,
+      "content": "<|sa|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 88,
+      "content": "<|lb|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 89,
+      "content": "<|my|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 90,
+      "content": "<|bo|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 91,
+      "content": "<|tl|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 92,
+      "content": "<|mg|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 93,
+      "content": "<|as|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 94,
+      "content": "<|tt|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 95,
+      "content": "<|haw|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 96,
+      "content": "<|ln|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 97,
+      "content": "<|ha|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 98,
+      "content": "<|ba|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 99,
+      "content": "<|jw|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 100,
+      "content": "<|su|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 101,
+      "content": "<|translate|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 102,
+      "content": "<|transcribe|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 103,
+      "content": "<|startoflm|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 104,
+      "content": "<|startofprev|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 105,
+      "content": "<|nocaptions|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 106,
+      "content": "<|notimestamps|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1130,
+      "content": "<|tp|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "<|startoftranscript|>",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "<|notimestamps|>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "<|endoftext|>",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "SpecialToken": {
+          "id": "<|startoftranscript|>",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "<|notimestamps|>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "<|endoftext|>",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "<|endoftext|>": {
+        "id": "<|endoftext|>",
+        "ids": [
+          0
+        ],
+        "tokens": [
+          "<|endoftext|>"
+        ]
+      },
+      "<|notimestamps|>": {
+        "id": "<|notimestamps|>",
+        "ids": [
+          106
+        ],
+        "tokens": [
+          "<|notimestamps|>"
+        ]
+      },
+      "<|startoftranscript|>": {
+        "id": "<|startoftranscript|>",
+        "ids": [
+          1
+        ],
+        "tokens": [
+          "<|startoftranscript|>"
+        ]
+      }
+    }
+  },
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": "",
+    "end_of_word_suffix": "",
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "ignore_merges": false,
+    "vocab": {
+      "<|endoftext|>": 0,
+      "<|startoftranscript|>": 1,
+      "<|en|>": 2,
+      "<|zh|>": 3,
+      "<|de|>": 4,
+      "<|es|>": 5,
+      "<|ru|>": 6,
+      "<|ko|>": 7,
+      "<|fr|>": 8,
+      "<|ja|>": 9,
+      "<|pt|>": 10,
+      "<|tr|>": 11,
+      "<|pl|>": 12,
+      "<|ca|>": 13,
+      "<|nl|>": 14,
+      "<|ar|>": 15,
+      "<|sv|>": 16,
+      "<|it|>": 17,
+      "<|id|>": 18,
+      "<|hi|>": 19,
+      "<|fi|>": 20,
+      "<|vi|>": 21,
+      "<|he|>": 22,
+      "<|uk|>": 23,
+      "<|el|>": 24,
+      "<|ms|>": 25,
+      "<|cs|>": 26,
+      "<|ro|>": 27,
+      "<|da|>": 28,
+      "<|hu|>": 29,
+      "<|ta|>": 30,
+      "<|no|>": 31,
+      "<|th|>": 32,
+      "<|ur|>": 33,
+      "<|hr|>": 34,
+      "<|bg|>": 35,
+      "<|lt|>": 36,
+      "<|la|>": 37,
+      "<|mi|>": 38,
+      "<|ml|>": 39,
+      "<|cy|>": 40,
+      "<|sk|>": 41,
+      "<|te|>": 42,
+      "<|fa|>": 43,
+      "<|lv|>": 44,
+      "<|bn|>": 45,
+      "<|sr|>": 46,
+      "<|az|>": 47,
+      "<|sl|>": 48,
+      "<|kn|>": 49,
+      "<|et|>": 50,
+      "<|mk|>": 51,
+      "<|br|>": 52,
+      "<|eu|>": 53,
+      "<|is|>": 54,
+      "<|hy|>": 55,
+      "<|ne|>": 56,
+      "<|mn|>": 57,
+      "<|bs|>": 58,
+      "<|kk|>": 59,
+      "<|sq|>": 60,
+      "<|sw|>": 61,
+      "<|gl|>": 62,
+      "<|mr|>": 63,
+      "<|pa|>": 64,
+      "<|si|>": 65,
+      "<|km|>": 66,
+      "<|sn|>": 67,
+      "<|yo|>": 68,
+      "<|so|>": 69,
+      "<|af|>": 70,
+      "<|oc|>": 71,
+      "<|ka|>": 72,
+      "<|be|>": 73,
+      "<|tg|>": 74,
+      "<|sd|>": 75,
+      "<|gu|>": 76,
+      "<|am|>": 77,
+      "<|yi|>": 78,
+      "<|lo|>": 79,
+      "<|uz|>": 80,
+      "<|fo|>": 81,
+      "<|ht|>": 82,
+      "<|ps|>": 83,
+      "<|tk|>": 84,
+      "<|nn|>": 85,
+      "<|mt|>": 86,
+      "<|sa|>": 87,
+      "<|lb|>": 88,
+      "<|my|>": 89,
+      "<|bo|>": 90,
+      "<|tl|>": 91,
+      "<|mg|>": 92,
+      "<|as|>": 93,
+      "<|tt|>": 94,
+      "<|haw|>": 95,
+      "<|ln|>": 96,
+      "<|ha|>": 97,
+      "<|ba|>": 98,
+      "<|jw|>": 99,
+      "<|su|>": 100,
+      "<|translate|>": 101,
+      "<|transcribe|>": 102,
+      "<|startoflm|>": 103,
+      "<|startofprev|>": 104,
+      "<|nocaptions|>": 105,
+      "<|notimestamps|>": 106,
+      "!": 107,
+      "\"": 108,
+      "#": 109,
+      "$": 110,
+      "%": 111,
+      "&": 112,
+      "'": 113,
+      "(": 114,
+      ")": 115,
+      "*": 116,
+      "+": 117,
+      ",": 118,
+      "-": 119,
+      ".": 120,
+      "/": 121,
+      "0": 122,
+      "1": 123,
+      "2": 124,
+      "3": 125,
+      "4": 126,
+      "5": 127,
+      "6": 128,
+      "7": 129,
+      "8": 130,
+      "9": 131,
+      ":": 132,
+      ";": 133,
+      "<": 134,
+      "=": 135,
+      ">": 136,
+      "?": 137,
+      "@": 138,
+      "A": 139,
+      "B": 140,
+      "C": 141,
+      "D": 142,
+      "E": 143,
+      "F": 144,
+      "G": 145,
+      "H": 146,
+      "I": 147,
+      "J": 148,
+      "K": 149,
+      "L": 150,
+      "M": 151,
+      "N": 152,
+      "O": 153,
+      "P": 154,
+      "Q": 155,
+      "R": 156,
+      "S": 157,
+      "T": 158,
+      "U": 159,
+      "V": 160,
+      "W": 161,
+      "X": 162,
+      "Y": 163,
+      "Z": 164,
+      "[": 165,
+      "\\": 166,
+      "]": 167,
+      "^": 168,
+      "_": 169,
+      "`": 170,
+      "a": 171,
+      "b": 172,
+      "c": 173,
+      "d": 174,
+      "e": 175,
+      "f": 176,
+      "g": 177,
+      "h": 178,
+      "i": 179,
+      "j": 180,
+      "k": 181,
+      "l": 182,
+      "m": 183,
+      "n": 184,
+      "o": 185,
+      "p": 186,
+      "q": 187,
+      "r": 188,
+      "s": 189,
+      "t": 190,
+      "u": 191,
+      "v": 192,
+      "w": 193,
+      "x": 194,
+      "y": 195,
+      "z": 196,
+      "{": 197,
+      "|": 198,
+      "}": 199,
+      "~": 200,
+      "¡": 201,
+      "¢": 202,
+      "£": 203,
+      "¤": 204,
+      "¥": 205,
+      "¦": 206,
+      "§": 207,
+      "¨": 208,
+      "©": 209,
+      "ª": 210,
+      "«": 211,
+      "¬": 212,
+      "®": 213,
+      "¯": 214,
+      "°": 215,
+      "±": 216,
+      "²": 217,
+      "³": 218,
+      "´": 219,
+      "µ": 220,
+      "¶": 221,
+      "·": 222,
+      "¸": 223,
+      "¹": 224,
+      "º": 225,
+      "»": 226,
+      "¼": 227,
+      "½": 228,
+      "¾": 229,
+      "¿": 230,
+      "À": 231,
+      "Á": 232,
+      "Â": 233,
+      "Ã": 234,
+      "Ä": 235,
+      "Å": 236,
+      "Æ": 237,
+      "Ç": 238,
+      "È": 239,
+      "É": 240,
+      "Ê": 241,
+      "Ë": 242,
+      "Ì": 243,
+      "Í": 244,
+      "Î": 245,
