jvonrad commited on
Commit
257520a
·
verified ·
1 Parent(s): 6d9c6d2

Upload tokenizers/unigram_starved/meta.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. tokenizers/unigram_starved/meta.json +432 -0
tokenizers/unigram_starved/meta.json ADDED
@@ -0,0 +1,432 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "flavor": "unigram",
3
+ "condition": "starved",
4
+ "vocab_size": 65536,
5
+ "specials": [
6
+ "<unk>",
7
+ "<bos>",
8
+ "<eos>",
9
+ "<pad>"
10
+ ],
11
+ "corpus_files": [
12
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/aak_Latn.txt",
13
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/abk_Cyrl.txt",
14
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/abq_Cyrl.txt",
15
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/abt_Latn.txt",
16
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ace_Latn.txt",
17
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ach_Latn.txt",
18
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/acm_Arab.txt",
19
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/acn_Latn.txt",
20
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ady_Cyrl.txt",
21
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/aeb_Arab.txt",
22
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/afr_Latn.txt",
23
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/aii_Syrc.txt",
24
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/als_Latn.txt",
25
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/alt_Cyrl.txt",
26
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/amh_Ethi.txt",
27
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ang_Latn.txt",
28
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/anp_Deva.txt",
29
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/apc_Arab.txt",
30
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/arb_Arab.txt",
31
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/arb_Latn.txt",
32
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/arg_Latn.txt",
33
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/arn_Latn.txt",
34
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ars_Arab.txt",
35
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ary_Arab.txt",
36
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/arz_Arab.txt",
37
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/asm_Beng.txt",
38
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ast_Latn.txt",
39
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ava_Cyrl.txt",
40
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/avk_Latn.txt",
41
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/awa_Deva.txt",
42
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ayr_Latn.txt",
43
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/azb_Arab.txt",
44
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/azj_Cyrl.txt",
45
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/azj_Latn.txt",
46
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bak_Cyrl.txt",
47
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bam_Latn.txt",
48
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ban_Latn.txt",
49
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bar_Latn.txt",
50
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bba_Latn.txt",
51
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bbc_Latn.txt",
52
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bci_Latn.txt",
53
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bcl_Latn.txt",
54
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bel_Cyrl.txt",
55
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bem_Latn.txt",
56
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ben_Beng.txt",
57
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ben_Latn.txt",
58
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bew_Latn.txt",
59
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bho_Deva.txt",
60
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bis_Latn.txt",
61
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bjn_Arab.txt",
62
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bjn_Latn.txt",
63
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bod_Tibt.txt",
64
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bos_Latn.txt",
65
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bre_Latn.txt",
66
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/brh_Arab.txt",
67
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bru_Latn.txt",
68
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/brx_Deva.txt",
69
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bts_Latn.txt",
70
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/btx_Latn.txt",
71
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bul_Cyrl.txt",
72
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/bxr_Cyrl.txt",
73
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/cab_Latn.txt",
74
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/cac_Latn.txt",
75
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/cat_Latn.txt",
76
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/cbk_Latn.txt",
77
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ceb_Latn.txt",
78
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ces_Latn.txt",
79
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/cfm_Latn.txt",
80
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/che_Cyrl.txt",
81
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/chk_Latn.txt",
82
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/chv_Cyrl.txt",
83
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ckb_Arab.txt",
84
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/cmn_Hani.txt",
85
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/cnh_Latn.txt",
86
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/cop_Copt.txt",
87
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/cor_Latn.txt",
88
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/cos_Latn.txt",
89
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/crh_Cyrl.txt",
90
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/crh_Latn.txt",
91
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/crn_Latn.txt",
92
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/crs_Latn.txt",
93
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/csb_Latn.txt",
94
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ctd_Latn.txt",
95
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/cym_Latn.txt",
96
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/dak_Latn.txt",
97
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/dan_Latn.txt",
98
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/dar_Cyrl.txt",
99
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/deu_Latn.txt",
100
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/diq_Latn.txt",
101
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/div_Thaa.txt",
102
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/doi_Deva.txt",
103
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/dsb_Latn.txt",
104
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/dtp_Latn.txt",
105
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/dyu_Latn.txt",
106
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/dzo_Tibt.txt",
107
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/efi_Latn.txt",
108
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ekk_Latn.txt",
109
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ell_Grek.txt",
110
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/eml_Latn.txt",
111
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/en.txt",
112
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/epo_Latn.txt",
