Upload processor

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: microsoft/trocr-small-handwritten
 tags:
 - generated_from_trainer
+base_model: microsoft/trocr-small-handwritten
 model-index:
 - name: ocr-pemilu
  results: []

preprocessor_config.json

@@ -34,6 +34,7 @@
  0.5,
  0.5
  ],
+ "processor_class": "TrOCRProcessor",
  "resample": 3,
  "rescale_factor": 0.00392156862745098,
  "size": {

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f5e2fefcf793761a76a6bfb8ad35489f9c203b25557673284b6d032f41043f4
+size 1356293

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+ "bos_token": "<s>",
+ "cls_token": "<s>",
+ "eos_token": "</s>",
+ "mask_token": {
+ "content": "<mask>",
+ "lstrip": true,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "<pad>",
+ "sep_token": "</s>",
+ "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "<pad>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "3": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "64001": {
+ "content": "<mask>",
+ "lstrip": true,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<s>",
+ "clean_up_tokenization_spaces": true,
+ "cls_token": "<s>",
+ "eos_token": "</s>",
+ "mask_token": "<mask>",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "<pad>",
+ "processor_class": "TrOCRProcessor",
+ "sep_token": "</s>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "XLMRobertaTokenizer",
+ "unk_token": "<unk>"
+}