+      "Ï": 246,
+      "Ð": 247,
+      "Ñ": 248,
+      "Ò": 249,
+      "Ó": 250,
+      "Ô": 251,
+      "Õ": 252,
+      "Ö": 253,
+      "×": 254,
+      "Ø": 255,
+      "Ù": 256,
+      "Ú": 257,
+      "Û": 258,
+      "Ü": 259,
+      "Ý": 260,
+      "Þ": 261,
+      "ß": 262,
+      "à": 263,
+      "á": 264,
+      "â": 265,
+      "ã": 266,
+      "ä": 267,
+      "å": 268,
+      "æ": 269,
+      "ç": 270,
+      "è": 271,
+      "é": 272,
+      "ê": 273,
+      "ë": 274,
+      "ì": 275,
+      "í": 276,
+      "î": 277,
+      "ï": 278,
+      "ð": 279,
+      "ñ": 280,
+      "ò": 281,
+      "ó": 282,
+      "ô": 283,
+      "õ": 284,
+      "ö": 285,
+      "÷": 286,
+      "ø": 287,
+      "ù": 288,
+      "ú": 289,
+      "û": 290,
+      "ü": 291,
+      "ý": 292,
+      "þ": 293,
+      "ÿ": 294,
+      "Ā": 295,
+      "ā": 296,
+      "Ă": 297,
+      "ă": 298,
+      "Ą": 299,
+      "ą": 300,
+      "Ć": 301,
+      "ć": 302,
+      "Ĉ": 303,
+      "ĉ": 304,
+      "Ċ": 305,
+      "ċ": 306,
+      "Č": 307,
+      "č": 308,
+      "Ď": 309,
+      "ď": 310,
+      "Đ": 311,
+      "đ": 312,
+      "Ē": 313,
+      "ē": 314,
+      "Ĕ": 315,
+      "ĕ": 316,
+      "Ė": 317,
+      "ė": 318,
+      "Ę": 319,
+      "ę": 320,
+      "Ě": 321,
+      "ě": 322,
+      "Ĝ": 323,
+      "ĝ": 324,
+      "Ğ": 325,
+      "ğ": 326,
+      "Ġ": 327,
+      "ġ": 328,
+      "Ģ": 329,
+      "ģ": 330,
+      "Ĥ": 331,
+      "ĥ": 332,
+      "Ħ": 333,
+      "ħ": 334,
+      "Ĩ": 335,
+      "ĩ": 336,
+      "Ī": 337,
+      "ī": 338,
+      "Ĭ": 339,
+      "ĭ": 340,
+      "Į": 341,
+      "į": 342,
+      "İ": 343,
+      "ı": 344,
+      "IJ": 345,
+      "ij": 346,
+      "Ĵ": 347,
+      "ĵ": 348,
+      "Ķ": 349,
+      "ķ": 350,
+      "ĸ": 351,
+      "Ĺ": 352,
+      "ĺ": 353,
+      "Ļ": 354,
+      "ļ": 355,
+      "Ľ": 356,
+      "ľ": 357,
+      "Ŀ": 358,
+      "ŀ": 359,
+      "Ł": 360,
+      "ł": 361,
+      "Ń": 362,
+      "Ġl": 363,
+      "na": 364,
+      "Ġli": 365,
+      "Ġt": 366,
+      "Ġp": 367,
+      "Ġs": 368,
+      "Ġm": 369,
+      "an": 370,
+      "Ġe": 371,
+      "Ġk": 372,
+      "li": 373,
+      "ona": 374,
+      "en": 375,
+      "wa": 376,
+      "al": 377,
+      "ni": 378,
+      "si": 379,
+      "Ġni": 380,
+      "ala": 381,
+      "Ġla": 382,
+      "Ġta": 383,
+      "Ġpi": 384,
+      "on": 385,
+      "jan": 386,
+      "Ġmi": 387,
+      "ki": 388,
+      "ma": 389,
+      "Ġsi": 390,
+      "Ġtawa": 391,
+      "te": 392,
+      "mi": 393,
+      "Ġlon": 394,
+      "Ġw": 395,
+      "Ġala": 396,
+      "Ġto": 397,
+      "il": 398,
+      "ama": 399,
+      "Ġpona": 400,
+      "Ġmu": 401,
+      "Ġo": 402,
+      "Ġjan": 403,
+      "Ġpa": 404,
+      "ke": 405,
+      "ka": 406,
+      "Ġsina": 407,
+      "Ġlu": 408,
+      "lin": 409,
+      "Ġkama": 410,
+      "so": 411,
+      "Ġona": 412,
+      "po": 413,
+      "Ġtoki": 414,
+      "ile": 415,
+      "Ġna": 416,
+      "enpo": 417,
+      "Ġsu": 418,
+      "Ġwile": 419,
+      "Ġse": 420,
+      "Ġi": 421,
+      "Ġmute": 422,
+      "pa": 423,
+      "sina": 424,
+      "Ġa": 425,
+      "Ġken": 426,
+      "lo": 427,
+      "pe": 428,
+      "kin": 429,
+      "me": 430,
+      "Ġan": 431,
+      "jo": 432,
+      "mo": 433,
+      "Ġsona": 434,
+      "Ġtan": 435,
+      "Ġlukin": 436,
+      "sa": 437,
+      "Ġpilin": 438,
+      "ken": 439,
+      "ale": 440,
+      "ta": 441,
+      "elo": 442,
+      "Ġike": 443,
+      "Ġtomo": 444,
+      "ku": 445,
+      "Ġale": 446,
+      "ilo": 447,
+      "wi": 448,
+      "Ġmo": 449,
+      "pu": 450,
+      "Ġku": 451,
+      "eli": 452,
+      "Ġseme": 453,
+      "sin": 454,
+      "Ġlili": 455,
+      "Ġtenpo": 456,
+      "Ġki": 457,
+      "Ġsuli": 458,
+      "Ġwa": 459,
+      "Ġke": 460,
+      "peken": 461,
+      "Ġpali": 462,
+      "Ġkepeken": 463,
+      "ja": 464,
+      "tenpo": 465,
+      "Ġma": 466,
+      "Ġpana": 467,
+      "pi": 468,
+      "Ġjo": 469,
+      "wen": 470,
+      "weli": 471,
+      "Ġtu": 472,
+      "Ġtaso": 473,
+      "un": 474,
+      "Ġante": 475,
+      "Ġmoku": 476,
+      "eka": 477,
+      "len": 478,
+      "Ġpo": 479,
+      "Ġweka": 480,
+      "kala": 481,
+      "Ġwan": 482,
+      "Ġluka": 483,
+      "Ġnasin": 484,
+      "Ġsin": 485,
+      "Ġolin": 486,
+      "ko": 487,
+      "npa": 488,
+      "Ġmusi": 489,
+      "Ġwawa": 490,
+      "Ġsama": 491,
+      "Ġkala": 492,
+      "no": 493,
+      "Ġtelo": 494,
+      "lu": 495,
+      "Ġawen": 496,
+      "Ġnimi": 497,
+      "je": 498,
+      "Ġnanpa": 499,
+      "ĠK": 500,
+      "telen": 501,
+      "ĠT": 502,
+      "Ġlawa": 503,
+      "Ġilo": 504,
+      "Ġso": 505,
+      "Ġlipu": 506,
+      "Ġpakala": 507,
+      "tu": 508,
+      "Ġpini": 509,
+      "Ġsitelen": 510,
+      "uta": 511,
+      "Ġsuno": 512,
+      "Ġsoweli": 513,
+      "Ġsewi": 514,
+      "Ġnasa": 515,
+      "ĠTu": 516,
+      "Ġen": 517,
+      "taso": 518,
+      "to": 519,
+      "jelo": 520,
+      "Ġkin": 521,
+      "Ġpoka": 522,
+      "lupu": 523,
+      "tuli": 524,
+      "Ġijo": 525,
+      "untuli": 526,
+      "ĠKuntuli": 527,
+      "le": 528,
+      "Ġlape": 529,
+      "Ġkute": 530,
+      "Ġka": 531,
+      "soweli": 532,
+      "Ġanu": 533,
+      "Ġlen": 534,
+      "Ġkalama": 535,
+      "Ġmon": 536,
+      "Ġsike": 537,
+      "Ġmoli": 538,
+      "Ġkasi": 539,
+      "pen": 540,
+      "Ġalasa": 541,
+      "Ġsuwi": 542,
+      "Ġanpa": 543,
+      "Ġkule": 544,
+      "kesi": 545,
+      "nsa": 546,
+      "Ġopen": 547,
+      "Ġja": 548,
+      "Ġkon": 549,
+      "Ġkulupu": 550,
+      "ĠS": 551,
+      "Ġu": 552,
+      "Ġinsa": 553,
+      "oje": 554,
+      "Ġ\"": 555,
+      "Ġloje": 556,
+      "Ġseli": 557,
+      "Ġkili": 558,
+      "tala": 559,
+      "la": 560,
+      "Ġali": 561,
+      "sun": 562,
+      "nasin": 563,
+      "pin": 564,
+      "Ġutala": 565,
+      "ani": 566,
+      "Ġpoki": 567,
+      "ena": 568,
+      "suta": 569,
+      "Ġsijelo": 570,
+      "Ġn": 571,
+      "Ġjaki": 572,
+      "ĠA": 573,
+      "ĠP": 574,
+      "Ġle": 575,
+      "Ġpan": 576,
+      "Ġmani": 577,
+      "Ġko": 578,
+      "meja": 579,
+      "Ġuta": 580,
+      "Ġpu": 581,
+      "Ġpimeja": 582,
+      "toki": 583,
+      "Ġmonsuta": 584,
+      "Ġnena": 585,
+      "Ġlin": 586,
+      "nimi": 587,
+      "Ġmije": 588,
+      "Ġmun": 589,
+      "Ġlupa": 590,
+      "ĠL": 591,
+      "Ġmama": 592,
+      "mako": 593,
+      "Ġnamako": 594,
+      "Ġsinpin": 595,
+      "tan": 596,
+      "Ġmeli": 597,
+      "Ġsupa": 598,
+      "Ġwaso": 599,
+      "tomo": 600,
+      "sike": 601,
+      "Ġakesi": 602,
+      "noka": 603,
+      "lon": 604,
+      "kasi": 605,
+      "Ġlinja": 606,
+      "mu": 607,
+      "Ġnoka": 608,
+      "Ġwalo": 609,
+      "akesi": 610,
+      "ĠM": 611,
+      "Ġun": 612,
+      "kulupu": 613,
+      "Ġkiwen": 614,
+      "pisi": 615,
+      "ĠAn": 616,
+      "ijo": 617,
+      "se": 618,
+      "san": 619,
+      "we": 620,
+      "Ġjelo": 621,
+      "Ġesun": 622,
+      "Ġlaso": 623,
+      "Ġpake": 624,
+      "Ġkipisi": 625,
+      "pan": 626,
+      "lipu": 627,
+      "telo": 628,
+      "Ġmonsi": 629,
+      "Ġlete": 630,
+      "Ġunpa": 631,
+      "alu": 632,
+      "kewi": 633,
+      "kalama": 634,
+      "sikeke": 635,
+      "ĠAnkewi": 636,
+      "ju": 637,
+      "sila": 638,
+      "Ġpalisa": 639,
+      "kalu": 640,
+      "ĠE": 641,
+      "sitelen": 642,
+      "tesan": 643,
+      "Ġselo": 644,
+      "takalu": 645,
+      "jetesan": 646,