113
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/eus_Latn.txt",
114
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ewe_Latn.txt",
115
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ext_Latn.txt",
116
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/fao_Latn.txt",
117
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/fas_Arab.txt",
118
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/fij_Latn.txt",
119
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/fil_Latn.txt",
120
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/fin_Latn.txt",
121
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/fit_Latn.txt",
122
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/fon_Latn.txt",
123
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/fra_Latn.txt",
124
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/fro_Latn.txt",
125
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/frp_Latn.txt",
126
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/frr_Latn.txt",
127
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/fry_Latn.txt",
128
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/fuf_Latn.txt",
129
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/fur_Latn.txt",
130
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/gaa_Latn.txt",
131
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/gag_Cyrl.txt",
132
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/gag_Latn.txt",
133
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/gaz_Latn.txt",
134
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/gcf_Latn.txt",
135
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/gil_Latn.txt",
136
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/gla_Latn.txt",
137
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/gle_Latn.txt",
138
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/glg_Latn.txt",
139
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/glk_Arab.txt",
140
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/glv_Latn.txt",
141
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/gmh_Latn.txt",
142
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/gom_Deva.txt",
143
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/gom_Latn.txt",
144
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/gos_Latn.txt",
145
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/grc_Grek.txt",
146
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/gsw_Latn.txt",
147
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/gug_Latn.txt",
148
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/guj_Gujr.txt",
149
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/guw_Latn.txt",
150
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/gym_Latn.txt",
151
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/hac_Arab.txt",
152
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/hat_Latn.txt",
153
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/hau_Latn.txt",
154
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/haw_Latn.txt",
155
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/hbo_Hebr.txt",
156
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/heb_Hebr.txt",
157
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/hif_Latn.txt",
158
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/hil_Latn.txt",
159
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/hin_Deva.txt",
160
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/hin_Latn.txt",
161
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/hmo_Latn.txt",
162
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/hmr_Latn.txt",
163
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/hne_Deva.txt",
164
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/hrv_Latn.txt",
165
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/hsb_Latn.txt",
166
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/hun_Latn.txt",
167
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/hye_Armn.txt",
168
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/hyw_Armn.txt",
169
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/iba_Latn.txt",
170
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ibo_Latn.txt",
171
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ido_Latn.txt",
172
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ify_Latn.txt",
173
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ike_Cans.txt",
174
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ilo_Latn.txt",
175
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ina_Latn.txt",
176
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ind_Latn.txt",
177
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/inh_Cyrl.txt",
178
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/isl_Latn.txt",
179
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/iso_Latn.txt",
180
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ita_Latn.txt",
181
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/jac_Latn.txt",
182
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/jav_Latn.txt",
183
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/jpn_Jpan.txt",
184
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kaa_Cyrl.txt",
185
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kaa_Latn.txt",
186
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kab_Latn.txt",
187
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kac_Latn.txt",
188
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kal_Latn.txt",
189
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kan_Knda.txt",
190
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kan_Latn.txt",
191
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kat_Geor.txt",
192
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kaz_Cyrl.txt",
193
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kbd_Cyrl.txt",
194
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kea_Latn.txt",
195
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kek_Latn.txt",
196
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kha_Latn.txt",
197
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/khk_Cyrl.txt",
198
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/khm_Khmr.txt",
199
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kik_Latn.txt",
200
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kin_Latn.txt",
201
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kir_Cyrl.txt",
202
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kiu_Latn.txt",
203
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kmb_Latn.txt",
204
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kmr_Latn.txt",
205
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kng_Latn.txt",
206
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kor_Hang.txt",
207
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kos_Latn.txt",
208
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kpv_Cyrl.txt",
209
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/krc_Cyrl.txt",
210
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/krj_Latn.txt",
211
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/krl_Latn.txt",
212
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ksh_Latn.txt",
213
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ksw_Mymr.txt",
214
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kua_Latn.txt",
215
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/kum_Cyrl.txt",
216
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/lad_Latn.txt",
217
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/lao_Laoo.txt",
218
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/lat_Latn.txt",
