Hugging Face's logo

kiansheik
/
tupi-verb-anotation

Text2Text Generation
Transformers
Safetensors
t5
tupi
guarani
text-generation-inference
Inference Endpoints
Model card Files Community
1
kiansheik commited on
Commit
54f8a24
•
1 Parent(s): e729561

first

Browse files
Files changed (7) hide show
  1. added_tokens.json +195 -0
  2. config.json +61 -0
  3. generation_config.json +7 -0
  4. model.safetensors +3 -0
  5. special_tokens_map.json +746 -0
  6. spiece.model +3 -0
  7. tokenizer_config.json +1775 -0
added_tokens.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 32099,
3
+ "<extra_id_10>": 32089,
4
+ "<extra_id_11>": 32088,
5
+ "<extra_id_12>": 32087,
6
+ "<extra_id_13>": 32086,
7
+ "<extra_id_14>": 32085,
8
+ "<extra_id_15>": 32084,
9
+ "<extra_id_16>": 32083,
10
+ "<extra_id_17>": 32082,
11
+ "<extra_id_18>": 32081,
12
+ "<extra_id_19>": 32080,
13
+ "<extra_id_1>": 32098,
14
+ "<extra_id_20>": 32079,
15
+ "<extra_id_21>": 32078,
16
+ "<extra_id_22>": 32077,
17
+ "<extra_id_23>": 32076,
18
+ "<extra_id_24>": 32075,
19
+ "<extra_id_25>": 32074,
20
+ "<extra_id_26>": 32073,
21
+ "<extra_id_27>": 32072,
22
+ "<extra_id_28>": 32071,
23
+ "<extra_id_29>": 32070,
24
+ "<extra_id_2>": 32097,
25
+ "<extra_id_30>": 32069,
26
+ "<extra_id_31>": 32068,
27
+ "<extra_id_32>": 32067,
28
+ "<extra_id_33>": 32066,
29
+ "<extra_id_34>": 32065,
30
+ "<extra_id_35>": 32064,
31
+ "<extra_id_36>": 32063,
32
+ "<extra_id_37>": 32062,
33
+ "<extra_id_38>": 32061,
34
+ "<extra_id_39>": 32060,
35
+ "<extra_id_3>": 32096,
36
+ "<extra_id_40>": 32059,
37
+ "<extra_id_41>": 32058,
38
+ "<extra_id_42>": 32057,
39
+ "<extra_id_43>": 32056,
40
+ "<extra_id_44>": 32055,
41
+ "<extra_id_45>": 32054,
42
+ "<extra_id_46>": 32053,
43
+ "<extra_id_47>": 32052,
44
+ "<extra_id_48>": 32051,
45
+ "<extra_id_49>": 32050,
46
+ "<extra_id_4>": 32095,
47
+ "<extra_id_50>": 32049,
48
+ "<extra_id_51>": 32048,
49
+ "<extra_id_52>": 32047,
50
+ "<extra_id_53>": 32046,
51
+ "<extra_id_54>": 32045,
52
+ "<extra_id_55>": 32044,
53
+ "<extra_id_56>": 32043,
54
+ "<extra_id_57>": 32042,
55
+ "<extra_id_58>": 32041,
56
+ "<extra_id_59>": 32040,
57
+ "<extra_id_5>": 32094,
58
+ "<extra_id_60>": 32039,
59
+ "<extra_id_61>": 32038,
60
+ "<extra_id_62>": 32037,
61
+ "<extra_id_63>": 32036,
62
+ "<extra_id_64>": 32035,
63
+ "<extra_id_65>": 32034,
64
+ "<extra_id_66>": 32033,
65
+ "<extra_id_67>": 32032,
66
+ "<extra_id_68>": 32031,
67
+ "<extra_id_69>": 32030,
68
+ "<extra_id_6>": 32093,
69
+ "<extra_id_70>": 32029,
70
+ "<extra_id_71>": 32028,
71
+ "<extra_id_72>": 32027,
72
+ "<extra_id_73>": 32026,
73
+ "<extra_id_74>": 32025,
74
+ "<extra_id_75>": 32024,
75
+ "<extra_id_76>": 32023,
76
+ "<extra_id_77>": 32022,
77
+ "<extra_id_78>": 32021,
78
+ "<extra_id_79>": 32020,
79
+ "<extra_id_7>": 32092,
80
+ "<extra_id_80>": 32019,
81
+ "<extra_id_81>": 32018,
82
+ "<extra_id_82>": 32017,
83
+ "<extra_id_83>": 32016,
84
+ "<extra_id_84>": 32015,
85
+ "<extra_id_85>": 32014,
86
+ "<extra_id_86>": 32013,
87
+ "<extra_id_87>": 32012,
88
+ "<extra_id_88>": 32011,
89
+ "<extra_id_89>": 32010,
90
+ "<extra_id_8>": 32091,
91
+ "<extra_id_90>": 32009,
92
+ "<extra_id_91>": 32008,
93
+ "<extra_id_92>": 32007,
94
+ "<extra_id_93>": 32006,
95
+ "<extra_id_94>": 32005,
96
+ "<extra_id_95>": 32004,
97
+ "<extra_id_96>": 32003,
98
+ "<extra_id_97>": 32002,
99
+ "<extra_id_98>": 32001,
100
+ "<extra_id_99>": 32000,
101
+ "<extra_id_9>": 32090,
102
+ "[CIRCUMSTANTIAL_SUFFIX:CONSONANT_ENDING]": 32133,
103
+ "[CIRCUMSTANTIAL_SUFFIX:NULL_ENDING]": 32180,
104
+ "[CIRCUMSTANTIAL_SUFFIX:VOWEL_ENDING]": 32160,
105
+ "[GERUND_SUBJECT_PREFIX:1ppe]": 32168,
106
+ "[GERUND_SUBJECT_PREFIX:1ppi]": 32150,
107
+ "[GERUND_SUBJECT_PREFIX:1ps]": 32184,
108
+ "[GERUND_SUBJECT_PREFIX:2pp]": 32122,
109
+ "[GERUND_SUBJECT_PREFIX:2ps]": 32123,
110
+ "[GERUND_SUBJECT_PREFIX:3p]": 32132,
111
+ "[GERUND_SUFFIX:CLASS_1:B]": 32177,
112
+ "[GERUND_SUFFIX:CLASS_1:CONSONANT]": 32175,
113
+ "[GERUND_SUFFIX:CLASS_1:IYU]": 32125,
114
+ "[GERUND_SUFFIX:CLASS_1:NASAL_IYU]": 32146,
115
+ "[GERUND_SUFFIX:CLASS_1:NASAL_VOWEL]": 32109,
116
+ "[GERUND_SUFFIX:CLASS_1:ORAL_VOWEL]": 32174,
117
+ "[GERUND_SUFFIX:CLASS_1:R]": 32162,
118
+ "[GERUND_SUFFIX:CLASS_1]": 32100,
119
+ "[GERUND_SUFFIX:CLASS_2:DEFAULT]": 32176,
120
+ "[GERUND_SUFFIX:CLASS_2:NASAL_VOWEL_ENDING]": 32166,
121
+ "[GERUND_SUFFIX:CLASS_2:ORAL_VOWEL_ENDING]": 32170,
122
+ "[IMPERATIVE_PREFIX:2pp]": 32144,
123
+ "[IMPERATIVE_PREFIX:2ps]": 32153,
124
+ "[NEGATION_PARTICLE:NA]": 32152,
125
+ "[NEGATION_PARTICLE:UME]": 32135,
126
+ "[NEGATION_PREFIX]": 32143,
127
+ "[NEGATION_SUFFIX:CONSONANT_ENDING]": 32103,
128
+ "[NEGATION_SUFFIX:VOWEL_ENDING]": 32101,
129
+ "[NEGATION_SUFFIX]": 32156,
130
+ "[OBJECT:1ppe]": 32116,
131
+ "[OBJECT:1ppi]": 32190,
132
+ "[OBJECT:1ps]": 32124,
133
+ "[OBJECT:2pp:SUBJECT_1P]": 32145,
134
+ "[OBJECT:2pp]": 32102,
135
+ "[OBJECT:2ps:SUBJECT_1P]": 32186,
136
+ "[OBJECT:2ps]": 32179,
137
+ "[OBJECT:3p:MONOSYLLABIC]": 32167,
138
+ "[OBJECT:3p]": 32137,
139
+ "[OBJECT:MUTUAL]": 32106,
140
+ "[OBJECT:REFLEXIVE]": 32148,
141
+ "[OBJECT_MARKER:3p:DEFAULT]": 32114,
142
+ "[OBJECT_MARKER:3p:MONOSYLLABIC]": 32108,
143
+ "[OBJECT_MARKER:3p:PLURIFORM_PREFIX:MONOSYLLABIC]": 32151,
144
+ "[PAD]": 32192,
145
+ "[PERMISSIVE_PREFIX:CONSONANT]": 32149,
146
+ "[PERMISSIVE_PREFIX:VOWEL]": 32118,
147
+ "[PLURIFORM_PREFIX:R]": 32141,
148
+ "[PLURIFORM_PREFIX:S]": 32154,
149
+ "[ROOT]": 32163,
150
+ "[SUBJECT:1ppe]": 32158,
151
+ "[SUBJECT:1ppi]": 32120,
152
+ "[SUBJECT:1ps]": 32112,
153
+ "[SUBJECT:2pp:OBJECT_1P]": 32131,
154
+ "[SUBJECT:2pp]": 32172,
155
+ "[SUBJECT:2ps:OBJECT_1P]": 32178,
156
+ "[SUBJECT:2ps]": 32173,
157
+ "[SUBJECT:3p]": 32113,
158
+ "[SUBJECT_PREFIX:1ppe]": 32189,
159
+ "[SUBJECT_PREFIX:1ppi]": 32107,
160
+ "[SUBJECT_PREFIX:1ps]": 32159,
161
+ "[SUBJECT_PREFIX:2pp]": 32119,
162
+ "[SUBJECT_PREFIX:2ps]": 32130,
163
+ "[SUBJECT_PREFIX:3p]": 32171,
164
+ "a'e": 32127,
165
+ "amo": 32104,
166
+ "bo": 32110,
167
+ "e'ym": 32139,
168
+ "endé": 32128,