+      "jetesantakalu": 647,
+      "waso": 648,
+      "Ġmisikeke": 649,
+      "pipi": 650,
+      "Ġpowe": 651,
+      "kosila": 652,
+      "suno": 653,
+      "ĠI": 654,
+      "onsi": 655,
+      "pali": 656,
+      "meli": 657,
+      "musi": 658,
+      "\".": 659,
+      "kon": 660,
+      "olin": 661,
+      "su": 662,
+      "âĢ": 663,
+      "ĠN": 664,
+      "Ġtonsi": 665,
+      "wawa": 666,
+      "Ġpipi": 667,
+      "mama": 668,
+      "Ġoko": 669,
+      "moku": 670,
+      "Ġleko": 671,
+      "Ġkokosila": 672,
+      "sona": 673,
+      "seme": 674,
+      "juna": 675,
+      "eso": 676,
+      "Ġmeso": 677,
+      "linja": 678,
+      "Ġmajuna": 679,
+      "lukin": 680,
+      "ĠSon": 681,
+      "ĠIn": 682,
+      "selo": 683,
+      "wile": 684,
+      "Ġlan": 685,
+      "sima": 686,
+      "kili": 687,
+      "pilin": 688,
+      "luka": 689,
+      "ĠKa": 690,
+      "ĠTe": 691,
+      "ĠLi": 692,
+      "ĠMe": 693,
+      "ĠInli": 694,
+      "Ġlanpan": 695,
+      "..": 696,
+      "ike": 697,
+      "seli": 698,
+      "ton": 699,
+      "wan": 700,
+      "sijelo": 701,
+      "kijetesantakalu": 702,
+      "Ġape": 703,
+      "pesi": 704,
+      "kule": 705,
+      "piku": 706,
+      "Ġsoko": 707,
+      "Ġjasima": 708,
+      "ĠPi": 709,
+      "ĠSonja": 710,
+      "Ġapeja": 711,
+      "ĠJ": 712,
+      "nanpa": 713,
+      "sinpin": 714,
+      "Ġkijetesantakalu": 715,
+      "lupa": 716,
+      "lawa": 717,
+      "ali": 718,
+      "nton": 719,
+      "ĠâĢ": 720,
+      "Ġte": 721,
+      "kiwen": 722,
+      "pakala": 723,
+      "winton": 724,
+      "luwi": 725,
+      "Ġlinluwi": 726,
+      "ĠLo": 727,
+      "ĠEwinton": 728,
+      "âĢĿ": 729,
+      "ĠNi": 730,
+      "ĠâĢľ": 731,
+      "lan": 732,
+      "ntu": 733,
+      "oko": 734,
+      "ĠW": 735,
+      "Ġmelo": 736,
+      "Ġepiku": 737,
+      "mije": 738,
+      "pini": 739,
+      "ĠKi": 740,
+      "ĠTo": 741,
+      "Ġkapesi": 742,
+      "ĠSa": 743,
+      "ĠSu": 744,
+      "ĠSan": 745,
+      "ĠSen": 746,
+      "ĠPa": 747,
+      "ĠPe": 748,
+      "ĠLa": 749,
+      "palisa": 750,
+      "ĠTelen": 751,
+      "ĠLisa": 752,
+      "Ġmelome": 753,
+      "awen": 754,
+      "mon": 755,
+      "mun": 756,
+      "pona": 757,
+      "ĠO": 758,
+      "nata": 759,
+      "lija": 760,
+      "poki": 761,
+      "sawi": 762,
+      "Ġkuntu": 763,
+      "jaki": 764,
+      "Ġpuwa": 765,
+      "ĠMi": 766,
+      "sewi": 767,
+      "supa": 768,
+      "ĠKanata": 769,
+      "ĠMewi": 770,
+      "...": 771,
+      "ĠJu": 772,
+      "ĠSeni": 773,
+      "monsuta": 774,
+      "epiku": 775,
+      "open": 776,
+      "ante": 777,
+      "sija": 778,
+      "Ġmijo": 779,
+      "misikeke": 780,
+      "amana": 781,
+      "poka": 782,
+      "sali": 783,
+      "ĠKu": 784,
+      "ĠKen": 785,
+      "ĠTa": 786,
+      "ĠSi": 787,
+      "ĠSamana": 788,
+      "Ġusawi": 789,
+      "lape": 790,
+      "lapi": 791,
+      "ĠPo": 792,
+      "mute": 793,
+      "panpo": 794,
+      "ĠElo": 795,
+      "ĠKapesi": 796,
+      "ĠKin": 797,
+      "ĠSupanpo": 798,
+      "ĠSanta": 799,
+      "ĠLasina": 800,
+      "ĠMewika": 801,
+      "Ġmijomi": 802,
+      "eko": 803,
+      "esun": 804,
+      "imi": 805,
+      "insa": 806,
+      "juta": 807,
+      "kama": 808,
+      "mala": 809,
+      "nena": 810,
+      "utala": 811,
+      "yu": 812,
+      "¼ģ": 813,
+      "ï¼ģ": 814,
+      "ĠU": 815,
+      "nasa": 816,
+      "Ġsan": 817,
+      "Ġete": 818,
+      "Ġkan": 819,
+      "wala": 820,
+      "sipin": 821,
+      "alata": 822,
+      "alasija": 823,
+      "onken": 824,
+      "Ġpasila": 825,
+      "keke": 826,
+      "pana": 827,
+      "pelan": 828,
+      "Ġkiki": 829,
+      "kokosila": 830,
+      "ĠKan": 831,
+      "ĠKeli": 832,
+      "ĠTimi": 833,
+      "Ġkamala": 834,
+      "ĠSo": 835,
+      "ĠAsi": 836,
+      "ĠPu": 837,
+      "ĠPan": 838,
+      "ĠPona": 839,
+      "ĠPalata": 840,
+      "ĠLe": 841,
+      "ĠMa": 842,
+      "ĠMalasija": 843,
+      "Ġunu": 844,
+      "ĠEko": 845,
+      "ĠEpelan": 846,
+      "ĠIta": 847,
+      "ĠNe": 848,
+      "ĠNu": 849,
+      "ĠSonko": 850,
+      "ĠLin": 851,
+      "ĠMekeke": 852,
+      "ĠPita": 853,
+      "ĠJonken": 854,
+      "ĠLola": 855,
+      "âĢĿ.": 856,
+      "ĠWa": 857,
+      "ĠTosi": 858,
+      "ĠToki": 859,
+      "ĠSusan": 860,
+      "ĠPepu": 861,
+      "ĠMisali": 862,
+      "ĠSiko": 863,
+      "lapisu": 864,
+      "ĠElopa": 865,
+      "ĠKinkili": 866,
+      "Ġkamalawala": 867,
+      "ĠEpelanto": 868,
+      "!\"": 869,
+      "\",": 870,
+      "\"?": 871,
+      ".\"": 872,
+      "?!": 873,
+      "Eko": 874,
+      "asin": 875,
+      "esi": 876,
+      "eta": 877,
+      "elon": 878,
+      "esija": 879,
+      "ije": 880,
+      "isipin": 881,
+      "jal": 882,
+      "jon": 883,
+      "jama": 884,
+      "kan": 885,
+      "lani": 886,
+      "man": 887,
+      "mani": 888,
+      "nu": 889,
+      "omi": 890,
+      "ose": 891,
+      "pon": 892,
+      "pil": 893,
+      "pani": 894,
+      "palu": 895,
+      "son": 896,
+      "sama": 897,
+      "tonsi": 898,
+      "upi": 899,
+      "wani": 900,
+      "Ġyu": 901,
+      "nawi": 902,
+      "naja": 903,
+      "Ġpeta": 904,
+      "anu": 905,
+      "anka": 906,
+      "anpa": 907,
+      "antan": 908,
+      "lia": 909,
+      "lisa": 910,
+      "liku": 911,
+      "lilan": 912,
+      "wasi": 913,
+      "wawi": 914,
+      "nija": 915,
+      "siko": 916,
+      "alasa": 917,
+      "Ġtaki": 918,
+      "onyu": 919,
+      "Ġmisa": 920,
+      "kini": 921,
+      "kijo": 922,
+      "kiko": 923,
+      "kimu": 924,
+      "kipisi": 925,
+      "kisan": 926,
+      "majuna": 927,
+      "telan": 928,
+      "mile": 929,
+      "ila": 930,
+      "Ġmulapisu": 931,
+      "Ġowe": 932,
+      "Ġojuta": 933,
+      "kepeken": 934,
+      "kenaja": 935,
+      "kaso": 936,
+      "katon": 937,
+      "kawan": 938,
+      "soko": 939,
+      "polo": 940,
+      "powe": 941,
+      "Ġisipin": 942,
+      "pajal": 943,
+      "pakawan": 944,
+      "loje": 945,
+      "peta": 946,
+      "peko": 947,
+      "meso": 948,
+      "mesu": 949,
+      "jole": 950,
+      "joju": 951,
+      "mosi": 952,
+      "momo": 953,
+      "moto": 954,
+      "salin": 955,
+      "tawa": 956,
+      "tawan": 957,
+      "tasali": 958,
+      "kukan": 959,
+      "wito": 960,
+      "pusi": 961,
+      "puwani": 962,
+      "Ġwale": 963,
+      "Ġkese": 964,
+      "jasima": 965,
+      "pili": 966,
+      "pimeja": 967,
+      "Ġtuli": 968,
+      "uneko": 969,
+      "kowa": 970,
+      "nokijo": 971,
+      "jesa": 972,
+      "jekenaja": 973,
+      "ĠKena": 974,
+      "ĠKijo": 975,
+      "ĠKelon": 976,
+      "ĠKomi": 977,
+      "ĠKila": 978,
+      "ĠTen": 979,
+      "ĠTonyu": 980,
+      "Ġsoto": 981,
+      "lete": 982,
+      "leko": 983,
+      "Ġkonwe": 984,
+      "ĠSuneko": 985,
+      "Ġumesu": 986,
+      "laso": 987,
+      "lasin": 988,
+      "ĠAli": 989,
+      "ĠAwi": 990,
+      "ĠAlapi": 991,
+      "ĠAman": 992,
+      "ĠAwawi": 993,
+      "ĠApolo": 994,
+      "ĠAtawan": 995,
+      "ĠAlasin": 996,
+      "ĠPuta": 997,
+      "ĠLuta": 998,
+      "ĠLupi": 999,
+      "ĠLantan": 1000,
+      "mulapisu": 1001,
+      "ĠMena": 1002,
+      "ĠMose": 1003,
+      "ĠManka": 1004,
+      "ĠAnse": 1005,
+      "ĠAnson": 1006,
+      "ĠAnkowa": 1007,
+      "ijosa": 1008,
+      "aluto": 1009,
+      "jusi": 1010,
+      "juwan": 1011,
+      "jukini": 1012,
+      "ĠEki": 1013,
+      "ĠElisa": 1014,
+      "ĠIlan": 1015,
+      "suli": 1016,