219
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/lbe_Cyrl.txt",
220
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/lez_Cyrl.txt",
221
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/lfn_Latn.txt",
222
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/lij_Latn.txt",
223
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/lim_Latn.txt",
224
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/lin_Latn.txt",
225
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/lit_Latn.txt",
226
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/lmo_Latn.txt",
227
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/loz_Latn.txt",
228
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ltg_Latn.txt",
229
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ltz_Latn.txt",
230
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/lua_Latn.txt",
231
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/lub_Latn.txt",
232
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/lug_Latn.txt",
233
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/luo_Latn.txt",
234
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/lus_Latn.txt",
235
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/lvs_Latn.txt",
236
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/lzh_Hani.txt",
237
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mah_Latn.txt",
238
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mai_Deva.txt",
239
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mal_Latn.txt",
240
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mal_Mlym.txt",
241
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mam_Latn.txt",
242
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mar_Deva.txt",
243
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mar_Latn.txt",
244
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mdf_Cyrl.txt",
245
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/meu_Latn.txt",
246
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mfe_Latn.txt",
247
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mhr_Cyrl.txt",
248
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mkd_Cyrl.txt",
249
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mlt_Latn.txt",
250
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mni_Beng.txt",
251
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mni_Latn.txt",
252
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mnw_Mymr.txt",
253
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mos_Latn.txt",
254
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mps_Latn.txt",
255
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mri_Latn.txt",
256
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mrj_Cyrl.txt",
257
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mui_Latn.txt",
258
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mwl_Latn.txt",
259
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mww_Latn.txt",
260
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/mya_Mymr.txt",
261
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/myv_Cyrl.txt",
262
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/nah_Latn.txt",
263
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/nan_Latn.txt",
264
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/nap_Latn.txt",
265
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/nbl_Latn.txt",
266
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/nch_Latn.txt",
267
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/nde_Latn.txt",
268
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ndo_Latn.txt",
269
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/nds_Latn.txt",
270
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/new_Deva.txt",
271
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/nhe_Latn.txt",
272
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/nld_Latn.txt",
273
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/nno_Latn.txt",
274
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/nob_Latn.txt",
275
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/nog_Cyrl.txt",
276
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/non_Latn.txt",
277
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/npi_Deva.txt",
278
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/npi_Latn.txt",
279
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/nrm_Latn.txt",
280
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/nso_Latn.txt",
281
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/nya_Latn.txt",
282
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/nyu_Latn.txt",
283
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/nzi_Latn.txt",
284
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/oci_Latn.txt",
285
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/olo_Latn.txt",
286
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/orv_Cyrl.txt",
287
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ory_Latn.txt",
288
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ory_Orya.txt",
289
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/oss_Cyrl.txt",
290
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/pag_Latn.txt",
291
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/pam_Latn.txt",
292
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/pan_Guru.txt",
293
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/pan_Latn.txt",
294
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/pap_Latn.txt",
295
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/pbt_Arab.txt",
296
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/pcd_Latn.txt",
297
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/pck_Latn.txt",
298
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/pdt_Latn.txt",
299
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/pfl_Latn.txt",
300
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/plt_Latn.txt",
301
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/pms_Latn.txt",
302
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/pnb_Arab.txt",
303
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/poh_Latn.txt",
304
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/pol_Latn.txt",
305
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/pon_Latn.txt",
306
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/por_Latn.txt",
307
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/quc_Latn.txt",
308
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/qug_Latn.txt",
309
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/quy_Latn.txt",
310
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/quz_Latn.txt",
311
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/rar_Latn.txt",
312
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/rcf_Latn.txt",
313
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/rmc_Latn.txt",
314
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/rmn_Grek.txt",
315
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/rmn_Latn.txt",
316
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/rmy_Cyrl.txt",
317
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/rmy_Latn.txt",
318
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/roh_Latn.txt",
319
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ron_Cyrl.txt",
320
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ron_Latn.txt",
321
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/rop_Latn.txt",
322
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/rue_Cyrl.txt",
323
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/run_Latn.txt",
324
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/rup_Latn.txt",
325