169
+ "ere": 32157,
170
+ "gûi": 32185,
171
+ "ixé": 32165,
172
+ "mo": 32164,
173
+ "n'": 32126,
174
+ "na": 32155,
175
+ "namo": 32142,
176
+ "nde": 32181,
177
+ "opo": 32183,
178
+ "oro": 32105,
179
+ "oré": 32169,
180
+ "pa": 32136,
181
+ "peîepé": 32117,
182
+ "peẽ": 32138,
183
+ "ramo": 32161,
184
+ "ta": 32129,
185
+ "umẽ": 32191,
186
+ "xe": 32182,
187
+ "í": 32121,
188
+ "îa": 32187,
189
+ "îandé": 32115,
190
+ "îe": 32147,
191
+ "îepé": 32188,
192
+ "îo": 32140,
193
+ "îos": 32134,
194
+ "́": 32111
195
+ }
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 512,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "relu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": false,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 6,
22
+ "num_heads": 8,
23
+ "num_layers": 6,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "task_specific_params": {
29
+ "summarization": {
30
+ "early_stopping": true,
31
+ "length_penalty": 2.0,
32
+ "max_length": 200,
33
+ "min_length": 30,
34
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 4,
36
+ "prefix": "summarize: "
37
+ },
38
+ "translation_en_to_de": {
39
+ "early_stopping": true,
40
+ "max_length": 300,
41
+ "num_beams": 4,
42
+ "prefix": "translate English to German: "
43
+ },
44
+ "translation_en_to_fr": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to French: "
49
+ },
50
+ "translation_en_to_ro": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to Romanian: "
55
+ }
56
+ },
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.38.1",
59
+ "use_cache": true,
60
+ "vocab_size": 32193
61
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.38.1"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bda335eee6b0b71e68ba47a22d86956045c03b150668db8544eba78f3d01fb03
3
+ size 242175016
special_tokens_map.json ADDED
@@ -0,0 +1,746 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "[GERUND_SUFFIX:CLASS_1]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "[NEGATION_SUFFIX:VOWEL_ENDING]",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "[OBJECT:2pp]",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "[NEGATION_SUFFIX:CONSONANT_ENDING]",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "amo",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "oro",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "[OBJECT:MUTUAL]",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "[SUBJECT_PREFIX:1ppi]",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "[OBJECT_MARKER:3p:MONOSYLLABIC]",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "[GERUND_SUFFIX:CLASS_1:NASAL_VOWEL]",
68
+ "lstrip": false,
69
+ "normalized": false,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "bo",
75
+ "lstrip": false,
76
+ "normalized": false,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ {
81
+ "content": "́",
82
+ "lstrip": false,
83
+ "normalized": false,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ },
87
+ {
88
+ "content": "[SUBJECT:1ps]",
89
+ "lstrip": false,
90
+ "normalized": false,
91
+ "rstrip": false,
92
+ "single_word": false
93
+ },
94
+ {
95
+ "content": "[SUBJECT:3p]",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false
100
+ },
101
+ {
102
+ "content": "a",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false
107
+ },
108
+ {
109
+ "content": "[OBJECT_MARKER:3p:DEFAULT]",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false
114
+ },
115
+ {
116
+ "content": "îandé",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false
121
+ },
122
+ {
123
+ "content": "[OBJECT:1ppe]",
124
+ "lstrip": false,
125
+ "normalized": false,
126
+ "rstrip": false,
127
+ "single_word": false
128
+ },
129
+ {
130
+ "content": "peîepé",
131
+ "lstrip": false,
132
+ "normalized": false,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ },
136
+ {
137
+ "content": "[PERMISSIVE_PREFIX:VOWEL]",
138
+ "lstrip": false,
139
+ "normalized": false,
140
+ "rstrip": false,
141
+ "single_word": false
142
+ },
143
+ {
144
+ "content": "t",
145
+ "lstrip": false,
146
+ "normalized": false,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ },
150
+ {
151
+ "content": "[SUBJECT_PREFIX:2pp]",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false
156
+ },
157
+ {
158
+ "content": "[SUBJECT:1ppi]",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false
163
+ },
164
+ {
165
+ "content": "í",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false
170
+ },
171
+ {
172
+ "content": "[GERUND_SUBJECT_PREFIX:2pp]",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false
177
+ },
178
+ {
179
+ "content": "[GERUND_SUBJECT_PREFIX:2ps]",
180
+ "lstrip": false,
181
+ "normalized": false,
182
+ "rstrip": false,
183
+ "single_word": false
184
+ },
185
+ {
186
+ "content": "[OBJECT:1ps]",
187
+ "lstrip": false,
188
+ "normalized": false,
189
+ "rstrip": false,
190
+ "single_word": false
191
+ },
192
+ {
193
+ "content": "[GERUND_SUFFIX:CLASS_1:IYU]",
194
+ "lstrip": false,
195
+ "normalized": false,
196
+ "rstrip": false,
197
+ "single_word": false
198
+ },
199
+ {
200
+ "content": "pe",
201
+ "lstrip": false,
202
+ "normalized": false,
203
+ "rstrip": false,
204
+ "single_word": false
205
+ },
206
+ {
207
+ "content": "n'",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false
212
+ },
213
+ {
214
+ "content": "s",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false
219
+ },
220
+ {
221
+ "content": "a'e",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false
226
+ },
227
+ {
228
+ "content": "endé",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false
233
+ },
234
+ {
235
+ "content": "ta",
236
+ "lstrip": false,
237
+ "normalized": false,
238
+ "rstrip": false,
239
+ "single_word": false
240
+ },
241
+ {
242
+ "content": "[SUBJECT_PREFIX:2ps]",
243
+ "lstrip": false,
244
+ "normalized": false,
245
+ "rstrip": false,
246
+ "single_word": false
247
+ },
248
+ {
249
+ "content": "[SUBJECT:2pp:OBJECT_1P]",
250
+ "lstrip": false,
251
+ "normalized": false,
252
+ "rstrip": false,
253
+ "single_word": false
254
+ },
255
+ {
256