+      "suka": 1017,
+      "suwi": 1018,
+      "supan": 1019,
+      "ĠNasin": 1020,
+      "ĠNaluto": 1021,
+      "ĠInton": 1022,
+      "ĠKapil": 1023,
+      "ĠKajesa": 1024,
+      "ĠTepo": 1025,
+      "ĠTeja": 1026,
+      "ĠTewen": 1027,
+      "ĠTepani": 1028,
+      "ĠLilija": 1029,
+      "ĠLililan": 1030,
+      "ĠMelani": 1031,
+      "ĠMesiko": 1032,
+      "ĠMekiko": 1033,
+      "selija": 1034,
+      "ĠPiwi": 1035,
+      "ĠPisin": 1036,
+      "ĠPiju": 1037,
+      "ĠPinija": 1038,
+      "ĠPikaso": 1039,
+      "ĠPinokijo": 1040,
+      "ĠJan": 1041,
+      "Ġteje": 1042,
+      "ĠLopin": 1043,
+      "ĠLowasi": 1044,
+      "ĠLokaton": 1045,
+      "ĠLosupan": 1046,
+      "ĠNiki": 1047,
+      "ĠNimu": 1048,
+      "ĠNijon": 1049,
+      "ĠNipon": 1050,
+      "ĠNimile": 1051,
+      "ĠWeko": 1052,
+      "ĠWije": 1053,
+      "ĠWijosa": 1054,
+      "ĠKita": 1055,
+      "ĠKiliku": 1056,
+      "ĠToto": 1057,
+      "ĠSaku": 1058,
+      "ĠSasalin": 1059,
+      "ĠSajusi": 1060,
+      "ĠSentu": 1061,
+      "ĠPasi": 1062,
+      "ĠPakala": 1063,
+      "ĠPakisan": 1064,
+      "ĠPapuwani": 1065,
+      "ĠPewe": 1066,
+      "ĠPekimu": 1067,
+      "ĠPejoju": 1068,
+      "ĠLajo": 1069,
+      "ĠLawito": 1070,
+      "ĠOsin": 1071,
+      "ĠOwe": 1072,
+      "ĠOjuta": 1073,
+      "ĠOselija": 1074,
+      "ĠMimoku": 1075,
+      "ĠMijama": 1076,
+      "ĠJuli": 1077,
+      "ĠJuke": 1078,
+      "ĠJutu": 1079,
+      "ĠJulija": 1080,
+      "ĠKupa": 1081,
+      "ĠKulija": 1082,
+      "ĠKukukan": 1083,
+      "ĠTawi": 1084,
+      "ĠTapajal": 1085,
+      "ĠTajuwan": 1086,
+      "ĠPota": 1087,
+      "ĠPomoto": 1088,
+      "ĠPosuka": 1089,
+      "ĠUtu": 1090,
+      "ĠUsawi": 1091,
+      "ĠKanse": 1092,
+      "ĠKanpusi": 1093,
+      "ĠSomomo": 1094,
+      "ĠPutu": 1095,
+      "ĠPunawi": 1096,
+      "ĠPanto": 1097,
+      "ĠPantasali": 1098,
+      "ĠLewi": 1099,
+      "ĠLemosi": 1100,
+      "ĠMaku": 1101,
+      "ĠMasu": 1102,
+      "ĠItalija": 1103,
+      "ĠItalia": 1104,
+      "ĠNepalu": 1105,
+      "ĠNetelan": 1106,
+      "ĠNuken": 1107,
+      "ĠNuwan": 1108,
+      "ĠLinta": 1109,
+      "ĠLinja": 1110,
+      "ĠWajole": 1111,
+      "ĠWapili": 1112,
+      "esipo": 1113,
+      "Ġyupeko": 1114,
+      "Ġwaleja": 1115,
+      "ĠKenajekenaja": 1116,
+      "ĠKijoto": 1117,
+      "ĠKominu": 1118,
+      "ĠAnsetan": 1119,
+      "ĠElisape": 1120,
+      "ĠNasinesipo": 1121,
+      "ĠIntonesija": 1122,
+      "ĠKapilu": 1123,
+      "ĠKilikuntu": 1124,
+      "ĠPapuwanijukini": 1125,
+      "ĠTapajalo": 1126,
+      "ĠPomotolo": 1127,
+      "ĠPantasalipakawan": 1128,
+      "Ġyupekosi": 1129
+    },
+    "merges": [
+      "Ġ l",
+      "n a",
+      "Ġl i",
+      "Ġ t",
+      "�� p",
+      "Ġ s",
+      "Ġ m",
+      "a n",
+      "Ġ e",
+      "Ġ k",
+      "l i",
+      "o na",
+      "e n",
+      "w a",
+      "a l",
+      "n i",
+      "s i",
+      "Ġ ni",
+      "al a",
+      "Ġl a",
+      "Ġt a",
+      "Ġp i",
+      "o n",
+      "j an",
+      "Ġm i",
+      "k i",
+      "m a",
+      "Ġs i",
+      "Ġta wa",
+      "t e",
+      "m i",
+      "Ġl on",
+      "Ġ w",
+      "Ġ ala",
+      "Ġt o",
+      "i l",
+      "a ma",
+      "Ġp ona",
+      "Ġm u",
+      "Ġ o",
+      "Ġ jan",
+      "Ġp a",
+      "k e",
+      "k a",
+      "Ġsi na",
+      "Ġl u",
+      "li n",
+      "Ġk ama",
+      "s o",
+      "Ġ ona",
+      "p o",
+      "Ġto ki",
+      "il e",
+      "Ġ na",
+      "en po",
+      "Ġs u",
+      "Ġw ile",
+      "Ġs e",
+      "Ġ i",
+      "Ġmu te",
+      "p a",
+      "si na",
+      "Ġ a",
+      "Ġk en",
+      "l o",
+      "p e",
+      "ki n",
+      "m e",
+      "Ġ an",
+      "j o",
+      "m o",
+      "Ġs ona",
+      "Ġt an",
+      "Ġlu kin",
+      "s a",
+      "Ġpi lin",
+      "k en",
+      "al e",
+      "t a",
+      "e lo",
+      "Ġi ke",
+      "Ġto mo",
+      "k u",
+      "Ġ ale",
+      "il o",
+      "w i",
+      "Ġm o",
+      "p u",
+      "Ġk u",
+      "e li",
+      "Ġse me",
+      "si n",
+      "Ġli li",
+      "Ġt enpo",
+      "Ġk i",
+      "Ġsu li",
+      "Ġ wa",
+      "Ġk e",
+      "pe ken",
+      "Ġpa li",
+      "Ġke peken",
+      "j a",
+      "t enpo",
+      "Ġm a",
+      "Ġpa na",
+      "p i",
+      "Ġ jo",
+      "w en",
+      "w eli",
+      "Ġt u",
+      "Ġta so",
+      "u n",
+      "Ġan te",
+      "Ġmo ku",
+      "e ka",
+      "l en",
+      "Ġp o",
+      "Ġw eka",
+      "k ala",
+      "Ġw an",
+      "Ġlu ka",
+      "Ġna sin",
+      "Ġsi n",
+      "Ġo lin",
+      "k o",
+      "n pa",
+      "Ġmu si",
+      "Ġwa wa",
+      "Ġs ama",
+      "Ġk ala",
+      "n o",
+      "Ġt elo",
+      "l u",
+      "Ġa wen",
+      "Ġni mi",
+      "j e",
+      "Ġna npa",
+      "Ġ K",
+      "te len",
+      "Ġ T",
+      "Ġla wa",
+      "Ġ ilo",
+      "Ġs o",
+      "Ġli pu",
+      "Ġpa kala",
+      "t u",
+      "Ġpi ni",
+      "Ġsi telen",
+      "u ta",
+      "Ġsu no",
+      "Ġso weli",
+      "Ġse wi",
+      "Ġna sa",
+      "ĠT u",
+      "Ġe n",
+      "ta so",
+      "t o",
+      "j elo",
+      "Ġki n",
+      "Ġpo ka",
+      "lu pu",
+      "tu li",
+      "Ġi jo",
+      "un tuli",
+      "ĠK untuli",
+      "l e",
+      "Ġla pe",
+      "Ġku te",
+      "Ġk a",
+      "so weli",
+      "Ġan u",
+      "Ġl en",
+      "Ġkala ma",
+      "Ġm on",
+      "Ġsi ke",
+      "Ġmo li",
+      "Ġka si",
+      "p en",
+      "Ġala sa",
+      "Ġsu wi",
+      "Ġan pa",
+      "Ġku le",
+      "ke si",
+      "n sa",
+      "Ġo pen",
+      "Ġ ja",
+      "Ġk on",
+      "Ġku lupu",
+      "Ġ S",
+      "Ġ u",
+      "Ġi nsa",
+      "o je",
+      "Ġ \"",
+      "Ġl oje",
+      "Ġse li",
+      "Ġki li",
+      "t ala",
+      "l a",
+      "Ġa li",
+      "s un",
+      "na sin",
+      "pi n",
+      "Ġu tala",
+      "an i",
+      "Ġpo ki",
+      "e na",
+      "s uta",
+      "Ġsi jelo",
+      "Ġ n",
+      "Ġja ki",
+      "Ġ A",
+      "Ġ P",
+      "Ġl e",
+      "Ġp an",
+      "Ġm ani",
+      "Ġk o",
+      "me ja",
+      "Ġ uta",
+      "Ġp u",
+      "Ġpi meja",
+      "to ki",
+      "Ġmon suta",
+      "Ġn ena",
+      "Ġli n",
+      "ni mi",
+      "Ġmi je",
+      "Ġmu n",
+      "Ġlu pa",
+      "Ġ L",
+      "Ġm ama",
+      "ma ko",
+      "Ġna mako",
+      "Ġsin pin",
+      "t an",
+      "Ġm eli",
+      "Ġsu pa",
+      "Ġwa so",
+      "to mo",
+      "si ke",
+      "Ġa kesi",
+      "no ka",
+      "l on",
+      "ka si",
+      "Ġlin ja",
+      "m u",
+      "Ġ noka",
+      "Ġwa lo",
+      "a kesi",
+      "Ġ M",
+      "Ġ un",
+      "ku lupu",
+      "Ġki wen",
+      "pi si",
+      "ĠA n",
+      "i jo",
+      "s e",
+      "s an",
+      "w e",
+      "Ġ jelo",
+      "Ġe sun",
+      "Ġla so",
+      "Ġpa ke",
+      "Ġki pisi",
+      "p an",
+      "li pu",
+      "te lo",
+      "Ġmon si",
+      "Ġle te",
+      "Ġun pa",
+      "al u",
+      "ke wi",
+      "kala ma",
+      "sike ke",
+      "ĠAn kewi",
+      "j u",
+      "si la",
+      "Ġpali sa",
+      "k alu",
+      "Ġ E",
+      "si telen",
+      "te san",
+      "Ġse lo",
+      "ta kalu",
+      "je tesan",
+      "jetesan takalu",
+      "wa so",
+      "Ġmi sikeke",
+      "pi pi",
+      "Ġpo we",
+      "ko sila",
+      "sun o",
+      "Ġ I",
+      "on si",
+      "pa li",
+      "me li",
+      "mu si",
+      "\" .",
+      "k on",
+      "o lin",
+      "s u",
+      "â Ģ",
+      "Ġ N",
+      "Ġt onsi",
+      "wa wa",
+      "Ġpi pi",
+      "ma ma",
+      "Ġo ko",
+      "mo ku",
+      "Ġle ko",
+      "Ġko kosila",
+      "s ona",