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/rus_Cyrl.txt",
326
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/sag_Latn.txt",
327
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/sah_Cyrl.txt",
328
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/san_Deva.txt",
329
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/san_Latn.txt",
330
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/sat_Olck.txt",
331
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/scn_Latn.txt",
332
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/sco_Latn.txt",
333
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/sdh_Arab.txt",
334
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/sgs_Latn.txt",
335
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/shn_Mymr.txt",
336
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/sin_Sinh.txt",
337
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/slk_Latn.txt",
338
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/slv_Latn.txt",
339
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/sma_Latn.txt",
340
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/sme_Latn.txt",
341
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/smj_Latn.txt",
342
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/smn_Latn.txt",
343
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/smo_Latn.txt",
344
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/sms_Latn.txt",
345
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/sna_Latn.txt",
346
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/snd_Arab.txt",
347
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/som_Latn.txt",
348
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/sot_Latn.txt",
349
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/srd_Latn.txt",
350
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/srm_Latn.txt",
351
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/srn_Latn.txt",
352
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/srp_Cyrl.txt",
353
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/srp_Latn.txt",
354
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ssw_Latn.txt",
355
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/stq_Latn.txt",
356
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/sun_Latn.txt",
357
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/swc_Latn.txt",
358
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/swe_Latn.txt",
359
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/swg_Latn.txt",
360
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/swh_Latn.txt",
361
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/syc_Syrc.txt",
362
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/szl_Latn.txt",
363
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/szy_Latn.txt",
364
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tab_Cyrl.txt",
365
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tah_Latn.txt",
366
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tam_Latn.txt",
367
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tam_Taml.txt",
368
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tat_Cyrl.txt",
369
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tat_Latn.txt",
370
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tbz_Latn.txt",
371
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tcy_Knda.txt",
372
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tcz_Latn.txt",
373
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tel_Latn.txt",
374
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tel_Telu.txt",
375
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tet_Latn.txt",
376
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tgk_Cyrl.txt",
377
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tha_Thai.txt",
378
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tir_Ethi.txt",
379
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tiv_Latn.txt",
380
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tlh_Latn.txt",
381
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tly_Latn.txt",
382
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tog_Latn.txt",
383
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/toi_Latn.txt",
384
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ton_Latn.txt",
385
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/top_Latn.txt",
386
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tpi_Latn.txt",
387
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tsn_Latn.txt",
388
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tso_Latn.txt",
389
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tuk_Cyrl.txt",
390
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tuk_Latn.txt",
391
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tvl_Latn.txt",
392
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/twi_Latn.txt",
393
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tyv_Cyrl.txt",
394
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tzh_Latn.txt",
395
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tzm_Tfng.txt",
396
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/tzo_Latn.txt",
397
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ubu_Latn.txt",
398
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/udm_Cyrl.txt",
399
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/uig_Arab.txt",
400
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/uig_Latn.txt",
401
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ukr_Cyrl.txt",
402
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/umb_Latn.txt",
403
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/urd_Arab.txt",
404
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/urd_Latn.txt",
405
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/uzn_Cyrl.txt",
406
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/uzn_Latn.txt",
407
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/uzs_Arab.txt",
408
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/vec_Latn.txt",
409
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ven_Latn.txt",
410
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/vep_Latn.txt",
411
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/vie_Latn.txt",
412
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/vls_Latn.txt",
413
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/vol_Latn.txt",
414
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/vro_Latn.txt",
415
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/wal_Latn.txt",
416
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/wln_Latn.txt",
417
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/wol_Latn.txt",
418
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/wuu_Hani.txt",
419
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/xal_Cyrl.txt",
420
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/xho_Latn.txt",
421
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/xmf_Geor.txt",
422
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/ydd_Hebr.txt",
423
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/yor_Latn.txt",
424
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/yua_Latn.txt",
425
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/yue_Hani.txt",
426
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/zai_Latn.txt",
427
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/zea_Latn.txt",
428
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/zom_Latn.txt",
429
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/zsm_Latn.txt",
430
+ "/scratch/u6jh/jvonrad.u6jh/xscript/tok_corpora/starved/zul_Latn.txt"
431
+ ]
432
+ }