+ "content": "[GERUND_SUBJECT_PREFIX:3p]",
257
+ "lstrip": false,
258
+ "normalized": false,
259
+ "rstrip": false,
260
+ "single_word": false
261
+ },
262
+ {
263
+ "content": "[CIRCUMSTANTIAL_SUFFIX:CONSONANT_ENDING]",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false
268
+ },
269
+ {
270
+ "content": "îos",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false
275
+ },
276
+ {
277
+ "content": "[NEGATION_PARTICLE:UME]",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false
282
+ },
283
+ {
284
+ "content": "pa",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false
289
+ },
290
+ {
291
+ "content": "[OBJECT:3p]",
292
+ "lstrip": false,
293
+ "normalized": false,
294
+ "rstrip": false,
295
+ "single_word": false
296
+ },
297
+ {
298
+ "content": "peẽ",
299
+ "lstrip": false,
300
+ "normalized": false,
301
+ "rstrip": false,
302
+ "single_word": false
303
+ },
304
+ {
305
+ "content": "e'ym",
306
+ "lstrip": false,
307
+ "normalized": false,
308
+ "rstrip": false,
309
+ "single_word": false
310
+ },
311
+ {
312
+ "content": "îo",
313
+ "lstrip": false,
314
+ "normalized": false,
315
+ "rstrip": false,
316
+ "single_word": false
317
+ },
318
+ {
319
+ "content": "[PLURIFORM_PREFIX:R]",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": false,
323
+ "single_word": false
324
+ },
325
+ {
326
+ "content": "namo",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false
331
+ },
332
+ {
333
+ "content": "[NEGATION_PREFIX]",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false
338
+ },
339
+ {
340
+ "content": "[IMPERATIVE_PREFIX:2pp]",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false
345
+ },
346
+ {
347
+ "content": "[OBJECT:2pp:SUBJECT_1P]",
348
+ "lstrip": false,
349
+ "normalized": false,
350
+ "rstrip": false,
351
+ "single_word": false
352
+ },
353
+ {
354
+ "content": "[GERUND_SUFFIX:CLASS_1:NASAL_IYU]",
355
+ "lstrip": false,
356
+ "normalized": false,
357
+ "rstrip": false,
358
+ "single_word": false
359
+ },
360
+ {
361
+ "content": "îe",
362
+ "lstrip": false,
363
+ "normalized": false,
364
+ "rstrip": false,
365
+ "single_word": false
366
+ },
367
+ {
368
+ "content": "[OBJECT:REFLEXIVE]",
369
+ "lstrip": false,
370
+ "normalized": false,
371
+ "rstrip": false,
372
+ "single_word": false
373
+ },
374
+ {
375
+ "content": "[PERMISSIVE_PREFIX:CONSONANT]",
376
+ "lstrip": false,
377
+ "normalized": false,
378
+ "rstrip": false,
379
+ "single_word": false
380
+ },
381
+ {
382
+ "content": "[GERUND_SUBJECT_PREFIX:1ppi]",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false
387
+ },
388
+ {
389
+ "content": "[OBJECT_MARKER:3p:PLURIFORM_PREFIX:MONOSYLLABIC]",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false
394
+ },
395
+ {
396
+ "content": "[NEGATION_PARTICLE:NA]",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false
401
+ },
402
+ {
403
+ "content": "[IMPERATIVE_PREFIX:2ps]",
404
+ "lstrip": false,
405
+ "normalized": false,
406
+ "rstrip": false,
407
+ "single_word": false
408
+ },
409
+ {
410
+ "content": "r",
411
+ "lstrip": false,
412
+ "normalized": false,
413
+ "rstrip": false,
414
+ "single_word": false
415
+ },
416
+ {
417
+ "content": "[PLURIFORM_PREFIX:S]",
418
+ "lstrip": false,
419
+ "normalized": false,
420
+ "rstrip": false,
421
+ "single_word": false
422
+ },
423
+ {
424
+ "content": "na",
425
+ "lstrip": false,
426
+ "normalized": false,
427
+ "rstrip": false,
428
+ "single_word": false
429
+ },
430
+ {
431
+ "content": "[NEGATION_SUFFIX]",
432
+ "lstrip": false,
433
+ "normalized": false,
434
+ "rstrip": false,
435
+ "single_word": false
436
+ },
437
+ {
438
+ "content": "ere",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false
443
+ },
444
+ {
445
+ "content": "[SUBJECT:1ppe]",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false
450
+ },
451
+ {
452
+ "content": "[SUBJECT_PREFIX:1ps]",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false
457
+ },
458
+ {
459
+ "content": "[CIRCUMSTANTIAL_SUFFIX:VOWEL_ENDING]",
460
+ "lstrip": false,
461
+ "normalized": false,
462
+ "rstrip": false,
463
+ "single_word": false
464
+ },
465
+ {
466
+ "content": "i",
467
+ "lstrip": false,
468
+ "normalized": false,
469
+ "rstrip": false,
470
+ "single_word": false
471
+ },
472
+ {
473
+ "content": "abo",
474
+ "lstrip": false,
475
+ "normalized": false,
476
+ "rstrip": false,
477
+ "single_word": false
478
+ },
479
+ {
480
+ "content": "î",
481
+ "lstrip": false,
482
+ "normalized": false,
483
+ "rstrip": false,
484
+ "single_word": false
485
+ },
486
+ {
487
+ "content": "ramo",
488
+ "lstrip": false,
489
+ "normalized": false,
490
+ "rstrip": false,
491
+ "single_word": false
492
+ },
493
+ {
494
+ "content": "e",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false
499
+ },
500
+ {
501
+ "content": "û",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false
506
+ },
507
+ {
508
+ "content": "[GERUND_SUFFIX:CLASS_1:R]",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false
513
+ },
514
+ {
515
+ "content": "[ROOT]",
516
+ "lstrip": false,
517
+ "normalized": false,
518
+ "rstrip": false,
519
+ "single_word": false
520
+ },
521
+ {
522
+ "content": "mo",
523
+ "lstrip": false,
524
+ "normalized": false,
525
+ "rstrip": false,
526
+ "single_word": false
527
+ },
528
+ {
529
+ "content": "ixé",
530
+ "lstrip": false,
531
+ "normalized": false,
532
+ "rstrip": false,
533
+ "single_word": false
534
+ },
535
+ {
536
+ "content": "[GERUND_SUFFIX:CLASS_2:NASAL_VOWEL_ENDING]",
537
+ "lstrip": false,
538
+ "normalized": false,
539
+ "rstrip": false,
540
+ "single_word": false
541
+ },
542
+ {
543
+ "content": "[OBJECT:3p:MONOSYLLABIC]",
544
+ "lstrip": false,
545
+ "normalized": false,
546
+ "rstrip": false,
547
+ "single_word": false
548
+ },
549
+ {
550
+ "content": "[GERUND_SUBJECT_PREFIX:1ppe]",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false
555
+ },
556
+ {
557
+ "content": "oré",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false
562
+ },
563
+ {
564
+ "content": "[GERUND_SUFFIX:CLASS_2:ORAL_VOWEL_ENDING]",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false
