Upload TrOCR processor for Ethiopic OCR
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +1 -8
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -43,23 +43,16 @@
|
|
| 43 |
}
|
| 44 |
},
|
| 45 |
"bos_token": "<s>",
|
| 46 |
-
"clean_up_tokenization_spaces":
|
| 47 |
"cls_token": "<s>",
|
| 48 |
"eos_token": "</s>",
|
| 49 |
"errors": "replace",
|
| 50 |
"mask_token": "<mask>",
|
| 51 |
-
"max_length": 128,
|
| 52 |
"model_max_length": 512,
|
| 53 |
-
"pad_to_multiple_of": null,
|
| 54 |
"pad_token": "<pad>",
|
| 55 |
-
"pad_token_type_id": 0,
|
| 56 |
-
"padding_side": "right",
|
| 57 |
"processor_class": "TrOCRProcessor",
|
| 58 |
"sep_token": "</s>",
|
| 59 |
-
"stride": 0,
|
| 60 |
"tokenizer_class": "RobertaTokenizer",
|
| 61 |
"trim_offsets": true,
|
| 62 |
-
"truncation_side": "right",
|
| 63 |
-
"truncation_strategy": "longest_first",
|
| 64 |
"unk_token": "<unk>"
|
| 65 |
}
|
|
|
|
| 43 |
}
|
| 44 |
},
|
| 45 |
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
"cls_token": "<s>",
|
| 48 |
"eos_token": "</s>",
|
| 49 |
"errors": "replace",
|
| 50 |
"mask_token": "<mask>",
|
|
|
|
| 51 |
"model_max_length": 512,
|
|
|
|
| 52 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
| 53 |
"processor_class": "TrOCRProcessor",
|
| 54 |
"sep_token": "</s>",
|
|
|
|
| 55 |
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
"trim_offsets": true,
|
|
|
|
|
|
|
| 57 |
"unk_token": "<unk>"
|
| 58 |
}
|