Upload processor
Browse files- merges.txt +0 -0
- preprocessor_config.json +24 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
- vocab.json +0 -0
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
preprocessor_config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"do_rescale": true,
|
4 |
+
"do_resize": true,
|
5 |
+
"feature_extractor_type": "ViTFeatureExtractor",
|
6 |
+
"image_mean": [
|
7 |
+
0.485,
|
8 |
+
0.456,
|
9 |
+
0.406
|
10 |
+
],
|
11 |
+
"image_processor_type": "ViTImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.229,
|
14 |
+
0.224,
|
15 |
+
0.225
|
16 |
+
],
|
17 |
+
"processor_class": "TrOCRProcessor",
|
18 |
+
"resample": 3,
|
19 |
+
"rescale_factor": 0.00392156862745098,
|
20 |
+
"size": {
|
21 |
+
"height": 1024,
|
22 |
+
"width": 1024
|
23 |
+
}
|
24 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"errors": "replace",
|
7 |
+
"mask_token": "<mask>",
|
8 |
+
"model_max_length": 512,
|
9 |
+
"name_or_path": "/lustre07/scratch/gagan30/arocr/results/arocr/None-v6-scratch/results",
|
10 |
+
"pad_token": "<pad>",
|
11 |
+
"processor_class": "TrOCRProcessor",
|
12 |
+
"sep_token": "</s>",
|
13 |
+
"special_tokens_map_file": null,
|
14 |
+
"tokenizer_class": "RobertaTokenizer",
|
15 |
+
"trim_offsets": true,
|
16 |
+
"unk_token": "<unk>"
|
17 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|