569
+ },
570
+ {
571
+ "content": "[SUBJECT_PREFIX:3p]",
572
+ "lstrip": false,
573
+ "normalized": false,
574
+ "rstrip": false,
575
+ "single_word": false
576
+ },
577
+ {
578
+ "content": "[SUBJECT:2pp]",
579
+ "lstrip": false,
580
+ "normalized": false,
581
+ "rstrip": false,
582
+ "single_word": false
583
+ },
584
+ {
585
+ "content": "[SUBJECT:2ps]",
586
+ "lstrip": false,
587
+ "normalized": false,
588
+ "rstrip": false,
589
+ "single_word": false
590
+ },
591
+ {
592
+ "content": "[GERUND_SUFFIX:CLASS_1:ORAL_VOWEL]",
593
+ "lstrip": false,
594
+ "normalized": false,
595
+ "rstrip": false,
596
+ "single_word": false
597
+ },
598
+ {
599
+ "content": "[GERUND_SUFFIX:CLASS_1:CONSONANT]",
600
+ "lstrip": false,
601
+ "normalized": false,
602
+ "rstrip": false,
603
+ "single_word": false
604
+ },
605
+ {
606
+ "content": "[GERUND_SUFFIX:CLASS_2:DEFAULT]",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false
611
+ },
612
+ {
613
+ "content": "[GERUND_SUFFIX:CLASS_1:B]",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false
618
+ },
619
+ {
620
+ "content": "[SUBJECT:2ps:OBJECT_1P]",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false
625
+ },
626
+ {
627
+ "content": "[OBJECT:2ps]",
628
+ "lstrip": false,
629
+ "normalized": false,
630
+ "rstrip": false,
631
+ "single_word": false
632
+ },
633
+ {
634
+ "content": "[CIRCUMSTANTIAL_SUFFIX:NULL_ENDING]",
635
+ "lstrip": false,
636
+ "normalized": false,
637
+ "rstrip": false,
638
+ "single_word": false
639
+ },
640
+ {
641
+ "content": "nde",
642
+ "lstrip": false,
643
+ "normalized": false,
644
+ "rstrip": false,
645
+ "single_word": false
646
+ },
647
+ {
648
+ "content": "o",
649
+ "lstrip": false,
650
+ "normalized": false,
651
+ "rstrip": false,
652
+ "single_word": false
653
+ },
654
+ {
655
+ "content": "xe",
656
+ "lstrip": false,
657
+ "normalized": false,
658
+ "rstrip": false,
659
+ "single_word": false
660
+ },
661
+ {
662
+ "content": "opo",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false
667
+ },
668
+ {
669
+ "content": "[GERUND_SUBJECT_PREFIX:1ps]",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false
674
+ },
675
+ {
676
+ "content": "gûi",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false
681
+ },
682
+ {
683
+ "content": "[OBJECT:2ps:SUBJECT_1P]",
684
+ "lstrip": false,
685
+ "normalized": false,
686
+ "rstrip": false,
687
+ "single_word": false
688
+ },
689
+ {
690
+ "content": "îa",
691
+ "lstrip": false,
692
+ "normalized": false,
693
+ "rstrip": false,
694
+ "single_word": false
695
+ },
696
+ {
697
+ "content": "îepé",
698
+ "lstrip": false,
699
+ "normalized": false,
700
+ "rstrip": false,
701
+ "single_word": false
702
+ },
703
+ {
704
+ "content": "[SUBJECT_PREFIX:1ppe]",
705
+ "lstrip": false,
706
+ "normalized": false,
707
+ "rstrip": false,
708
+ "single_word": false
709
+ },
710
+ {
711
+ "content": "[OBJECT:1ppi]",
712
+ "lstrip": false,
713
+ "normalized": false,
714
+ "rstrip": false,
715
+ "single_word": false
716
+ },
717
+ {
718
+ "content": "umẽ",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false
723
+ }
724
+ ],
725
+ "eos_token": {
726
+ "content": "</s>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false
731
+ },
732
+ "pad_token": {
733
+ "content": "[PAD]",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false
738
+ },
739
+ "unk_token": {
740
+ "content": "<unk>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false
745
+ }
746
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer_config.json ADDED
@@ -0,0 +1,1775 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "7": {
29
+ "content": "s",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "9": {
37
+ "content": "a",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "15": {
45
+ "content": "e",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "17": {
53
+ "content": "t",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "23": {
61
+ "content": "i",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32": {
69
+ "content": "o",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "52": {
77
+ "content": "r",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "855": {
85
+ "content": "pe",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "3633": {
93
+ "content": "î",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "9008": {
101
+ "content": "abo",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "10443": {
109
+ "content": "û",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32000": {
117
+ "content": "<extra_id_99>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32001": {
125
+ "content": "<extra_id_98>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32002": {
133
+ "content": "<extra_id_97>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32003": {
141
+ "content": "<extra_id_96>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32004": {
149
+ "content": "<extra_id_95>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32005": {
157
+ "content": "<extra_id_94>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32006": {
165
+ "content": "<extra_id_93>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32007": {
173
+ "content": "<extra_id_92>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32008": {
181
+ "content": "<extra_id_91>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32009": {
189
+ "content": "<extra_id_90>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32010": {
197
+ "content": "<extra_id_89>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32011": {
205
+ "content": "<extra_id_88>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32012": {
213
+ "content": "<extra_id_87>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32013": {
221
+ "content": "<extra_id_86>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32014": {
229
+ "content": "<extra_id_85>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32015": {
237
+ "content": "<extra_id_84>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32016": {
245