+      "se me",
+      "ju na",
+      "e so",
+      "Ġm eso",
+      "lin ja",
+      "Ġma juna",
+      "lu kin",
+      "ĠS on",
+      "ĠI n",
+      "s elo",
+      "w ile",
+      "Ġl an",
+      "si ma",
+      "ki li",
+      "pi lin",
+      "lu ka",
+      "ĠK a",
+      "ĠT e",
+      "ĠL i",
+      "ĠM e",
+      "ĠIn li",
+      "Ġlan pan",
+      ". .",
+      "i ke",
+      "s eli",
+      "t on",
+      "w an",
+      "si jelo",
+      "ki jetesantakalu",
+      "Ġa pe",
+      "pe si",
+      "ku le",
+      "pi ku",
+      "Ġso ko",
+      "Ġja sima",
+      "ĠP i",
+      "ĠSon ja",
+      "Ġape ja",
+      "Ġ J",
+      "na npa",
+      "sin pin",
+      "Ġki jetesantakalu",
+      "lu pa",
+      "la wa",
+      "a li",
+      "n ton",
+      "Ġ âĢ",
+      "Ġt e",
+      "ki wen",
+      "pa kala",
+      "wi nton",
+      "lu wi",
+      "Ġlin luwi",
+      "ĠL o",
+      "ĠE winton",
+      "âĢ Ŀ",
+      "ĠN i",
+      "ĠâĢ ľ",
+      "l an",
+      "n tu",
+      "o ko",
+      "Ġ W",
+      "Ġm elo",
+      "Ġe piku",
+      "mi je",
+      "pi ni",
+      "ĠK i",
+      "ĠT o",
+      "Ġka pesi",
+      "ĠS a",
+      "ĠS u",
+      "ĠS an",
+      "ĠS en",
+      "ĠP a",
+      "ĠP e",
+      "ĠL a",
+      "pali sa",
+      "ĠTe len",
+      "ĠLi sa",
+      "Ġmelo me",
+      "a wen",
+      "m on",
+      "m un",
+      "p ona",
+      "Ġ O",
+      "na ta",
+      "li ja",
+      "po ki",
+      "sa wi",
+      "Ġku ntu",
+      "ja ki",
+      "Ġpu wa",
+      "ĠM i",
+      "se wi",
+      "su pa",
+      "ĠKa nata",
+      "ĠMe wi",
+      ".. .",
+      "ĠJ u",
+      "ĠSen i",
+      "mon suta",
+      "e piku",
+      "o pen",
+      "an te",
+      "si ja",
+      "Ġmi jo",
+      "mi sikeke",
+      "ama na",
+      "po ka",
+      "sa li",
+      "ĠK u",
+      "ĠK en",
+      "ĠT a",
+      "ĠS i",
+      "ĠS amana",
+      "Ġu sawi",
+      "la pe",
+      "la pi",
+      "ĠP o",
+      "mu te",
+      "pan po",
+      "ĠE lo",
+      "ĠKa pesi",
+      "ĠKi n",
+      "ĠSu panpo",
+      "ĠSan ta",
+      "ĠLa sina",
+      "ĠMewi ka",
+      "Ġmijo mi",
+      "e ko",
+      "e sun",
+      "i mi",
+      "i nsa",
+      "j uta",
+      "k ama",
+      "m ala",
+      "n ena",
+      "u tala",
+      "y u",
+      "¼ ģ",
+      "ï ¼ģ",
+      "Ġ U",
+      "na sa",
+      "Ġs an",
+      "Ġe te",
+      "Ġk an",
+      "wa la",
+      "si pin",
+      "ala ta",
+      "ala sija",
+      "on ken",
+      "Ġpa sila",
+      "ke ke",
+      "pa na",
+      "pe lan",
+      "Ġki ki",
+      "ko kosila",
+      "ĠK an",
+      "ĠK eli",
+      "ĠT imi",
+      "Ġka mala",
+      "ĠS o",
+      "ĠA si",
+      "ĠP u",
+      "ĠP an",
+      "ĠP ona",
+      "ĠP alata",
+      "ĠL e",
+      "ĠM a",
+      "ĠM alasija",
+      "Ġun u",
+      "ĠE ko",
+      "ĠE pelan",
+      "ĠI ta",
+      "ĠN e",
+      "ĠN u",
+      "ĠSon ko",
+      "ĠLi n",
+      "ĠMe keke",
+      "ĠPi ta",
+      "ĠJ onken",
+      "ĠLo la",
+      "âĢĿ .",
+      "ĠW a",
+      "ĠTo si",
+      "ĠTo ki",
+      "ĠSu san",
+      "ĠPe pu",
+      "ĠMi sali",
+      "ĠSi ko",
+      "lapi su",
+      "ĠElo pa",
+      "ĠKin kili",
+      "Ġkamala wala",
+      "ĠEpelan to",
+      "! \"",
+      "\" ,",
+      "\" ?",
+      ". \"",
+      "? !",
+      "E ko",
+      "a sin",
+      "e si",
+      "e ta",
+      "e lon",
+      "e sija",
+      "i je",
+      "i sipin",
+      "j al",
+      "j on",
+      "j ama",
+      "k an",
+      "l ani",
+      "m an",
+      "m ani",
+      "n u",
+      "o mi",
+      "o se",
+      "p on",
+      "p il",
+      "p ani",
+      "p alu",
+      "s on",
+      "s ama",
+      "t onsi",
+      "u pi",
+      "w ani",
+      "Ġ yu",
+      "na wi",
+      "na ja",
+      "Ġp eta",
+      "an u",
+      "an ka",
+      "an pa",
+      "an tan",
+      "li a",
+      "li sa",
+      "li ku",
+      "li lan",
+      "wa si",
+      "wa wi",
+      "ni ja",
+      "si ko",
+      "ala sa",
+      "Ġta ki",
+      "on yu",
+      "Ġmi sa",
+      "ki ni",
+      "ki jo",
+      "ki ko",
+      "ki mu",
+      "ki pisi",
+      "ki san",
+      "ma juna",
+      "te lan",
+      "mi le",
+      "il a",
+      "Ġmu lapisu",
+      "Ġo we",
+      "Ġo juta",
+      "ke peken",
+      "ke naja",
+      "ka so",
+      "ka ton",
+      "ka wan",
+      "so ko",
+      "po lo",
+      "po we",
+      "Ġi sipin",
+      "pa jal",
+      "pa kawan",
+      "lo je",
+      "pe ta",
+      "pe ko",
+      "me so",
+      "me su",
+      "jo le",
+      "jo ju",
+      "mo si",
+      "mo mo",
+      "mo to",
+      "sa lin",
+      "ta wa",
+      "ta wan",
+      "ta sali",
+      "ku kan",
+      "wi to",
+      "pu si",
+      "pu wani",
+      "Ġwa le",
+      "Ġke se",
+      "ja sima",
+      "pi li",
+      "pi meja",
+      "Ġtu li",
+      "un eko",
+      "ko wa",
+      "no kijo",
+      "je sa",
+      "je kenaja",
+      "ĠK ena",
+      "ĠK ijo",
+      "ĠK elon",
+      "ĠK omi",
+      "ĠK ila",
+      "ĠT en",
+      "ĠT onyu",
+      "Ġso to",
+      "le te",
+      "le ko",
+      "Ġkon we",
+      "ĠS uneko",
+      "Ġu mesu",
+      "la so",
+      "la sin",
+      "ĠA li",
+      "ĠA wi",
+      "ĠA lapi",
+      "ĠA man",
+      "ĠA wawi",
+      "ĠA polo",
+      "ĠA tawan",
+      "ĠA lasin",
+      "ĠP uta",
+      "ĠL uta",
+      "ĠL upi",
+      "ĠL antan",
+      "mu lapisu",
+      "ĠM ena",
+      "ĠM ose",
+      "ĠM anka",
+      "ĠAn se",
+      "ĠAn son",
+      "ĠAn kowa",
+      "ijo sa",
+      "alu to",
+      "ju si",
+      "ju wan",
+      "ju kini",
+      "ĠE ki",
+      "ĠE lisa",
+      "ĠI lan",
+      "su li",
+      "su ka",
+      "su wi",
+      "su pan",
+      "ĠN asin",
+      "ĠN aluto",
+      "ĠIn ton",
+      "ĠKa pil",
+      "ĠKa jesa",
+      "ĠTe po",
+      "ĠTe ja",
+      "ĠTe wen",
+      "ĠTe pani",
+      "ĠLi lija",
+      "ĠLi lilan",
+      "ĠMe lani",
+      "ĠMe siko",
+      "ĠMe kiko",
+      "seli ja",
+      "ĠPi wi",
+      "ĠPi sin",
+      "ĠPi ju",
+      "ĠPi nija",
+      "ĠPi kaso",
+      "ĠPi nokijo",
+      "ĠJ an",
+      "Ġte je",
+      "ĠLo pin",
+      "ĠLo wasi",
+      "ĠLo katon",
+      "ĠLo supan",
+      "ĠNi ki",
+      "ĠNi mu",
+      "ĠNi jon",
+      "ĠNi pon",
+      "ĠNi mile",
+      "ĠW eko",
+      "ĠW ije",
+      "ĠW ijosa",
+      "ĠKi ta",
+      "ĠKi liku",
+      "ĠTo to",
+      "ĠSa ku",
+      "ĠSa salin",
+      "ĠSa jusi",
+      "ĠSen tu",
+      "ĠPa si",
+      "ĠPa kala",
+      "ĠPa kisan",
+      "ĠPa puwani",
+      "ĠPe we",
+      "ĠPe kimu",
+      "ĠPe joju",
+      "ĠLa jo",
+      "ĠLa wito",
+      "ĠO sin",
+      "ĠO we",
+      "ĠO juta",
+      "ĠO selija",
+      "ĠMi moku",
+      "ĠMi jama",
+      "ĠJu li",
+      "ĠJu ke",
+      "ĠJu tu",
+      "ĠJu lija",
+      "ĠKu pa",
+      "ĠKu lija",
+      "ĠKu kukan",
+      "ĠTa wi",
+      "ĠTa pajal",
+      "ĠTa juwan",
+      "ĠPo ta",
+      "ĠPo moto",
+      "ĠPo suka",
+      "ĠU tu",
+      "ĠU sawi",
+      "ĠKan se",
+      "ĠKan pusi",
+      "ĠSo momo",
+      "ĠPu tu",
+      "ĠPu nawi",
+      "ĠPan to",
+      "ĠPan tasali",
+      "ĠLe wi",
+      "ĠLe mosi",
+      "ĠMa ku",
+      "ĠMa su",
+      "ĠIta lija",
+      "ĠIta lia",
+      "ĠNe palu",
+      "ĠNe telan",
+      "ĠNu ken",
+      "ĠNu wan",
+      "ĠLin ta",
+      "ĠLin ja",
+      "ĠWa jole",
+      "ĠWa pili",
+      "esi po",
+      "Ġyu peko",
+      "Ġwale ja",
+      "ĠKena jekenaja",
+      "ĠKijo to",
+      "ĠKomi nu",
+      "ĠAnse tan",
+      "ĠElisa pe",
+      "ĠNasin esipo",
