Hugging Face's logo

Flova
/
omr_transformer

Image-to-Text
Transformers
PyTorch
English
vision-encoder-decoder
image-text-to-text
Inference Endpoints
Model card Files Community
1
Flova commited on
Commit
393ab4f
·
1 Parent(s): 91a26e4

Upload processor

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +0 -1
  2. tokenizer.json +1 -9
  3. tokenizer_config.json +185 -3
special_tokens_map.json CHANGED
@@ -2,6 +2,5 @@
2
  "bos_token": "<s>",
3
  "eos_token": "</s>",
4
  "pad_token": "<pad>",
5
- "sep_token": "<sep/>",
6
  "unk_token": "<unk>"
7
  }
 
2
  "bos_token": "<s>",
3
  "eos_token": "</s>",
4
  "pad_token": "<pad>",
 
5
  "unk_token": "<unk>"
6
  }
tokenizer.json CHANGED
@@ -200,15 +200,6 @@
200
  "rstrip": false,
201
  "normalized": true,
202
  "special": false
203
- },
204
- {
205
- "id": 75,
206
- "content": "<sep/>",
207
- "single_word": false,
208
- "lstrip": false,
209
- "rstrip": false,
210
- "normalized": false,
211
- "special": true
212
  }
213
  ],
214
  "normalizer": {
@@ -233,6 +224,7 @@
233
  "continuing_subword_prefix": null,
234
  "end_of_word_suffix": "</w>",
235
  "fuse_unk": false,
 
236
  "vocab": {
237
  "<unk>": 0,
238
  "'": 1,
 
200
  "rstrip": false,
201
  "normalized": true,
202
  "special": false
 
 
 
 
 
 
 
 
 
203
  }
204
  ],
205
  "normalizer": {
 
224
  "continuing_subword_prefix": null,
225
  "end_of_word_suffix": "</w>",
226
  "fuse_unk": false,
227
+ "byte_fallback": false,
228
  "vocab": {
229
  "<unk>": 0,
230
  "'": 1,
tokenizer_config.json CHANGED
@@ -1,7 +1,189 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "model_max_length": 1000000000000000019884624838656,
3
- "name_or_path": "./model_char_1_fix",
4
  "processor_class": "DonutProcessor",
5
- "special_tokens_map_file": "./model_char_1/special_tokens_map.json",
6
- "tokenizer_class": "PreTrainedTokenizerFast"
7
  }
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "54": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "55": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "56": {
28
+ "content": "<s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "57": {
36
+ "content": "\\repeat ",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "58": {
44
+ "content": "volta ",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "59": {
52
+ "content": "\\key ",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "60": {
60
+ "content": "\\minor ",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "61": {
68
+ "content": "\\major ",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "62": {
76
+ "content": "\\tempo ",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "63": {
84
+ "content": "4=40 ",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "64": {
92
+ "content": "4=60 ",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "65": {
100
+ "content": "4=96 ",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "66": {
108
+ "content": "4=120 ",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "67": {
116
+ "content": "- \\marcato \\ppp ",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "68": {
124
+ "content": "\\pp ",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "69": {
132
+ "content": "\\p ",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "70": {
140
+ "content": "\\mp ",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "71": {
148
+ "content": "\\mf ",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "72": {
156
+ "content": "\\f ",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "73": {
164
+ "content": "\\ff ",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "74": {
172
+ "content": "\\fff ",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ }
179
+ },
180
+ "additional_special_tokens": [],
181
+ "bos_token": "<s>",
182
+ "clean_up_tokenization_spaces": true,
183
+ "eos_token": "</s>",
184
  "model_max_length": 1000000000000000019884624838656,
185
+ "pad_token": "<pad>",
186
  "processor_class": "DonutProcessor",
187
+ "tokenizer_class": "PreTrainedTokenizerFast",
188
+ "unk_token": "<unk>"
189
  }