+ "content": "<extra_id_83>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32017": {
253
+ "content": "<extra_id_82>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32018": {
261
+ "content": "<extra_id_81>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32019": {
269
+ "content": "<extra_id_80>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32020": {
277
+ "content": "<extra_id_79>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32021": {
285
+ "content": "<extra_id_78>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32022": {
293
+ "content": "<extra_id_77>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32023": {
301
+ "content": "<extra_id_76>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32024": {
309
+ "content": "<extra_id_75>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32025": {
317
+ "content": "<extra_id_74>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32026": {
325
+ "content": "<extra_id_73>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32027": {
333
+ "content": "<extra_id_72>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32028": {
341
+ "content": "<extra_id_71>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32029": {
349
+ "content": "<extra_id_70>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32030": {
357
+ "content": "<extra_id_69>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32031": {
365
+ "content": "<extra_id_68>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32032": {
373
+ "content": "<extra_id_67>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32033": {
381
+ "content": "<extra_id_66>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32034": {
389
+ "content": "<extra_id_65>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32035": {
397
+ "content": "<extra_id_64>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32036": {
405
+ "content": "<extra_id_63>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32037": {
413
+ "content": "<extra_id_62>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32038": {
421
+ "content": "<extra_id_61>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32039": {
429
+ "content": "<extra_id_60>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32040": {
437
+ "content": "<extra_id_59>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32041": {
445
+ "content": "<extra_id_58>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32042": {
453
+ "content": "<extra_id_57>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32043": {
461
+ "content": "<extra_id_56>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32044": {
469
+ "content": "<extra_id_55>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32045": {
477
+ "content": "<extra_id_54>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32046": {
485
+ "content": "<extra_id_53>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32047": {
493
+ "content": "<extra_id_52>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32048": {
501
+ "content": "<extra_id_51>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32049": {
509
+ "content": "<extra_id_50>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32050": {
517
+ "content": "<extra_id_49>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32051": {
525
+ "content": "<extra_id_48>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32052": {
533
+ "content": "<extra_id_47>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32053": {
541
+ "content": "<extra_id_46>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32054": {
549
+ "content": "<extra_id_45>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32055": {
557
+ "content": "<extra_id_44>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32056": {
565
+ "content": "<extra_id_43>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32057": {
573
+ "content": "<extra_id_42>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32058": {
581
+ "content": "<extra_id_41>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32059": {
589
+ "content": "<extra_id_40>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32060": {
597
+ "content": "<extra_id_39>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32061": {
605
+ "content": "<extra_id_38>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32062": {
613
+ "content": "<extra_id_37>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32063": {
621
+ "content": "<extra_id_36>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32064": {
629
+ "content": "<extra_id_35>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32065": {
637
+ "content": "<extra_id_34>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32066": {
645
+ "content": "<extra_id_33>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32067": {
653
+ "content": "<extra_id_32>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32068": {
661
+ "content": "<extra_id_31>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32069": {
669
+ "content": "<extra_id_30>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32070": {
677
+ "content": "<extra_id_29>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32071": {
685
+ "content": "<extra_id_28>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32072": {
693
+ "content": "<extra_id_27>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32073": {
701
+ "content": "<extra_id_26>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32074": {
709
+ "content": "<extra_id_25>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32075": {
717
+ "content": "<extra_id_24>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32076": {
725
+ "content": "<extra_id_23>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32077": {
733
+ "content": "<extra_id_22>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32078": {
741
+ "content": "<extra_id_21>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32079": {
749
+ "content": "<extra_id_20>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32080": {
757