+      "ĠInton esija",
+      "ĠKapil u",
+      "ĠKiliku ntu",
+      "ĠPapuwani jukini",
+      "ĠTapajal o",
+      "ĠPomoto lo",
+      "ĠPantasali pakawan",
+      "Ġyupeko si"
+    ]
+  }
+}

tokenizer_config.json

@@ -0,0 +1,990 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftranscript|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|en|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|zh|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<|de|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|es|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|ru|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|ko|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<|fr|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<|ja|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<|pt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|tr|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<|pl|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<|ca|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<|nl|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<|ar|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<|sv|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<|it|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<|id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "<|hi|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "<|fi|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "<|vi|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "22": {
+      "content": "<|he|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "23": {
+      "content": "<|uk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24": {
+      "content": "<|el|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "25": {
+      "content": "<|ms|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "26": {
+      "content": "<|cs|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "27": {
+      "content": "<|ro|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "28": {
+      "content": "<|da|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "29": {
+      "content": "<|hu|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30": {
+      "content": "<|ta|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31": {
+      "content": "<|no|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "<|th|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "33": {
+      "content": "<|ur|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "34": {
+      "content": "<|hr|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35": {
+      "content": "<|bg|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36": {
+      "content": "<|lt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "37": {
+      "content": "<|la|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "38": {
+      "content": "<|mi|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "39": {
+      "content": "<|ml|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "40": {
+      "content": "<|cy|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "41": {
+      "content": "<|sk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "42": {
+      "content": "<|te|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "43": {
+      "content": "<|fa|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "44": {
+      "content": "<|lv|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "45": {
+      "content": "<|bn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "46": {
+      "content": "<|sr|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "47": {
+      "content": "<|az|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "48": {
+      "content": "<|sl|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49": {
+      "content": "<|kn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50": {
+      "content": "<|et|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "51": {
+      "content": "<|mk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "52": {
+      "content": "<|br|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "53": {
+      "content": "<|eu|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "54": {
+      "content": "<|is|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "55": {
+      "content": "<|hy|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "56": {
+      "content": "<|ne|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57": {
+      "content": "<|mn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58": {
+      "content": "<|bs|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "59": {
+      "content": "<|kk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "60": {
+      "content": "<|sq|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "61": {
+      "content": "<|sw|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "62": {
+      "content": "<|gl|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "63": {
+      "content": "<|mr|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64": {
+      "content": "<|pa|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65": {
+      "content": "<|si|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "66": {
+      "content": "<|km|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "67": {
+      "content": "<|sn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "68": {
+      "content": "<|yo|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "69": {
+      "content": "<|so|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "70": {
+      "content": "<|af|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "71": {
+      "content": "<|oc|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "72": {
+      "content": "<|ka|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73": {
+      "content": "<|be|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "74": {
+      "content": "<|tg|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75": {
+      "content": "<|sd|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "76": {
+      "content": "<|gu|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "77": {
+      "content": "<|am|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "78": {
+      "content": "<|yi|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "79": {
+      "content": "<|lo|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "80": {
+      "content": "<|uz|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "81": {
+      "content": "<|fo|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "82": {
+      "content": "<|ht|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "83": {
+      "content": "<|ps|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "84": {
+      "content": "<|tk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "85": {
+      "content": "<|nn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "86": {
+      "content": "<|mt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "87": {
+      "content": "<|sa|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "88": {
+      "content": "<|lb|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "89": {
+      "content": "<|my|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "90": {
+      "content": "<|bo|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "91": {
+      "content": "<|tl|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92": {
+      "content": "<|mg|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "93": {
+      "content": "<|as|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "94": {
+      "content": "<|tt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "95": {
