tokenizer_config.json
| 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 | "1024": { |
| 12 | "content": "<pad>", |
| 13 | "lstrip": false, |
| 14 | "normalized": false, |
| 15 | "rstrip": false, |
| 16 | "single_word": false, |
| 17 | "special": true |
| 18 | } |
| 19 | }, |
| 20 | "clean_up_tokenization_spaces": false, |
| 21 | "extra_special_tokens": {}, |
| 22 | "model_max_length": 1000000000000000019884624838656, |
| 23 | "pad_token": "<pad>", |
| 24 | "processor_class": "ParakeetProcessor", |
| 25 | "tokenizer_class": "ParakeetTokenizerFast", |
| 26 | "unk_token": "<unk>" |
| 27 | } |
| 28 | |