+ "content": "<extra_id_19>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32081": {
765
+ "content": "<extra_id_18>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32082": {
773
+ "content": "<extra_id_17>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32083": {
781
+ "content": "<extra_id_16>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32084": {
789
+ "content": "<extra_id_15>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32085": {
797
+ "content": "<extra_id_14>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32086": {
805
+ "content": "<extra_id_13>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32087": {
813
+ "content": "<extra_id_12>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32088": {
821
+ "content": "<extra_id_11>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "32089": {
829
+ "content": "<extra_id_10>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "32090": {
837
+ "content": "<extra_id_9>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "32091": {
845
+ "content": "<extra_id_8>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "32092": {
853
+ "content": "<extra_id_7>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "32093": {
861
+ "content": "<extra_id_6>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "32094": {
869
+ "content": "<extra_id_5>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "32095": {
877
+ "content": "<extra_id_4>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "32096": {
885
+ "content": "<extra_id_3>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "32097": {
893
+ "content": "<extra_id_2>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "32098": {
901
+ "content": "<extra_id_1>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "32099": {
909
+ "content": "<extra_id_0>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "32100": {
917
+ "content": "[GERUND_SUFFIX:CLASS_1]",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "32101": {
925
+ "content": "[NEGATION_SUFFIX:VOWEL_ENDING]",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "32102": {
933
+ "content": "[OBJECT:2pp]",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "32103": {
941
+ "content": "[NEGATION_SUFFIX:CONSONANT_ENDING]",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "32104": {
949
+ "content": "amo",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "32105": {
957
+ "content": "oro",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "32106": {
965
+ "content": "[OBJECT:MUTUAL]",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "32107": {
973
+ "content": "[SUBJECT_PREFIX:1ppi]",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "32108": {
981
+ "content": "[OBJECT_MARKER:3p:MONOSYLLABIC]",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "32109": {
989
+ "content": "[GERUND_SUFFIX:CLASS_1:NASAL_VOWEL]",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "32110": {
997
+ "content": "bo",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "32111": {
1005
+ "content": "́",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "32112": {
1013
+ "content": "[SUBJECT:1ps]",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "32113": {
1021
+ "content": "[SUBJECT:3p]",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "32114": {
1029
+ "content": "[OBJECT_MARKER:3p:DEFAULT]",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "32115": {
1037
+ "content": "îandé",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "32116": {
1045
+ "content": "[OBJECT:1ppe]",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "32117": {
1053
+ "content": "peîepé",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "32118": {
1061
+ "content": "[PERMISSIVE_PREFIX:VOWEL]",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "32119": {
1069
+ "content": "[SUBJECT_PREFIX:2pp]",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "32120": {
1077
+ "content": "[SUBJECT:1ppi]",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "32121": {
1085
+ "content": "í",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "32122": {
1093
+ "content": "[GERUND_SUBJECT_PREFIX:2pp]",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "32123": {
1101
+ "content": "[GERUND_SUBJECT_PREFIX:2ps]",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "32124": {
1109
+ "content": "[OBJECT:1ps]",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "32125": {
1117
+ "content": "[GERUND_SUFFIX:CLASS_1:IYU]",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "32126": {
1125
+ "content": "n'",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "32127": {
1133
+ "content": "a'e",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "32128": {
1141
+ "content": "endé",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "32129": {
1149
+ "content": "ta",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "32130": {
1157
+ "content": "[SUBJECT_PREFIX:2ps]",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ },
1164
+ "32131": {
1165
+ "content": "[SUBJECT:2pp:OBJECT_1P]",
1166
+ "lstrip": false,
1167
+ "normalized": false,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": true
1171
+ },
1172
+ "32132": {
1173
+ "content": "[GERUND_SUBJECT_PREFIX:3p]",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": true
1179
+ },
1180
+ "32133": {
1181
+ "content": "[CIRCUMSTANTIAL_SUFFIX:CONSONANT_ENDING]",
1182
+ "lstrip": false,
1183
+ "normalized": false,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": true
1187
+ },
1188
+ "32134": {
1189
+ "content": "îos",
1190
+ "lstrip": false,
1191
+ "normalized": false,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": true
1195
+ },
1196
+ "32135": {
1197
+ "content": "[NEGATION_PARTICLE:UME]",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "32136": {
1205
+ "content": "pa",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ },
1212
+ "32137": {
1213
+ "content": "[OBJECT:3p]",
1214
+ "lstrip": false,
1215
+ "normalized": false,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": true
1219
+ },
1220
+ "32138": {
1221