+      "content": "<|haw|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96": {
+      "content": "<|ln|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "97": {
+      "content": "<|ha|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "98": {
+      "content": "<|ba|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "99": {
+      "content": "<|jw|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "<|su|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "<|translate|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "<|transcribe|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "<|startoflm|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "<|startofprev|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "105": {
+      "content": "<|nocaptions|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<|notimestamps|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1130": {
+      "content": "<|tp|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|startoftranscript|>",
+    "<|en|>",
+    "<|zh|>",
+    "<|de|>",
+    "<|es|>",
+    "<|ru|>",
+    "<|ko|>",
+    "<|fr|>",
+    "<|ja|>",
+    "<|pt|>",
+    "<|tr|>",
+    "<|pl|>",
+    "<|ca|>",
+    "<|nl|>",
+    "<|ar|>",
+    "<|sv|>",
+    "<|it|>",
+    "<|id|>",
+    "<|hi|>",
+    "<|fi|>",
+    "<|vi|>",
+    "<|he|>",
+    "<|uk|>",
+    "<|el|>",
+    "<|ms|>",
+    "<|cs|>",
+    "<|ro|>",
+    "<|da|>",
+    "<|hu|>",
+    "<|ta|>",
+    "<|no|>",
+    "<|th|>",
+    "<|ur|>",
+    "<|hr|>",
+    "<|bg|>",
+    "<|lt|>",
+    "<|la|>",
+    "<|mi|>",
+    "<|ml|>",
+    "<|cy|>",
+    "<|sk|>",
+    "<|te|>",
+    "<|fa|>",
+    "<|lv|>",
+    "<|bn|>",
+    "<|sr|>",
+    "<|az|>",
+    "<|sl|>",
+    "<|kn|>",
+    "<|et|>",
+    "<|mk|>",
+    "<|br|>",
+    "<|eu|>",
+    "<|is|>",
+    "<|hy|>",
+    "<|ne|>",
+    "<|mn|>",
+    "<|bs|>",
+    "<|kk|>",
+    "<|sq|>",
+    "<|sw|>",
+    "<|gl|>",
+    "<|mr|>",
+    "<|pa|>",
+    "<|si|>",
+    "<|km|>",
+    "<|sn|>",
+    "<|yo|>",
+    "<|so|>",
+    "<|af|>",
+    "<|oc|>",
+    "<|ka|>",
+    "<|be|>",
+    "<|tg|>",
+    "<|sd|>",
+    "<|gu|>",
+    "<|am|>",
+    "<|yi|>",
+    "<|lo|>",
+    "<|uz|>",
+    "<|fo|>",
+    "<|ht|>",
+    "<|ps|>",
+    "<|tk|>",
+    "<|nn|>",
+    "<|mt|>",
+    "<|sa|>",
+    "<|lb|>",
+    "<|my|>",
+    "<|bo|>",
+    "<|tl|>",
+    "<|mg|>",
+    "<|as|>",
+    "<|tt|>",
+    "<|haw|>",
+    "<|ln|>",
+    "<|ha|>",
+    "<|ba|>",
+    "<|jw|>",
+    "<|su|>",
+    "<|translate|>",
+    "<|transcribe|>",
+    "<|startoflm|>",
+    "<|startofprev|>",
+    "<|nocaptions|>",
+    "<|notimestamps|>",
+    "<|tp|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "tokenizer_class": "WhisperTokenizer",
+  "unk_token": "<|endoftext|>"
+}

vocab.json

@@ -0,0 +1 @@
+{"<|endoftext|>":0,"<|startoftranscript|>":1,"<|en|>":2,"<|zh|>":3,"<|de|>":4,"<|es|>":5,"<|ru|>":6,"<|ko|>":7,"<|fr|>":8,"<|ja|>":9,"<|pt|>":10,"<|tr|>":11,"<|pl|>":12,"<|ca|>":13,"<|nl|>":14,"<|ar|>":15,"<|sv|>":16,"<|it|>":17,"<|id|>":18,"<|hi|>":19,"<|fi|>":20,"<|vi|>":21,"<|he|>":22,"<|uk|>":23,"<|el|>":24,"<|ms|>":25,"<|cs|>":26,"<|ro|>":27,"<|da|>":28,"<|hu|>":29,"<|ta|>":30,"<|no|>":31,"<|th|>":32,"<|ur|>":33,"<|hr|>":34,"<|bg|>":35,"<|lt|>":36,"<|la|>":37,"<|mi|>":38,"<|ml|>":39,"<|cy|>":40,"<|sk|>":41,"<|te|>":42,"<|fa|>":43,"<|lv|>":44,"<|bn|>":45,"<|sr|>":46,"<|az|>":47,"<|sl|>":48,"<|kn|>":49,"<|et|>":50,"<|mk|>":51,"<|br|>":52,"<|eu|>":53,"<|is|>":54,"<|hy|>":55,"<|ne|>":56,"<|mn|>":57,"<|bs|>":58,"<|kk|>":59,"<|sq|>":60,"<|sw|>":61,"<|gl|>":62,"<|mr|>":63,"<|pa|>":64,"<|si|>":65,"<|km|>":66,"<|sn|>":67,"<|yo|>":68,"<|so|>":69,"<|af|>":70,"<|oc|>":71,"<|ka|>":72,"<|be|>":73,"<|tg|>":74,"<|sd|>":75,"<|gu|>":76,"<|am|>":77,"<|yi|>":78,"<|lo|>":79,"<|uz|>":80,"<|fo|>":81,"<|ht|>":82,"<|ps|>":83,"<|tk|>":84,"<|nn|>":85,"<|mt|>":86,"<|sa|>":87,"<|lb|>":88,"<|my|>":89,"<|bo|>":90,"<|tl|>":91,"<|mg|>":92,"<|as|>":93,"<|tt|>":94,"<|haw|>":95,"<|ln|>":96,"<|ha|>":97,"<|ba|>":98,"<|jw|>":99,"<|su|>":100,"<|translate|>":101,"<|transcribe|>":102,"<|startoflm|>":103,"<|startofprev|>":104,"<|nocaptions|>":105,"<|notimestamps|>":106,"!":107,"\"":108,"#":109,"$":110,"%":111,"&":112,"'":113,"(":114,")":115,"*":116,"+":117,",":118,"-":119,".":120,"/":121,"0":122,"1":123,"2":124,"3":125,"4":126,"5":127,"6":128,"7":129,"8":130,"9":131,":":132,";":133,"<":134,"=":135,">":136,"?":137,"@":138,"A":139,"B":140,"C":141,"D":142,"E":143,"F":144,"G":145,"H":146,"I":147,"J":148,"K":149,"L":150,"M":151,"N":152,"O":153,"P":154,"Q":155,"R":156,"S":157,"T":158,"U":159,"V":160,"W":161,"X":162,"Y":163,"Z":164,"[":165,"\\":166,"]":167,"^":168,"_":169,"`":170,"a":171,"b":172,"c":173,"d":174,"e":175,"f":176,"g":177,"h":178,"i":179,"j":180,"k":181,"l":182,"m":183,"n":184,"o":185,"p":186,"q":187,"r":188,"s":189,"t":190,"u":191,"v":192,"w":193,"x":194,"y":195,"z":196,"{":197,"|":198,"}":199,"~":200,"¡":201,"¢":202,"£":203,"¤":204,"¥":205,"¦":206,"§":207,"¨":208,"©":209,"ª":210,"«":211,"¬":212,"®":213,"¯":214,"°":215,"±":216,"²":217,"³":218,"´":219,"µ":220,"¶":221,"·":222,"¸":223,"¹":224,"º":225,"»":226,"¼":227,"½":228,"¾":229,"¿":230,"À":231,"Á":232,"Â":233,"Ã":234,"Ä":235,"Å":236,"Æ":237,"Ç":238,"È":239,"É":240,"Ê":241,"Ë":242,"Ì":243,"Í":244,"Î":245,"Ï":246,"Ð":247,"Ñ":248,"Ò":249,"Ó":250,"Ô":251,"Õ":252,"Ö":253,"×":254,"Ø":255,"Ù":256,"Ú":257,"Û":258,"Ü":259,"Ý":260,"Þ":261,"ß":262,"à":263,"á":264,"â":265,"ã":266,"ä":267,"å":268,"æ":269,"ç":270,"è":271,"é":272,"ê":273,"ë":274,"ì":275,"í":276,"î":277,"ï":278,"ð":279,"ñ":280,"ò":281,"ó":282,"ô":283,"õ":284,"ö":285,"÷":286,"ø":287,"ù":288,"ú":289,"û":290,"ü":291,"ý":292,"þ":293,"ÿ":294,"Ā":295,"ā":296,"Ă":297,"ă":298,"Ą":299,"ą":300,"Ć":301,"ć":302,"Ĉ":303,"ĉ":304,"Ċ":305,"ċ":306,"Č":307,"č":308,"Ď":309,"ď":310,"Đ":311,"đ":312,"Ē":313,"ē":314,"Ĕ":315,"ĕ":316,"Ė":317,"ė":318,"Ę":319,"ę":320,"Ě":321,"ě":322,"Ĝ":323,"ĝ":324,"Ğ":325,"ğ":326,"Ġ":327,"ġ":328,"Ģ":329,"ģ":330,"Ĥ":331,"ĥ":332,"Ħ":333,"ħ":334,"Ĩ":335,"ĩ":336,"Ī":337,"ī":338,"Ĭ":339,"ĭ":340,"Į":341,"į":342,"İ":343,"ı":344,"IJ":345,"ij":346,"Ĵ":347,"ĵ":348,"Ķ":349,"ķ":350,"ĸ":351,"Ĺ":352,"ĺ":353,"Ļ":354,"ļ":355,"Ľ":356,"ľ":357,"Ŀ":358,"ŀ":359,"Ł":360,"ł":361,"Ń":362,"Ġl":363,"na":364,"Ġli":365,"Ġt":366,"Ġp":367,"Ġs":368,"Ġm":369,"an":370,"Ġe":371,"Ġk":372,"li":373,"ona":374,"en":375,"wa":376,"al":377,"ni":378,"si":379,"Ġni":380,"ala":381,"Ġla":382,"Ġta":383,"Ġpi":384,"on":385,"jan":386,"Ġmi":387,"ki":388,"ma":389,"Ġsi":390,"Ġtawa":391,"te":392,"mi":393,"Ġlon":394,"Ġw":395,"Ġala":396,"Ġto":397,"il":398,"ama":399,"Ġpona":400,"Ġmu":401,"Ġo":402,"Ġjan":403,"Ġpa":404,"ke":405,"ka":406,"Ġsina":407,"Ġlu":408,"lin":409,"Ġkama":410,"so":411,"Ġona":412,"po":413,"Ġtoki":414,"ile":415,"Ġna":416,"enpo":417,"Ġsu":418,"Ġwile":419,"Ġse":420,"Ġi":421,"Ġmute":422,"pa":423,"sina":424,"Ġa":425,"Ġken":426,"lo":427,"pe":428,"kin":429,"me":430,"Ġan":431,"jo":432,"mo":433,"Ġsona":434,"Ġtan":435,"Ġlukin":436,"sa":437,"Ġpilin":438,"ken":439,"ale":440,"ta":441,"elo":442,"Ġike":443,"Ġtomo":444,"ku":445,"Ġale":446,"ilo":447,"wi":448,"Ġmo":449,"pu":450,"Ġku":451,"eli":452,"Ġseme":453,"sin":454,"Ġlili":455,"Ġtenpo":456,"Ġki":457,"Ġsuli":458,"Ġwa":459,"Ġke":460,"peken":461,"Ġpali":462,"Ġkepeken":463,"ja":464,"tenpo":465,"Ġma":466,"Ġpana":467,"pi":468,"Ġjo":469,"wen":470,"weli":471,"Ġtu":472,"Ġtaso":473,"un":474,"Ġante":475,"Ġmoku":476,"eka":477,"len":478,"Ġpo":479,"Ġweka":480,"kala":481,"Ġwan":482,"Ġluka":483,"Ġnasin":484,"Ġsin":485,"Ġolin":486,"ko":487,"npa":488,"Ġmusi":489,"Ġwawa":490,"Ġsama":491,"Ġkala":492,"no":493,"Ġtelo":494,"lu":495,"Ġawen":496,"Ġnimi":497,"je":498,"Ġnanpa":499,"ĠK":500,"telen":501,"ĠT":502,"Ġlawa":503,"Ġilo":504,"Ġso":505,"Ġlipu":506,"Ġpakala":507,"tu":508,"Ġpini":509,"Ġsitelen":510,"uta":511,"Ġsuno":512,"Ġsoweli":513,"Ġsewi":514,"Ġnasa":515,"ĠTu":516,"Ġen":517,"taso":518,"to":519,"jelo":520,"Ġkin":521,"Ġpoka":522,"lupu":523,"tuli":524,"Ġijo":525,"untuli":526,"ĠKuntuli":527,"le":528,"Ġlape":529,"Ġkute":530,"Ġka":531,"soweli":532,"Ġanu":533,"Ġlen":534,"Ġkalama":535,"Ġmon":536,"Ġsike":537,"Ġmoli":538,"Ġkasi":539,"pen":540,"Ġalasa":541,"Ġsuwi":542,"Ġanpa":543,"Ġkule":544,"kesi":545,"nsa":546,"Ġopen":547,"Ġja":548,"Ġkon":549,"Ġkulupu":550,"ĠS":551,"Ġu":552,"Ġinsa":553,"oje":554,"Ġ\"":555,"Ġloje":556,"Ġseli":557,"Ġkili":558,"tala":559,"la":560,"Ġali":561,"sun":562,"nasin":563,"pin":564,"Ġutala":565,"ani":566,"Ġpoki":567,"ena":568,"suta":569,"Ġsijelo":570,"Ġn":571,"Ġjaki":572,"ĠA":573,"ĠP":574,"Ġle":575,"Ġpan":576,"Ġmani":577,"Ġko":578,"meja":579,"Ġuta":580,"Ġpu":581,"Ġpimeja":582,"toki":583,"Ġmonsuta":584,"Ġnena":585,"Ġlin":586,"nimi":587,"Ġmije":588,"Ġmun":589,"Ġlupa":590,"ĠL":591,"Ġmama":592,"mako":593,"Ġnamako":594,"Ġsinpin":595,"tan":596,"Ġmeli":597,"Ġsupa":598,"Ġwaso":599,"tomo":600,"sike":601,"Ġakesi":602,"noka":603,"lon":604,"kasi":605,"Ġlinja":606,"mu":607,"Ġnoka":608,"Ġwalo":609,"akesi":610,"ĠM":611,"Ġun":612,"kulupu":613,"Ġkiwen":614,"pisi":615,"ĠAn":616,"ijo":617,"se":618,"san":619,"we":620,"Ġjelo":621,"Ġesun":622,"Ġlaso":623,"Ġpake":624,"Ġkipisi":625,"pan":626,"lipu":627,"telo":628,"Ġmonsi":629,"Ġlete":630,"Ġunpa":631,"alu":632,"kewi":633,"kalama":634,"sikeke":635,"ĠAnkewi":636,"ju":637,"sila":638,"Ġpalisa":639,"kalu":640,"ĠE":641,"sitelen":642,"tesan":643,"Ġselo":644,"takalu":645,"jetesan":646,"jetesantakalu":647,"waso":648,"Ġmisikeke":649,"pipi":650,"Ġpowe":651,"kosila":652,"suno":653,"ĠI":654,"onsi":655,"pali":656,"meli":657,"musi":658,"\".":659,"kon":660,"olin":661,"su":662,"âĢ":663,"ĠN":664,"Ġtonsi":665,"wawa":666,"Ġpipi":667,"mama":668,"Ġoko":669,"moku":670,"Ġleko":671,"Ġkokosila":672,"sona":673,"seme":674,"juna":675,"eso":676,"Ġmeso":677,"linja":678,"Ġmajuna":679,"lukin":680,"ĠSon":681,"ĠIn":682,"selo":683,"wile":684,"Ġlan":685,"sima":686,"kili":687,"pilin":688,"luka":689,"ĠKa":690,"ĠTe":691,"ĠLi":692,"ĠMe":693,"ĠInli":694,"Ġlanpan":695,"..":696,"ike":697,"seli":698,"ton":699,"wan":700,"sijelo":701,"kijetesantakalu":702,"Ġape":703,"pesi":704,"kule":705,"piku":706,"Ġsoko":707,"Ġjasima":708,"ĠPi":709,"ĠSonja":710,"Ġapeja":711,"ĠJ":712,"nanpa":713,"sinpin":714,"Ġkijetesantakalu":715,"lupa":716,"lawa":717,"ali":718,"nton":719,"ĠâĢ":720,"Ġte":721,"kiwen":722,"pakala":723,"winton":724,"luwi":725,"Ġlinluwi":726,"ĠLo":727,"ĠEwinton":728,"âĢĿ":729,"ĠNi":730,"ĠâĢľ":731,"lan":732,"ntu":733,"oko":734,"ĠW":735,"Ġmelo":736,"Ġepiku":737,"mije":738,"pini":739,"ĠKi":740,"ĠTo":741,"Ġkapesi":742,"ĠSa":743,"ĠSu":744,"ĠSan":745,"ĠSen":746,"ĠPa":747,"ĠPe":748,"ĠLa":749,"palisa":750,"ĠTelen":751,"ĠLisa":752,"Ġmelome":753,"awen":754,"mon":755,"mun":756,"pona":757,"ĠO":758,"nata":759,"lija":760,"poki":761,"sawi":762,"Ġkuntu":763,"jaki":764,"Ġpuwa":765,"ĠMi":766,"sewi":767,"supa":768,"ĠKanata":769,"ĠMewi":770,"...":771,"ĠJu":772,"ĠSeni":773,"monsuta":774,"epiku":775,"open":776,"ante":777,"sija":778,"Ġmijo":779,"misikeke":780,"amana":781,"poka":782,"sali":783,"ĠKu":784,"ĠKen":785,"ĠTa":786,"ĠSi":787,"ĠSamana":788,"Ġusawi":789,"lape":790,"lapi":791,"ĠPo":792,"mute":793,"panpo":794,"ĠElo":795,"ĠKapesi":796,"ĠKin":797,"ĠSupanpo":798,"ĠSanta":799,"ĠLasina":800,"ĠMewika":801,"Ġmijomi":802,"eko":803,"esun":804,"imi":805,"insa":806,"juta":807,"kama":808,"mala":809,"nena":810,"utala":811,"yu":812,"¼ģ":813,"ï¼ģ":814,"ĠU":815,"nasa":816,"Ġsan":817,"Ġete":818,"Ġkan":819,"wala":820,"sipin":821,"alata":822,"alasija":823,"onken":824,"Ġpasila":825,"keke":826,"pana":827,"pelan":828,"Ġkiki":829,"kokosila":830,"ĠKan":831,"ĠKeli":832,"ĠTimi":833,"Ġkamala":834,"ĠSo":835,"ĠAsi":836,"ĠPu":837,"ĠPan":838,"ĠPona":839,"ĠPalata":840,"ĠLe":841,"ĠMa":842,"ĠMalasija":843,"Ġunu":844,"ĠEko":845,"ĠEpelan":846,"ĠIta":847,"ĠNe":848,"ĠNu":849,"ĠSonko":850,"ĠLin":851,"ĠMekeke":852,"ĠPita":853,"ĠJonken":854,"ĠLola":855,"âĢĿ.":856,"ĠWa":857,"ĠTosi":858,"ĠToki":859,"ĠSusan":860,"ĠPepu":861,"ĠMisali":862,"ĠSiko":863,"lapisu":864,"ĠElopa":865,"ĠKinkili":866,"Ġkamalawala":867,"ĠEpelanto":868,"!\"":869,"\",":870,"\"?":871,".\"":872,"?!":873,"Eko":874,"asin":875,"esi":876,"eta":877,"elon":878,"esija":879,"ije":880,"isipin":881,"jal":882,"jon":883,"jama":884,"kan":885,"lani":886,"man":887,"mani":888,"nu":889,"omi":890,"ose":891,"pon":892,"pil":893,"pani":894,"palu":895,"son":896,"sama":897,"tonsi":898,"upi":899,"wani":900,"Ġyu":901,"nawi":902,"naja":903,"Ġpeta":904,"anu":905,"anka":906,"anpa":907,"antan":908,"lia":909,"lisa":910,"liku":911,"lilan":912,"wasi":913,"wawi":914,"nija":915,"siko":916,"alasa":917,"Ġtaki":918,"onyu":919,"Ġmisa":920,"kini":921,"kijo":922,"kiko":923,"kimu":924,"kipisi":925,"kisan":926,"majuna":927,"telan":928,"mile":929,"ila":930,"��mulapisu":931,"Ġowe":932,"Ġojuta":933,"kepeken":934,"kenaja":935,"kaso":936,"katon":937,"kawan":938,"soko":939,"polo":940,"powe":941,"Ġisipin":942,"pajal":943,"pakawan":944,"loje":945,"peta":946,"peko":947,"meso":948,"mesu":949,"jole":950,"joju":951,"mosi":952,"momo":953,"moto":954,"salin":955,"tawa":956,"tawan":957,"tasali":958,"kukan":959,"wito":960,"pusi":961,"puwani":962,"Ġwale":963,"Ġkese":964,"jasima":965,"pili":966,"pimeja":967,"Ġtuli":968,"uneko":969,"kowa":970,"nokijo":971,"jesa":972,"jekenaja":973,"ĠKena":974,"ĠKijo":975,"ĠKelon":976,"ĠKomi":977,"ĠKila":978,"ĠTen":979,"ĠTonyu":980,"Ġsoto":981,"lete":982,"leko":983,"Ġkonwe":984,"ĠSuneko":985,"Ġumesu":986,"laso":987,"lasin":988,"ĠAli":989,"ĠAwi":990,"ĠAlapi":991,"ĠAman":992,"ĠAwawi":993,"ĠApolo":994,"ĠAtawan":995,"ĠAlasin":996,"ĠPuta":997,"ĠLuta":998,"ĠLupi":999,"ĠLantan":1000,"mulapisu":1001,"ĠMena":1002,"ĠMose":1003,"ĠManka":1004,"ĠAnse":1005,"ĠAnson":1006,"ĠAnkowa":1007,"ijosa":1008,"aluto":1009,"jusi":1010,"juwan":1011,"jukini":1012,"ĠEki":1013,"ĠElisa":1014,"ĠIlan":1015,"suli":1016,"suka":1017,"suwi":1018,"supan":1019,"ĠNasin":1020,"ĠNaluto":1021,"ĠInton":1022,"ĠKapil":1023,"ĠKajesa":1024,"ĠTepo":1025,"ĠTeja":1026,"ĠTewen":1027,"ĠTepani":1028,"ĠLilija":1029,"ĠLililan":1030,"ĠMelani":1031,"ĠMesiko":1032,"ĠMekiko":1033,"selija":1034,"ĠPiwi":1035,"ĠPisin":1036,"ĠPiju":1037,"ĠPinija":1038,"ĠPikaso":1039,"ĠPinokijo":1040,"ĠJan":1041,"Ġteje":1042,"ĠLopin":1043,"ĠLowasi":1044,"ĠLokaton":1045,"ĠLosupan":1046,"ĠNiki":1047,"ĠNimu":1048,"ĠNijon":1049,"ĠNipon":1050,"ĠNimile":1051,"ĠWeko":1052,"ĠWije":1053,"ĠWijosa":1054,"ĠKita":1055,"ĠKiliku":1056,"ĠToto":1057,"ĠSaku":1058,"ĠSasalin":1059,"ĠSajusi":1060,"ĠSentu":1061,"ĠPasi":1062,"ĠPakala":1063,"ĠPakisan":1064,"ĠPapuwani":1065,"ĠPewe":1066,"ĠPekimu":1067,"ĠPejoju":1068,"ĠLajo":1069,"ĠLawito":1070,"ĠOsin":1071,"ĠOwe":1072,"ĠOjuta":1073,"ĠOselija":1074,"ĠMimoku":1075,"ĠMijama":1076,"ĠJuli":1077,"ĠJuke":1078,"ĠJutu":1079,"ĠJulija":1080,"ĠKupa":1081,"ĠKulija":1082,"ĠKukukan":1083,"ĠTawi":1084,"ĠTapajal":1085,"ĠTajuwan":1086,"ĠPota":1087,"ĠPomoto":1088,"ĠPosuka":1089,"ĠUtu":1090,"ĠUsawi":1091,"ĠKanse":1092,"ĠKanpusi":1093,"ĠSomomo":1094,"ĠPutu":1095,"ĠPunawi":1096,"ĠPanto":1097,"ĠPantasali":1098,"ĠLewi":1099,"ĠLemosi":1100,"ĠMaku":1101,"ĠMasu":1102,"ĠItalija":1103,"ĠItalia":1104,"ĠNepalu":1105,"ĠNetelan":1106,"ĠNuken":1107,"ĠNuwan":1108,"ĠLinta":1109,"ĠLinja":1110,"ĠWajole":1111,"ĠWapili":1112,"esipo":1113,"Ġyupeko":1114,"Ġwaleja":1115,"ĠKenajekenaja":1116,"ĠKijoto":1117,"ĠKominu":1118,"ĠAnsetan":1119,"ĠElisape":1120,"ĠNasinesipo":1121,"ĠIntonesija":1122,"ĠKapilu":1123,"ĠKilikuntu":1124,"ĠPapuwanijukini":1125,"ĠTapajalo":1126,"ĠPomotolo":1127,"ĠPantasalipakawan":1128,"Ġyupekosi":1129}