+ "content": "peẽ",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": true
1227
+ },
1228
+ "32139": {
1229
+ "content": "e'ym",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": true
1235
+ },
1236
+ "32140": {
1237
+ "content": "îo",
1238
+ "lstrip": false,
1239
+ "normalized": false,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": true
1243
+ },
1244
+ "32141": {
1245
+ "content": "[PLURIFORM_PREFIX:R]",
1246
+ "lstrip": false,
1247
+ "normalized": false,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": true
1251
+ },
1252
+ "32142": {
1253
+ "content": "namo",
1254
+ "lstrip": false,
1255
+ "normalized": false,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": true
1259
+ },
1260
+ "32143": {
1261
+ "content": "[NEGATION_PREFIX]",
1262
+ "lstrip": false,
1263
+ "normalized": false,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": true
1267
+ },
1268
+ "32144": {
1269
+ "content": "[IMPERATIVE_PREFIX:2pp]",
1270
+ "lstrip": false,
1271
+ "normalized": false,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": true
1275
+ },
1276
+ "32145": {
1277
+ "content": "[OBJECT:2pp:SUBJECT_1P]",
1278
+ "lstrip": false,
1279
+ "normalized": false,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": true
1283
+ },
1284
+ "32146": {
1285
+ "content": "[GERUND_SUFFIX:CLASS_1:NASAL_IYU]",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": true
1291
+ },
1292
+ "32147": {
1293
+ "content": "îe",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": true
1299
+ },
1300
+ "32148": {
1301
+ "content": "[OBJECT:REFLEXIVE]",
1302
+ "lstrip": false,
1303
+ "normalized": false,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": true
1307
+ },
1308
+ "32149": {
1309
+ "content": "[PERMISSIVE_PREFIX:CONSONANT]",
1310
+ "lstrip": false,
1311
+ "normalized": false,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": true
1315
+ },
1316
+ "32150": {
1317
+ "content": "[GERUND_SUBJECT_PREFIX:1ppi]",
1318
+ "lstrip": false,
1319
+ "normalized": false,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": true
1323
+ },
1324
+ "32151": {
1325
+ "content": "[OBJECT_MARKER:3p:PLURIFORM_PREFIX:MONOSYLLABIC]",
1326
+ "lstrip": false,
1327
+ "normalized": false,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": true
1331
+ },
1332
+ "32152": {
1333
+ "content": "[NEGATION_PARTICLE:NA]",
1334
+ "lstrip": false,
1335
+ "normalized": false,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": true
1339
+ },
1340
+ "32153": {
1341
+ "content": "[IMPERATIVE_PREFIX:2ps]",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": true
1347
+ },
1348
+ "32154": {
1349
+ "content": "[PLURIFORM_PREFIX:S]",
1350
+ "lstrip": false,
1351
+ "normalized": false,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": true
1355
+ },
1356
+ "32155": {
1357
+ "content": "na",
1358
+ "lstrip": false,
1359
+ "normalized": false,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": true
1363
+ },
1364
+ "32156": {
1365
+ "content": "[NEGATION_SUFFIX]",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": true
1371
+ },
1372
+ "32157": {
1373
+ "content": "ere",
1374
+ "lstrip": false,
1375
+ "normalized": false,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": true
1379
+ },
1380
+ "32158": {
1381
+ "content": "[SUBJECT:1ppe]",
1382
+ "lstrip": false,
1383
+ "normalized": false,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": true
1387
+ },
1388
+ "32159": {
1389
+ "content": "[SUBJECT_PREFIX:1ps]",
1390
+ "lstrip": false,
1391
+ "normalized": false,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": true
1395
+ },
1396
+ "32160": {
1397
+ "content": "[CIRCUMSTANTIAL_SUFFIX:VOWEL_ENDING]",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": true
1403
+ },
1404
+ "32161": {
1405
+ "content": "ramo",
1406
+ "lstrip": false,
1407
+ "normalized": false,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": true
1411
+ },
1412
+ "32162": {
1413
+ "content": "[GERUND_SUFFIX:CLASS_1:R]",
1414
+ "lstrip": false,
1415
+ "normalized": false,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": true
1419
+ },
1420
+ "32163": {
1421
+ "content": "[ROOT]",
1422
+ "lstrip": false,
1423
+ "normalized": false,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": true
1427
+ },
1428
+ "32164": {
1429
+ "content": "mo",
1430
+ "lstrip": false,
1431
+ "normalized": false,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": true
1435
+ },
1436
+ "32165": {
1437
+ "content": "ixé",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": true
1443
+ },
1444
+ "32166": {
1445
+ "content": "[GERUND_SUFFIX:CLASS_2:NASAL_VOWEL_ENDING]",
1446
+ "lstrip": false,
1447
+ "normalized": false,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": true
1451
+ },
1452
+ "32167": {
1453
+ "content": "[OBJECT:3p:MONOSYLLABIC]",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": true
1459
+ },
1460
+ "32168": {
1461
+ "content": "[GERUND_SUBJECT_PREFIX:1ppe]",
1462
+ "lstrip": false,
1463
+ "normalized": false,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": true
1467
+ },
1468
+ "32169": {
1469
+ "content": "oré",
1470
+ "lstrip": false,
1471
+ "normalized": false,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": true
1475
+ },
1476
+ "32170": {
1477
+ "content": "[GERUND_SUFFIX:CLASS_2:ORAL_VOWEL_ENDING]",
1478
+ "lstrip": false,
1479
+ "normalized": false,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": true
1483
+ },
1484
+ "32171": {
1485
+ "content": "[SUBJECT_PREFIX:3p]",
1486
+ "lstrip": false,
1487
+ "normalized": false,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": true
1491
+ },
1492
+ "32172": {
1493
+ "content": "[SUBJECT:2pp]",
1494
+ "lstrip": false,
1495
+ "normalized": false,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": true
1499
+ },
1500
+ "32173": {
1501
+ "content": "[SUBJECT:2ps]",
1502
+ "lstrip": false,
1503
+ "normalized": false,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": true
1507
+ },
1508
+ "32174": {
1509
+ "content": "[GERUND_SUFFIX:CLASS_1:ORAL_VOWEL]",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": true
1515
+ },
1516
+ "32175": {
1517
+ "content": "[GERUND_SUFFIX:CLASS_1:CONSONANT]",
1518
+ "lstrip": false,
1519
+ "normalized": false,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": true
1523
+ },
1524
+ "32176": {
1525
+ "content": "[GERUND_SUFFIX:CLASS_2:DEFAULT]",
1526
+ "lstrip": false,
1527
+ "normalized": false,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": true
1531
+ },
1532
+ "32177": {
1533
+ "content": "[GERUND_SUFFIX:CLASS_1:B]",
1534
+ "lstrip": false,
1535
+ "normalized": false,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": true
1539
+ },
1540
+ "32178": {
1541
+ "content": "[SUBJECT:2ps:OBJECT_1P]",
1542
+ "lstrip": false,
1543
+ "normalized": false,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": true
1547
+ },
1548
+ "32179": {
1549
+ "content": "[OBJECT:2ps]",
1550
+ "lstrip": false,
1551
+ "normalized": false,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": true
1555
+ },
1556
+ "32180": {
1557
+ "content": "[CIRCUMSTANTIAL_SUFFIX:NULL_ENDING]",
1558
+ "lstrip": false,
1559
+ "normalized": false,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": true
1563
+ },
1564
+ "32181": {
1565
+ "content": "nde",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": true
1571
+ },
1572
+ "32182": {
1573
+ "content": "xe",
1574
+ "lstrip": false,
1575
+ "normalized": false,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": true
1579
+ },
1580
+ "32183": {
1581
+ "content": "opo",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": true
1587
+ },
1588
+ "32184": {
1589
+ "content": "[GERUND_SUBJECT_PREFIX:1ps]",
1590
+ "lstrip": false,
1591
+ "normalized": false,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": true
1595
+ },
1596
+ "32185": {
1597
+ "content": "gûi",
1598
+ "lstrip": false,
1599
+ "normalized": false,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": true
1603
+ },
1604
+ "32186": {
1605
+ "content": "[OBJECT:2ps:SUBJECT_1P]",
1606
+ "lstrip": false,
1607
+ "normalized": false,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": true
1611
+ },
1612
+ "32187": {
1613
+ "content": "îa",
1614
+ "lstrip": false,
1615
+ "normalized": false,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": true
1619
+ },
1620
+ "32188": {
1621
+ "content": "îepé",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": true
1627
+ },
1628
+ "32189": {
1629
+ "content": "[SUBJECT_PREFIX:1ppe]",
1630
+ "lstrip": false,
1631
+ "normalized": false,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": true
1635
+ },
1636
+ "32190": {
1637
+ "content": "[OBJECT:1ppi]",
1638
+ "lstrip": false,
1639
+ "normalized": false,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": true
1643
+ },
1644
+ "32191": {
1645
+ "content": "umẽ",
1646
+ "lstrip": false,
1647
+ "normalized": false,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": true
1651
+ },
1652
+ "32192": {
1653
+ "content": "[PAD]",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": true
1659
+ }
1660
+ },
1661
+ "additional_special_tokens": [
1662
+ "[GERUND_SUFFIX:CLASS_1]",
1663
+ "[NEGATION_SUFFIX:VOWEL_ENDING]",
1664
+ "[OBJECT:2pp]",
1665
+ "[NEGATION_SUFFIX:CONSONANT_ENDING]",
1666
+ "amo",
1667
+ "oro",
1668
+ "[OBJECT:MUTUAL]",
1669
+ "[SUBJECT_PREFIX:1ppi]",
1670
+ "[OBJECT_MARKER:3p:MONOSYLLABIC]",
1671
+ "[GERUND_SUFFIX:CLASS_1:NASAL_VOWEL]",
1672
+ "bo",
1673
+ "́",
1674
+ "[SUBJECT:1ps]",
1675
+ "[SUBJECT:3p]",
1676
+ "a",
1677
+ "[OBJECT_MARKER:3p:DEFAULT]",
1678
+ "îandé",
1679
+ "[OBJECT:1ppe]",
1680
+ "peîepé",
1681
+ "[PERMISSIVE_PREFIX:VOWEL]",
1682
+ "t",
1683
+ "[SUBJECT_PREFIX:2pp]",
1684
+ "[SUBJECT:1ppi]",
1685
+ "í",
1686
+ "[GERUND_SUBJECT_PREFIX:2pp]",
1687
+ "[GERUND_SUBJECT_PREFIX:2ps]",
1688
+ "[OBJECT:1ps]",
1689
+ "[GERUND_SUFFIX:CLASS_1:IYU]",
1690
+ "pe",
1691
+ "n'",
1692
+ "s",
1693
+ "a'e",
1694
+ "endé",
1695
+ "ta",
1696
+ "[SUBJECT_PREFIX:2ps]",
1697
+ "[SUBJECT:2pp:OBJECT_1P]",
1698
+ "[GERUND_SUBJECT_PREFIX:3p]",
1699
+ "[CIRCUMSTANTIAL_SUFFIX:CONSONANT_ENDING]",
1700
+ "îos",
1701
+ "[NEGATION_PARTICLE:UME]",
1702
+ "pa",
1703
+ "[OBJECT:3p]",
1704
+ "peẽ",
1705
+ "e'ym",
1706
+ "îo",
1707
+ "[PLURIFORM_PREFIX:R]",
1708
+ "namo",
1709
+ "[NEGATION_PREFIX]",
1710
+ "[IMPERATIVE_PREFIX:2pp]",
1711
+ "[OBJECT:2pp:SUBJECT_1P]",
1712
+ "[GERUND_SUFFIX:CLASS_1:NASAL_IYU]",
1713
+ "îe",
1714
+ "[OBJECT:REFLEXIVE]",
1715
+ "[PERMISSIVE_PREFIX:CONSONANT]",
1716
+ "[GERUND_SUBJECT_PREFIX:1ppi]",
1717
+ "[OBJECT_MARKER:3p:PLURIFORM_PREFIX:MONOSYLLABIC]",
1718
+ "[NEGATION_PARTICLE:NA]",
1719
+ "[IMPERATIVE_PREFIX:2ps]",
1720
+ "r",
1721
+ "[PLURIFORM_PREFIX:S]",
1722
+ "na",
1723
+ "[NEGATION_SUFFIX]",
1724
+ "ere",
1725
+ "[SUBJECT:1ppe]",
1726
+ "[SUBJECT_PREFIX:1ps]",
1727
+ "[CIRCUMSTANTIAL_SUFFIX:VOWEL_ENDING]",
1728
+ "i",
1729
+ "abo",
1730
+ "î",
1731
+ "ramo",
1732
+ "e",
1733
+ "û",
1734
+ "[GERUND_SUFFIX:CLASS_1:R]",
1735
+ "[ROOT]",
1736
+ "mo",
1737
+ "ixé",
1738
+ "[GERUND_SUFFIX:CLASS_2:NASAL_VOWEL_ENDING]",
1739
+ "[OBJECT:3p:MONOSYLLABIC]",
1740
+ "[GERUND_SUBJECT_PREFIX:1ppe]",
1741
+ "oré",
1742
+ "[GERUND_SUFFIX:CLASS_2:ORAL_VOWEL_ENDING]",
1743
+ "[SUBJECT_PREFIX:3p]",
1744
+ "[SUBJECT:2pp]",
1745
+ "[SUBJECT:2ps]",
1746
+ "[GERUND_SUFFIX:CLASS_1:ORAL_VOWEL]",
1747
+ "[GERUND_SUFFIX:CLASS_1:CONSONANT]",
1748
+ "[GERUND_SUFFIX:CLASS_2:DEFAULT]",
1749
+ "[GERUND_SUFFIX:CLASS_1:B]",
1750
+ "[SUBJECT:2ps:OBJECT_1P]",
1751
+ "[OBJECT:2ps]",
1752
+ "[CIRCUMSTANTIAL_SUFFIX:NULL_ENDING]",
1753
+ "nde",
1754
+ "o",
1755
+ "xe",
1756
+ "opo",
1757
+ "[GERUND_SUBJECT_PREFIX:1ps]",
1758
+ "gûi",
1759
+ "[OBJECT:2ps:SUBJECT_1P]",
1760
+ "îa",
1761
+ "îepé",
1762
+ "[SUBJECT_PREFIX:1ppe]",
1763
+ "[OBJECT:1ppi]",
1764
+ "umẽ"
1765
+ ],
1766
+ "clean_up_tokenization_spaces": true,
1767
+ "eos_token": "</s>",
1768
+ "extra_ids": 100,
1769
+ "legacy": true,
1770
+ "model_max_length": 512,
1771
+ "pad_token": "[PAD]",
1772
+ "sp_model_kwargs": {},
1773
+ "tokenizer_class": "T5Tokenizer",
1774
+ "unk_token": "<unk>"
1775
+ }